Intentionally cause memory leaks on pressing x

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>

.gemini/settings.json

@@ -2,7 +2,6 @@
   "experimental": {
     "extensionReloading": true,
     "modelSteering": true,
-    "memoryManager": false,
     "topicUpdateNarration": true
   },
   "general": {

.gemini/skills/behavioral-evals/references/fixing.md

@@ -33,6 +33,35 @@ evaluation.
     - **Warning**: Do not lose test fidelity by making prompts too direct/easy.
     - **Primary Fix Trigger**: Adjust tool descriptions, system prompts
       (`snippets.ts`), or **modules that contribute to the prompt template**.
+    - Fixes should generally try to improve the prompt
+      `@packages/core/src/prompts/snippets.ts` first.
+    - **Instructional Generality**: Changes to the system prompt should aim to
+      be as general as possible while still accomplishing the goal. Specificity
+      should be added only as needed.
+      - **Principle**: Instead of creating "forbidden lists" for specific syntax
+        (e.g., "Don't use `Object.create()`"), formulate a broader engineering
+        principle that covers the underlying issue (e.g., "Prioritize explicit
+        composition over hidden prototype manipulation"). This improves
+        steerability across a wider range of similar scenarios.
+      - _Low Specificity_: "Follow ecosystem best practices"
+      - _Medium Specificity_: "Utilize OOP and functional best practices, as
+        applicable"
+      - _High Specificity_: Provide ecosystem-specific hints as examples of a
+        broader principle rather than direct instructions. e.g., "NEVER use
+        hacks like bypassing the type system or employing 'hidden' logic (e.g.:
+        reflection, prototype manipulation). Instead, use explicit and idiomatic
+        language features (e.g.: type guards, explicit class instantiation, or
+        object spread) that maintain structural integrity."
+    - **Prompt Simplification**: Once the test is passing, use `ask_user` to
+      determine if prompt simplification is desired.
+      - **Criteria**: Simplification should be attempted only if there are
+        related clauses that can be de-duplicated or reparented under a single
+        heading.
+      - **Verification**: As part of simplification, you MUST identify and run
+        any behavioral eval tests that might be affected by the changes to
+        ensure no regressions are introduced.
+    - Test fixes should not "cheat" by changing a test's `GEMINI.md` file or by
+      updating the test's prompt to instruct it to not repro the bug.
     - **Warning**: Prompts have multiple configurations; ensure your fix targets
       the correct config for the model in question.
 4.  **Architecture Options**: If prompt or instruction tuning triggers no

.github/workflows/chained_e2e.yml

@@ -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

.github/workflows/eval-pr.yml

@@ -1,7 +1,7 @@
 name: 'Evals: PR Evaluation & Regression'
 
 on:
-  pull_request:
+  pull_request_target:
     types: ['opened', 'synchronize', 'reopened', 'ready_for_review']
     paths:
       - 'packages/core/src/prompts/**'
@@ -23,13 +23,73 @@ permissions:
   actions: 'read'
 
 jobs:
+  detect-changes:
+    name: 'Detect Steering Changes'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    # Security: pull_request_target allows secrets, so we must gate carefully.
+    # Detection should not run code from the fork.
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event.pull_request.draft == false"
+    outputs:
+      SHOULD_RUN: '${{ steps.detect.outputs.SHOULD_RUN }}'
+      STEERING_DETECTED: '${{ steps.detect.outputs.STEERING_DETECTED }}'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
+        with:
+          # Check out the trusted code from main for detection
+          fetch-depth: 0
+
+      - name: 'Detect Steering Changes'
+        id: 'detect'
+        env:
+          # Use the PR's head SHA for comparison without checking it out
+          PR_HEAD_SHA: '${{ github.event.pull_request.head.sha }}'
+        run: |
+          # Fetch the fork's PR branch for analysis
+          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr-head
+
+          # Run the trusted script from main
+          SHOULD_RUN=$(node scripts/changed_prompt.js)
+          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
+          echo "SHOULD_RUN=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
+          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
+
+      - name: 'Notify Approval Required'
+        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          RUN_URL="https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
+          COMMENT_BODY="### 🛑 Action Required: Evaluation Approval
+
+          Steering changes have been detected in this PR. To prevent regressions, a maintainer must approve the evaluation run before this PR can be merged.
+
+          **Maintainers:**
+          1. Go to the [**Workflow Run Summary**]($RUN_URL).
+          2. Click the yellow **'Review deployments'** button.
+          3. Select the **'eval-gate'** environment and click **'Approve'**.
+
+          Once approved, the evaluation results will be posted here automatically.
+
+          <!-- eval-approval-notification -->"
+
+          # Check if comment already exists to avoid spamming
+          COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-approval-notification -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
+
+          if [ -z "$COMMENT_ID" ]; then
+            gh pr comment ${{ github.event.pull_request.number }} --body "$COMMENT_BODY"
+          else
+            echo "Updating existing notification comment $COMMENT_ID..."
+            gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body="$COMMENT_BODY"
+          fi
+
   pr-evaluation:
     name: 'Evaluate Steering & Regressions'
+    needs: 'detect-changes'
+    if: "needs.detect-changes.outputs.SHOULD_RUN == 'true'"
+    # Manual approval gate via environment
+    environment: 'eval-gate'
     runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name != 'pull_request' || (github.event.pull_request.draft == false && github.event.pull_request.head.repo.full_name == github.repository))"
-    # External contributors' PRs will wait for approval in this environment
-    environment: |-
-      ${{ (github.event.pull_request.head.repo.full_name == github.repository) && 'internal' || 'external-evals' }}
     env:
       # CENTRALIZED MODEL LIST
       MODEL_LIST: 'gemini-3-flash-preview'
@@ -38,32 +98,40 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
         with:
+          # Check out the fork's PR code for the actual evaluation
+          # This only runs AFTER manual approval
+          ref: '${{ github.event.pull_request.head.sha }}'
           fetch-depth: 0
 
+      - name: 'Remove Approval Notification'
+        # Run even if other steps fail, to ensure we clean up the "Action Required" message
+        if: 'always()'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          PR_NUMBER: '${{ github.event.pull_request.number }}'
+        run: |
+          echo "Debug: PR_NUMBER is '$PR_NUMBER'"
+          # Search for the notification comment by its hidden tag
+          COMMENT_ID=$(gh pr view "$PR_NUMBER" --json comments --jq '.comments[] | select(.body | contains("<!-- eval-approval-notification -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
+          if [ -n "$COMMENT_ID" ]; then
+            echo "Removing notification comment $COMMENT_ID now that run is approved..."
+            gh api -X DELETE "repos/${{ github.repository }}/issues/comments/$COMMENT_ID"
+          fi
+
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
         with:
           node-version-file: '.nvmrc'
           cache: 'npm'
 
-      - name: 'Detect Steering Changes'
-        id: 'detect'
-        run: |
-          SHOULD_RUN=$(node scripts/changed_prompt.js)
-          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
-          echo "SHOULD_RUN=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
-          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
-
       - name: 'Install dependencies'
-        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
         run: 'npm ci'
 
       - name: 'Build project'
-        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
         run: 'npm run build'
 
       - name: 'Analyze PR Content (Guidance)'
-        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
+        if: "needs.detect-changes.outputs.STEERING_DETECTED == 'true'"
         id: 'analysis'
         env:
           GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
@@ -81,7 +149,6 @@ jobs:
           fi
 
       - name: 'Execute Regression Check'
-        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
@@ -96,7 +163,7 @@ jobs:
           fi
 
       - name: 'Post or Update PR Comment'
-        if: "always() && (steps.detect.outputs.STEERING_DETECTED == 'true' || env.REPORT_FILE != '')"
+        if: "always() && (needs.detect-changes.outputs.STEERING_DETECTED == 'true' || env.REPORT_FILE != '')"
         env:
           GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
         run: |
@@ -107,7 +174,7 @@ jobs:
               echo ""
             fi
 
-            if [[ "${{ steps.detect.outputs.STEERING_DETECTED }}" == "true" ]]; then
+            if [[ "${{ needs.detect-changes.outputs.STEERING_DETECTED }}" == "true" ]]; then
               echo "### 🧠 Model Steering Guidance"
               echo ""
               echo "This PR modifies files that affect the model's behavior (prompts, tools, or instructions)."

.github/workflows/evals-nightly.yml

@@ -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

.github/workflows/memory-nightly.yml

@@ -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'

.github/workflows/perf-nightly.yml

@@ -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'

.gitignore

@@ -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/

GEMINI.md

@@ -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`)

docs/adk-replat/adk_migration_design_doc.md

@@ -1,438 +0,0 @@
-# Architectural Design: Gemini CLI to ADK Migration
-
-| Authors: [Adam Weidman](mailto:adamfweidman@google.com)  Contributors:  Reviewers: *See section [Status of this document](#status-of-this-document).* | Status: Draft  Last revised: Apr 7, 2026 Visibility: Confidential |
-| :--- | :--- |
-
----
-
-# Goal
-
-To migrate the Gemini CLI backend execution engine from its legacy fragmented loop structure to the Agent Development Kit (ADK). This migration will unify how agents and subagents are orchestrated, simplify state persistence, and expose a standard `AgentSession` interface for the CLI, future SDK surfaces, and subagent execution.
-
----
-
-# Context
-
-Over time, Gemini CLI has accumulated complex runtime behaviors: multi-tier tool scheduling, policy-driven approvals, payload masking, dynamic routing, and fine-grained telemetry. Integrating these with ADK requires a clean boundary that preserves Gemini CLI semantics without forking ADK core behavior.
-
-The key migration boundary is:
-
-- ADK runtime semantics -> Gemini CLI `AgentProtocol` / `AgentSession`
-- ADK `Event` stream -> Gemini CLI `AgentEvent` stream
-
-That boundary, not the model wrapper alone, is the architectural center of this design.
-
----
-
-# Current State and Proposed Mappings
-
-The following analysis maps existing Gemini CLI components onto ADK capabilities, citing both repositories (`gemini-cli` and `adk-js`).
-
-## Core Runtime Architecture
-
-The migration uses one shared ADK-backed runtime core. Every orchestrated agent, including subagents, is exposed through the same external session contract:
-
-- **Top-level CLI agent** -> `AgentSession`
-- **Future SDK entry point** -> `AgentSession`
-- **Subagent execution** -> `AgentSession`
-
-The runtime owns:
-
-- ADK runner/session lifecycle
-- tool execution
-- policy integration
-- routing, availability, compaction, and masking hooks
-- persistence integration
-
-The adapters own:
-
-- `streamId` timing guarantees
-- replay / reattach behavior
-- translation from ADK `Event` to Gemini CLI `AgentEvent`
-- top-level versus subagent event projection
-- projection of a child `AgentSession` into parent-facing tool or thread events when a subagent is embedded inside another agent
-
-The minimum shape is:
-
-```typescript
-interface PipelineServices {
-  run(
-    request: LlmRequest,
-    baseModel: BaseLlm,
-    stream: boolean,
-  ): AsyncGenerator<LlmResponse, void>;
-  connect(
-    request: LlmRequest,
-    baseModel: BaseLlm,
-  ): Promise<BaseLlmConnection>;
-}
-
-class GcliAgentModel extends BaseLlm {
-  constructor(
-    private baseModel: BaseLlm,
-    private pipeline: PipelineServices,
-  ) {
-    super({model: 'gcli-consolidated'});
-  }
-
-  async *generateContentAsync(
-    request: LlmRequest,
-    stream = false,
-  ): AsyncGenerator<LlmResponse, void> {
-    yield* this.pipeline.run(request, this.baseModel, stream);
-  }
-
-  async connect(request: LlmRequest): Promise<BaseLlmConnection> {
-    return this.pipeline.connect(request, this.baseModel);
-  }
-}
-```
-
-Design rule:
-
-- request mutation stays in the pipeline
-- all orchestrated agents expose the same `AgentSession` contract
-- session lifecycle, replay, approvals, and subagent projection stay in the runtime/adapters
-
-`AdkAgentService` is the composition root for this architecture. It creates and resumes both top-level and subagent `AgentSession`s, builds scoped registries and message-bus instances, wires policy and approval bridges, and embeds child sessions through projection adapters rather than through a separate subagent runtime. See Appendix A for the intended initialization shape.
-
-Composition rule:
-
-- stateful tools are cloned or reinstantiated per session when needed; stateless tools may be shared
-- MCP discovery is shared at the manager layer but registered into session-local tool, prompt, and resource registries
-- `AgentLoopContext` is decomposed into pipeline config, tool/subagent config, session services, callback bridges, and UI projection rather than passed through as a single runtime object
-- file persistence remains Gemini CLI-owned through `GcliFileSessionService extends BaseSessionService`
-
-Persistence rule:
-
-- persisted history is an append-only event log plus derived app/user/session state
-- the session service provides atomic append, crash-safe recovery, and single-writer enforcement
-- rewind truncates the event log, recomputes derived state, and invalidates confirmation/resumption state past the rewind point
-
-## 3.1 Authentication Flexibility
-
-The CLI resolves distinct authentication flows (OAuth, ADC, Compute metadata) using standard Google libraries.
-
-*   **Current State:** Resolved in `packages/core/src/code_assist/oauth2.ts` based on `AuthType`.
-    *   OAuth (`LOGIN_WITH_GOOGLE`)
-    *   Compute Metadata Server (`COMPUTE_ADC`)
-*   **Constraint:** Standard `Gemini` construction in `adk-js/core/src/models/google_llm.ts` still selects backend from constructor-level `apiKey` or Vertex config. It does **not** natively accept Gemini CLI's `AuthClient`-driven auth shape.
-*   **Proposed ADK Mapping:** Phase 1 keeps auth in `GcliAgentModel`. The pipeline resolves refreshed credentials and injects them through `request.config.httpOptions.headers` for unary requests and `request.liveConnectConfig.httpOptions.headers` for live connections.
-*   **Design position:** This is a **bridge**, not native ADK auth parity. Long-term cleanup is either:
-    *   a `CodeAssistLlm extends BaseLlm`, or
-    *   an upstream ADK auth-provider abstraction.
-
-```typescript
-request.config ??= {};
-request.config.httpOptions ??= {};
-request.config.httpOptions.headers = {
-  ...request.config.httpOptions.headers,
-  Authorization: `Bearer ${await auth.getAccessToken()}`,
-};
-```
-
-## 3.2 Model Steering and Mid-Stream Injection
-
-User interjections (hints) course-correct the loop mid-turn.
-
-*   **Current State:** Steering today is tied to the legacy loop and injection services.
-*   **Proposed ADK Mapping (Next-Step Steering):** Supported in Phase 1. `beforeModelCallback` can read queued hints and mutate the next outbound request.
-*   **Proposed ADK Mapping (True Real-Time Interrupt):** Still blocked. TypeScript ADK live runtime is not complete yet, and input-stream semantics are not a stable dependency.
-*   **Phase 1 behavior:** user interjections are queued and prepended to the next model request at tool or turn boundaries. True in-place turn interruption remains out of scope.
-
-## 3.3 State Management and Token Compaction
-
-The CLI truncates large tool responses and summarizes older history to protect token budgets.
-
-*   **Current State:** `ChatCompressionService` in `packages/core/src/context/chatCompressionService.ts` implements reverse token budgeting and a two-phase verification loop.
-*   **Proposed ADK Mapping:** Compaction remains a Gemini CLI-owned history processor invoked by the request pipeline.
-*   **Design position:** Phase 1 does **not** force this onto ADK `BaseContextCompactor`. Gemini CLI compression is currently an outbound-history projection with truncation plus summary/verification sub-calls, while ADK's native compactor path is event-log-centric and mutates session history.
-*   **Design choice:** In Phase 1, compaction mutates **outgoing request history only**. The persisted session event log remains canonical.
-*   **Utility calls:** Compaction sub-calls use the same routing, auth, and availability pipeline as primary model calls.
-
-## 3.4 Model Configuration and Hierarchical Overrides
-
-Dynamic aliasing (for example, temperature scoped to specific sub-commands).
-
-*   **Current State:** Managed by `ModelConfigService`.
-*   **Proposed ADK Mapping:** Resolution stays **request-scoped**, not session-init-scoped.
-*   **Design choice:** The session stores requested model and override state. The runtime resolves the concrete model and temperature on each request, including retries, subagents, and utility calls.
-
-## 3.5 Universal Policy Enforcement (TOML Rules)
-
-Tiered workspace restrictions (for example, read-only tools in untrusted folders).
-
-*   **Current State:** Intercepted at tool scheduling time in legacy scheduler loops.
-*   **Proposed ADK Mapping (Container):** Standardize on ADK `SecurityPlugin`.
-*   **Proposed ADK Mapping (Decision Brain):** Implement `GcliPolicyEngineAdapter implements BasePolicyEngine`.
-*   **Richer context:** The adapter is fed session/mode/subagent/MCP metadata from the runtime so current Gemini CLI policy semantics are preserved as closely as possible.
-*   **Phase 1 suspension flow:** current tool approvals use existing Gemini CLI callbacks. This is intentionally **non-native** and **non-resumable across process death**.
-*   **Long-term target:** move the same policy decisions onto native ADK confirmation/resumption semantics once the broader live/elicitation surface is ready.
-
-```typescript
-interface GcliPolicyBridge {
-  evaluate(context: ToolCallPolicyContext): Promise<PolicyCheckResult>;
-}
-
-export class GcliPolicyEngineAdapter implements BasePolicyEngine {
-  constructor(private readonly policyBridge: GcliPolicyBridge) {}
-
-  async evaluate(context: ToolCallPolicyContext): Promise<PolicyCheckResult> {
-    return this.policyBridge.evaluate(context);
-  }
-}
-```
-
-## 3.6 Telemetry and Observability (Clearcut Tracking)
-
-Hardware metrics, token counts, and step durations.
-
-*   **Current State:** `ClearcutLogger` reads system metrics and relies on deep scheduler hooks for latency accounting.
-*   **Proposed ADK Mapping:** Use a combination of:
-    *   passive event-stream observation, and
-    *   explicit runtime instrumentation where passive ADK events are insufficient.
-*   **Correlation rule:** tool timing is keyed by `functionCall.id`, **not** by `event.id`.
-*   **Design position:** Passive stream interception alone is not assumed to provide full parity.
-
-## 3.7 Dynamic Model Routing and Configurability
-
-Banning a model mid-turn, auto-routing via classifiers, and falling back dynamically without reinitializing the session.
-
-*   **Current State:** Managed by `ModelRouterService` and a chain of `RoutingStrategy` implementations which require the full `RoutingContext` (`history`, `request`, `AbortSignal`).
-*   **Proposed ADK Mapping:** Mostly implementable now, but not “100% possible today” without bridge logic.
-*   **Design choice:** The runtime constructs a proper `RoutingContext` from:
-    *   canonical session history
-    *   the pending user request
-    *   requested model
-    *   abort signal
-*   **Execution point:** routing remains request-scoped and runs before final dispatch.
-*   **Model banning:** treated as routing/fallback selection, not as a synthetic terminal model error.
-
-## 3.8 Fallbacks and Availability Management
-
-Ensuring availability by retrying or switching models when rate limits (429s) or terminal faults occur.
-
-*   **Current State:** Managed by `ModelAvailabilityService` and `ModelPool`.
-*   **Proposed ADK Mapping (Preflight):** availability and fallback selection run before dispatch and before routing commits to a concrete model.
-*   **Proposed ADK Mapping (Post-failure):** handled separately by the runtime. Availability state mutation and retry decisions are not treated as pure request preprocessing.
-*   **Global Application:** utility calls use the same availability/fallback services as primary model calls.
-*   **Retry safety rule:** automatic full-turn replay is allowed only before any side-effecting tool has executed. After side effects, the runtime surfaces the failure and requires explicit user action.
-*   **Phase 1 transition path:** approvals and fallback prompts continue to use existing Gemini CLI callbacks. The doc treats this as an internal bridge, not as an existing standard ADK elicitation API.
-
-## 3.9 State-Driven Mode Switching (Plan Mode)
-
-Dynamically shifting system prompts and active tools when users switch interaction tiers (for example, Chat Mode to Plan Mode).
-
-*   **Current State:** Toggled via `/plan`, which changes `ApprovalMode` and related legacy scheduler behavior.
-*   **Proposed ADK Mapping (Dynamic Prompt):** Use `InstructionProvider` in `LlmAgentConfig.instruction`.
-*   **Proposed ADK Mapping (Dynamic Tooling):** Use a custom `BaseToolset` whose filter is derived from session mode.
-*   **Single source of truth:** mode is session/runtime state derived from current approval mode; prompt, toolset, policy, routing, and UI all consume the same state.
-
-```typescript
-export class GcliModeAwareToolset extends BaseToolset {
-  constructor(
-    private readonly chatTools: BaseTool[],
-    private readonly planTools: BaseTool[],
-  ) {
-    super(() => true);
-  }
-
-  async getTools(context?: ReadonlyContext): Promise<BaseTool[]> {
-    const isPlan = context?.state.get('plan_mode') === true;
-    return isPlan ? this.planTools : this.chatTools;
-  }
-
-  async close(): Promise<void> {}
-}
-```
-
-## 3.10 Tool Output Masking
-
-Managing context window efficiency by offloading bulky tool outputs (for example, shell logs and large file reads) to files.
-
-*   **Current State:** `ToolOutputMaskingService` in `packages/core/src/context/toolOutputMaskingService.ts`.
-*   **Proposed ADK Mapping:** masking runs on **outgoing request history only**, after compaction.
-*   **Design choice:** persisted session history remains the canonical event log. Masking artifacts are session-scoped files referenced from the outbound request projection.
-
----
-
-# 5. Known Gaps in ADK (Gating Blockers)
-
-This section highlights existing gaps in standard ADK that prevent a seamless cutover without bridge logic or upstream changes.
-
-## 5.1 Real-Time User Message Injections (Aborted Turns)
-
-While next-step steering is possible today using `beforeModelCallback`, true real-time interruption requires:
-
-- stable input-stream support, and
-- a complete TypeScript live runtime
-
-Until then, the supported behavior is queued next-step steering at model boundaries, not mid-stream interruption.
-
-## 5.2 Conversation Rewind and State Reversal
-
-Translating manual trajectory drops to ADK runtime state is cumbersome. While Python ADK supports rollback, TypeScript ADK does not yet support it natively.
-
-*   **Resolution Strategy:** Gemini CLI implements rewind in `GcliFileSessionService`, but **not** as a shallow JSON edit. Rewind truncates the event log, recomputes derived state, and invalidates any confirmation/resumption state past the rewind point.
-
-## 5.3 Phase 1 Non-Goals
-
-To keep the migration surface bounded, Phase 1 intentionally excludes:
-
-- non-interactive surfacing of `elicitation_request` / `elicitation_response`
-- true live/bidi interruption semantics
-- native ADK confirmation/resumption parity for approvals and fallback prompts
-
----
-
-# Long-Term Vision: Unification of Agents and Subagents
-
-The long-term vision is that subagents and the primary agent share:
-
-- the same runtime core
-- the same tool definitions
-- the same policy constraints
-- the same configuration schemas
-- the same orchestration contract: `AgentSession`
-
-What may differ is the **embedding adapter**:
-
-- standalone/top-level agent -> consumed directly as `AgentSession`
-- subagent embedded by a parent agent -> projected from its `AgentSession` into parent-facing tool or child-thread events
-
-For SDK-first unification, Gemini CLI orchestration targets `AgentSession`, not a specific ADK tool abstraction. When a subagent must be exposed to a parent model as a tool, Gemini CLI wraps that child `AgentSession` with a `FunctionTool` or custom `BaseTool` projection. `AgentTool` remains the native ADK nested-agent option if we later want full ADK-native nested-agent semantics.
-
----
-
-# Migration Sequence and Unification Checklist
-
-The migration remains non-sequential, but each phase has an explicit success condition:
-
-- [ ] **Non-interactive session parity** `#22699`
-  output/error parity, basic replay correctness, feature-flagged rollout
-- [ ] **Interactive session parity** `#22701`
-  projected event parity, approval bridge wiring, no live-interrupt claim
-- [ ] **Subagent adapter parity** `#22700`
-  tool isolation, activity projection, policy/routing parity for child runs
-- [ ] **ADK session conformance** `#22974`
-  `AgentSession` timing/replay guarantees preserved by the adapter
-- [ ] **Skills parity** `#22966`
-  skills work through the shared runtime without special legacy paths
-- [ ] **Policy and confirmation parity** `#22964`
-  phase-1 callback bridge stable; native confirmation migration scoped separately
-- [ ] **Compaction quality parity** `#22979`
-  comparable summarization and truncation quality to current behavior
-
----
-
-# Appendix A: Initialization Sketch
-
-The main agent and subagents share the same composition root. The difference is whether the resulting `AgentSession` is consumed directly or projected into a parent session.
-
-```typescript
-shared = {
-  baseModel,
-  modelConfigService,
-  availabilityService,
-  router,
-  authService,
-  policyEngine,
-  mcpClientManager,
-  skillCatalog,
-  baseToolCatalog,
-  sessionService,
-}
-
-agentService = new AdkAgentService(shared)
-
-function createSession(definition, parentSessionId?) {
-  sessionRecord = sessionService.create({ definition, parentSessionId })
-  registries = buildScopedRegistries(definition, parentSessionId)
-  pipeline = createPipeline({
-    sessionId: sessionRecord.id,
-    agentId: definition.name,
-    parentSessionId,
-  })
-
-  model = new GcliAgentModel(baseModel, pipeline)
-  runtime = createAdkRuntime({
-    definition,
-    model,
-    sessionRecord,
-    registries,
-    policyEngine,
-  })
-
-  return new AgentSession(new AdkAgentProtocolAdapter(runtime))
-}
-
-function createSubagentTool(definition) {
-  return new FunctionTool(async (input, toolContext) => {
-    child = createSession(definition, toolContext.sessionId)
-    stream = await child.send(userMessage(input))
-
-    for await (event of child.stream(stream)) {
-      projectChildEventToParent(toolContext, event)
-    }
-
-    return collectFinalText()
-  })
-}
-```
-
-Child session projection shape:
-
-```typescript
-emit(tool_request({ requestId, name: definition.name, args: input }))
-
-for await (event of childSession.stream({ streamId })) {
-  if (event.type === 'message' || event.type === 'tool_update') {
-    emit(
-      tool_update({
-        requestId,
-        content: projectDisplayContent(event),
-      }),
-    )
-    continue
-  }
-
-  if (event.type === 'error') {
-    emit(
-      tool_response({
-        requestId,
-        name: definition.name,
-        isError: true,
-        content: projectErrorContent(event),
-      }),
-    )
-    return
-  }
-
-  if (event.type === 'agent_end') {
-    emit(
-      tool_response({
-        requestId,
-        name: definition.name,
-        content: collectFinalChildResult(),
-      }),
-    )
-    return
-  }
-}
-```
-
-Only the final `tool_response` is returned to the parent model. `tool_update` remains a progress/UI projection surface.
-
-Service lifetime split:
-
-- shared across sessions: model config, availability, routing, auth, policy engine, MCP manager, skill catalog
-- scoped per agent/session: `AgentSession`, pipeline instance, tool/prompt/resource registries, derived message bus
-- scoped per invocation: shell process, MCP request, confirmation continuation, tool progress updates
-
----
-
-# Status of this document approvals table {#status-of-this-document}
-
-| #begin-approvals-addon-section See [go/g3a-approvals](http://goto.google.com/g3a-approvals) for instructions on adding reviewers. |
-| :---: |
-.

docs/adk-replat/implementation_details.md

@@ -1,170 +0,0 @@
-# M5 Implementation Details
-
-Companion to `replatforming_design.md`. Per-flow walkthroughs, the routing
-and masking integration recipes, and the seam-level acceptance criteria
-for the early scaffolding PRs. Anything strategic goes back into the
-design doc; this file is the mechanical reference.
-
-## Surface Phases
-
-M5 lands by runnable surface, not by isolated subsystem. Each phase wires
-one call site end-to-end before the next starts.
-
-**Phase A — Non-interactive.** Wires the ADK runtime through the
-non-interactive AgentSession path. Translator, `GcliAgentModel` dispatch
-through `ContentGenerator`, `GcliRoutingProcessor`, 429 retry +
-`handleFallback` + `ModelAvailabilityService` (silent-policy branch swaps
-models without a UI prompt; non-silent intents are unreachable until the
-TUI handler lands), abort, scheduler-backed tool execution,
-`ToolOutputMaskingProcessor`, `LoopDetectionAdkPlugin`, native
-`MCPToolset` (`tools/list` + `tools/call`).
-
-**Phase B — Local subagents.** Same `AdkAgentProtocol` as Phase A; new
-work is subagent-only behavior: factory wiring at
-[`subagent-tool-wrapper.ts:97`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/subagent-tool-wrapper.ts#L97), `complete_task` terminator, grace-period
-recovery turn, scoped execution wrappers (workspace, memory-inbox,
-auto-memory-extraction), and the `onWaitingForConfirmation` activity
-signal. Event propagation to the parent is already an M4 property — no
-new wiring.
-
-**Phase C — Interactive.** Wires the TUI on top of the proven runtime.
-Stream rendering parity, `session_update`, `HookBridgePlugin` + lifecycle
-hooks + `Notification`, plan mode (`InstructionProvider` + mode-aware
-tools), user steering injection, the TUI-registered
-`fallbackModelHandler` callback (unlocks `retry_once`/`stop`/`upgrade`),
-and `/rewind`. **All `/slash commands` live outside the protocol
-layer** — `/rewind` is a slash-command/runtime-adapter concern.
-
-## Walkthroughs
-
-**Typical message:** user input → `AdkAgentProtocol.send` → emit `agent_start` (`BeforeAgent` hook fires) → emit deterministic `session_update{model}` once `config.getModel()` is resolved (do NOT wait on first translator output — first output may be `error` or `usage`) → `Runner.runAsync` → request processors run in one explicit ordered list (ADK defaults through `CONTENT_REQUEST_PROCESSOR`, then `ToolOutputMaskingProcessor`, then `GcliRoutingProcessor`, then the remaining ADK defaults; supplying `config.requestProcessors` replaces ADK's default list, so we must include the defaults ourselves) → tool preprocessing → `beforeModelCallback` runs guards + `BeforeModel` / `BeforeToolSelection` hooks → `GcliAgentModel.generateContentAsync` dispatches through `config.getContentGenerator().generateContentStream(...)` → translator emits `message` + `tool_request` events → `toAdkTool.execute` calls `scheduler.schedule` (`BeforeTool` hook, approval, exec, per-call truncation at 40k chars via [`tool-executor.ts:196-292`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/scheduler/tool-executor.ts#L196-L292), `AfterTool` hook) → feeds back → loop iterates → final `message` events → `agent_end` (`AfterAgent` hook fires). ADK currently dispatches function calls sequentially within a turn ([`functions.ts:345-491`](https://github.com/google/adk-js/blob/main/core/src/agents/functions.ts#L345-L491)), and `scheduler.schedule` queues concurrent callers — no interleaving risk.
-
-**429 fallback:** `GcliAgentModel` owns the same retry loop shape that `GeminiChat` owns today: the content-generator call is inside a `retryWithBackoff` `apiCall` closure, `onPersistent429` calls `handleFallback(config, currentModel, authType, error)`, the handler applies the existing `ModelAvailabilityService` transition and may call `config.activateFallbackMode(...)` for `retry_always`, then the retry loop resets attempts and re-runs the same closure. Do not throw to ADK Runner for retry; `LlmAgent.runAndHandleError` converts thrown model errors into error responses/events. Fallback retry must re-resolve the same current model/config path used by `GcliRoutingProcessor`, and the parity test must cover a fallback that changes the concrete model so we do not dispatch with stale model-specific config or tool declarations. The TUI's `fallbackModelHandler` callback ([`handler.ts:89`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/fallback/handler.ts#L89)) is what unlocks the non-silent intents (`retry_once`, `stop`, `upgrade`); non-interactive runs without one and `handleFallback` returns `null` after silent transitions — that's by design, not a Phase A limitation.
-
-**Loop detection:** `LoopDetectionAdkPlugin.onEventCallback` feeds each `partial:true` delta to `LoopDetectionService.addAndCheck`, and ignores the `partial:false` consolidated event so the accumulated buffer isn't double-counted. On terminate the plugin calls `protocol.abort()` with reason `LOOP_DETECTED`; the protocol emits a synthetic `error{_meta.code:'LOOP_DETECTED'}` event and the abort propagates through `InvocationContext.abortSignal` into `GcliAgentModel.generateContentAsync`. The plugin does NOT mutate the in-flight ADK event and does NOT abort inside `onEventCallback` — that would drop the event before yield ([`runner.ts:332-334`](https://github.com/google/adk-js/blob/main/core/src/runner/runner.ts#L332-L334)).
-
-**`/rewind`:** slash command → slash-command/runtime-adapter (NOT an `AgentProtocol` method) → `ChatRecordingService.rewindTo(id)` truncates `ConversationRecord.messages` ([`chatRecordingService.ts:743-762`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/services/chatRecordingService.ts#L743-L762)) → `sessionService.deleteSession(...)` drops the ADK session → emits `session_update`. Next `send()` calls `sessionService.createSession(...)` then `appendEvent`s each retained `ConversationRecord` message converted to an ADK `Event` (`InMemorySessionService.createSession` has no seed-events parameter — [`in_memory_session_service.ts:54-67`](https://github.com/google/adk-js/blob/main/core/src/sessions/in_memory_session_service.ts#L54-L67)). Conversion fields: ISO timestamp → epoch ms, `type:'user'|'gemini'` → `author`, synthesized deterministic `invocationId` (ConversationRecord has none), `ToolCallRecord` → `FunctionCall` + `FunctionResponse` Parts, thoughts and `TokensSummary` → `actions.customMetadata`. Rewind-injected events are non-partial by construction. Wired in Phase C alongside the rest of the interactive surface.
-
-**Subagent invocation:** Parent ADK `LlmAgent` dispatches an M4 subagent tool → [`subagent-tool-wrapper.ts:97`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/subagent-tool-wrapper.ts#L97) calls the session factory (today it constructs `LocalSubagentInvocation` directly — [`local-invocation.ts:48`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-invocation.ts#L48)) → factory returns an ADK-backed `AgentProtocol` when the flag is on, legacy `LocalSubagentInvocation` otherwise → child constructs its own independent `Runner` with its own `LlmAgent`, plugins, tools, and `GcliSessionService` → child events stream back through the M4 wrapper to the parent as `tool_update`s and a terminal `tool_response`. Both implementations satisfy `AgentProtocol`; the factory selects between them. Existing parent-side telemetry on [`subagent-tool.ts:224`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/subagent-tool.ts#L224) / [`subagent-tool-wrapper.ts:75`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/subagent-tool-wrapper.ts#L75) is the correlation point — no aggregation changes for M5.
-
-## Model routing
-
-ADK ships a `RoutedLlm` that can sit in front of a `BaseLlm` and pick a model
-per call. M5 does not use it. Gemini CLI already owns the routing stack
-(`ModelRouterService`, sequence-sticky model, `applyModelSelection`,
-`ModelConfigService`, `ModelAvailabilityService`, fallback config), and that
-behavior has to stay byte-for-byte the same through the deprecation window.
-Bolting a second routing layer on top would not preserve behavior; it would
-give us two places to keep in sync.
-
-The integration is a custom ADK **request processor**, not a step inside
-`BaseLlm`. ADK runs request processors at [`llm_agent.ts:731-743`](https://github.com/google/adk-js/blob/main/core/src/agents/llm_agent.ts#L731-L743) before
-tool preprocessing ([`llm_agent.ts:746`](https://github.com/google/adk-js/blob/main/core/src/agents/llm_agent.ts#L746)) and before
-`BaseLlm.generateContentAsync` ([`llm_agent.ts:1024`](https://github.com/google/adk-js/blob/main/core/src/agents/llm_agent.ts#L1024)). Selecting the model
-inside `generateContentAsync` is too late — tool declarations and
-generation config have already been materialized from whatever model was
-on the `LlmRequest` when it arrived.
-
-Per-call flow inside `GcliRoutingProcessor.runAsync(invocationContext, llmRequest)`:
-
-1. Build a `RoutingContext` from the masked `llmRequest.contents` + `invocationContext.session` + `Config` + `abortSignal`. Same shape `GeminiClient.processTurn` constructs today.
-2. If the current sequence model is set, keep using it for this tool-call sequence. Otherwise call `config.getModelRouterService().route(routingContext)`. Sequence-sticky state moves to `Config` (or its successor) in PR #14 with named reset points — today it lives on `GeminiClient` ([`client.ts:101`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/core/client.ts#L101), [`:339`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/core/client.ts#L339)).
-3. Run the selection through the existing path: `applyModelSelection(...)`, `ModelConfigService`, `ModelAvailabilityService`. Active model, availability state, fallback config, and resolved generation config stay consistent with the legacy run loop. Set the current sequence model.
-4. Rewrite `llmRequest.model`, `llmRequest.config` (system instructions, generation config), and the tool subset in place. ADK's tool preprocessing then sees the resolved model.
-
-`GcliAgentModel.generateContentAsync` is the content-generator dispatcher plus the legacy-compatible fallback retry loop:
-
-5. Check abort signal.
-6. Map ADK `LlmRequest` → `GenerateContentParameters` and call `config.getContentGenerator().generateContentStream(...)`. Auth (login-with-Google, Gemini API key, Vertex, ADC/compute, gateway, fake responses, logging/recording wrappers) lives inside the content generator implementation — no header injection in this layer.
-7. Stream the result back to ADK, propagating abort. On 429 / persistent quota errors, stay inside the local `retryWithBackoff` loop: call `handleFallback(...)`, let it apply the existing availability/fallback state transition, reset attempts when it returns a retry intent, and re-enter the content-generator call path. A thrown model error is terminal for this ADK iteration unless an ADK `onModelError` callback returns a replacement response; Runner does not automatically re-run request processors.
-
-## Availability service integration
-
-`ModelAvailabilityService` is a self-contained state machine — no Config in its constructor, no Config reads in its methods, just a `Map<ModelId, HealthState>` and the methods that mutate it ([`modelAvailabilityService.ts:41-137`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/availability/modelAvailabilityService.ts#L41-L137)). The class is reusable as-is under ADK. The integration *around* it is Config-driven, and that's what has to be ported.
-
-What feeds the service: `handleFallback` reads the policy chain from Config (`resolvePolicyChain(config)`), takes the failed model as a parameter, and calls `availability.selectFirstAvailable(candidates)`. The failed model comes from [`client.ts:1080`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/core/client.ts#L1080): `const active = this.config.getActiveModel()`. The retry loop re-polls Config between attempts so any mid-loop fallback mutation is picked up cleanly.
-
-What resets the service: two triggers, both outside the service. `reset()` fires from `config.setModel()` ([`config.ts:1813`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/config/config.ts#L1813)), itself triggered by `config.activateFallbackMode()` after a `retry_always` decision. `resetTurn()` fires at the turn boundary — call site not yet verified, probably `client.ts` or `GeminiChat`.
-
-What `GcliAgentModel` has to do: replicate the [`client.ts:1072-1110`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/core/client.ts#L1072-L1110) retry pattern faithfully — pre-call read `config.getActiveModel()`, call `handleFallback(config, currentAttemptModel, authType, error)` on persistent 429, re-poll Config before the next attempt. The `resetTurn` trigger lands at whatever ADK boundary corresponds to "new turn started" — ADK doesn't know about it, so it's an explicit wire.
-
-Subagent note: `AgentLoopContext.config` is shared by reference between parent and child, so parent and subagent share the same `ModelAvailabilityService.health` map and the same `_activeModel`. A subagent fallback mutates parent state. This is legacy behavior, not an ADK regression — flagging it as a documented property, not a Phase A task.
-
-Open Questions: locate the `resetTurn` call site in legacy and map it to an ADK trigger.
-
-## Tool output masking
-
-Two mechanisms, only one is new under ADK:
-
-**Per-call truncation (already done by the scheduler).** When a tool returns, [`tool-executor.ts:196-292`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/scheduler/tool-executor.ts#L196-L292) truncates content > 40k chars for shell and single-text-part MCP tools, writes the full output to `<projectTempDir>/.../<toolName>_<callId>_<random>.txt`, and returns a snippet + file path pointer. This rides for free in M5 because `toAdkTool` calls the scheduler.
-
-**Per-turn batch masking (this is what's new).** Today [`client.ts:637`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/core/client.ts#L637) calls `tryMaskToolOutputs(getHistory())` inside `processTurn`, after compression and before the model call. `ToolOutputMaskingService.mask` walks the whole history, applies a 50k-protection + 30k-prunable-gate sliding window, writes full content to disk, replaces `functionResponse.response` with a `<tool_output_masked>...</tool_output_masked>` preview + pointer ([`toolOutputMaskingService.ts:70-272`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/context/toolOutputMaskingService.ts#L70-L272)). Then `setHistory` syncs to `ChatRecordingService.updateMessagesFromHistory` ([`chatRecordingService.ts:768`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/services/chatRecordingService.ts#L768)).
-
-Under ADK this becomes a custom `RequestProcessor` (`ToolOutputMaskingProcessor`) registered with `LlmAgent` after ADK has built `llmRequest.contents` from `session.events` and before `GcliRoutingProcessor` reads those contents. The processor:
-
-1. Reads `llmRequest.contents` (produced by ADK's `ContentRequestProcessor` from `session.events`).
-2. Calls `ToolOutputMaskingService.mask(llmRequest.contents, config)`. The algorithm is unchanged.
-3. Applies each masked `functionResponse` back to the matching live ADK `Session.events` part by stable event/part identity. Do not use `session.events[i]` ⇔ `llmRequest.contents[i]`; ADK filters, rearranges, and clone-deeps content while building the request ([`content_processor_utils.ts:72-84`](https://github.com/google/adk-js/blob/main/core/src/agents/processors/content_processor_utils.ts#L72-L84)).
-4. Writes the masked `llmRequest.contents` back so the model call and downstream routing see the masked view.
-5. Calls `ChatRecordingService.updateMessagesFromHistory(masked)` so the persisted transcript matches.
-
-`isAlreadyMasked` keeps it idempotent across turns. The disk file path stays the same across runs once we drop the `Math.random()` suffix in the filename (also part of PR #21).
-
-## GcliSessionService
-
-`InMemorySessionService.getSession` does `cloneDeep(session)` ([`in_memory_session_service.ts:88-131`](https://github.com/google/adk-js/blob/main/core/src/sessions/in_memory_session_service.ts#L88-L131)), so the runner operates on a clone of the stored session. Any mutation to `invocationContext.session.events[i]` only persists for the duration of `runAsync`; the next turn fetches a fresh clone. Subclassing it is not enough: its `sessions` store is private ([`in_memory_session_service.ts:40`](https://github.com/google/adk-js/blob/main/core/src/sessions/in_memory_session_service.ts#L40)), and returning the stored reference from `getSession` would make inherited `appendEvent` push the same event twice ([`in_memory_session_service.ts:173-227`](https://github.com/google/adk-js/blob/main/core/src/sessions/in_memory_session_service.ts#L173-L227)).
-
-`GcliSessionService` extends `BaseSessionService`, not `InMemorySessionService`. It owns an authoritative live-session map keyed by `appName/userId/sessionId`. Plugins and request processors that mutate session events (masking is the primary use case) get persistence across turns.
-
-```ts
-class GcliSessionService extends BaseSessionService {
-  private readonly liveSessions = new Map<string, Session>();
-
-  private key(appName: string, userId: string, sessionId: string): string {
-    return `${appName}\0${userId}\0${sessionId}`;
-  }
-
-  override async createSession(req: CreateSessionRequest): Promise<Session> {
-    const session = createSession({
-      id: req.sessionId ?? randomUUID(),
-      appName: req.appName,
-      userId: req.userId,
-      state: req.state ?? {},
-      events: [],
-      lastUpdateTime: Date.now(),
-    });
-    this.liveSessions.set(this.key(req.appName, req.userId, session.id), session);
-    return session;
-  }
-
-  override async getSession(req: GetSessionRequest): Promise<Session | undefined> {
-    const session = this.liveSessions.get(
-      this.key(req.appName, req.userId, req.sessionId),
-    );
-    if (!session || !req.config) return session;
-    // If a caller asks for a filtered view, return a copy so the caller cannot
-    // mutate a truncated live session.
-    return copyWithFilteredEvents(session, req.config);
-  }
-
-  override async appendEvent(req: AppendEventRequest): Promise<Event> {
-    const event = await super.appendEvent(req); // pushes once, skips partials
-    req.session.lastUpdateTime = event.timestamp;
-    return event;
-  }
-}
-```
-
-`listSessions` and `deleteSession` operate on `liveSessions`; they do not delegate to an inner `InMemorySessionService` whose state would drift once `appendEvent` stops delegating. The runner calls `getSession` without `GetSessionConfig`, but preserving filtered-copy behavior for `numRecentEvents` / `afterTimestamp` keeps the service compatible with other ADK callers. If any M5 plugin uses ADK app/user state prefixes, PR #20 ports `InMemorySessionService`'s app-state/user-state handling too; otherwise the service intentionally supports only session-local state.
-
-## PR seam summary
-
-Seam names and acceptance criteria for the foundation PRs. Aside from the `GcliSessionService` code shape above, pseudo-code stubs are intentionally omitted because they drift from real code; the per-PR description owns the implementation specifics.
-
-**PR #1 — Scaffold.** Add `packages/core/src/adk-agent/`. Export `AdkAgentProtocol` (skeleton implementing `AgentProtocol`), `GcliSessionService` (`BaseSessionService` implementation with live session storage), and named seam files for `GcliAgentModel`, `GcliRoutingProcessor`, `ToolOutputMaskingProcessor`, `HookBridgePlugin`, `LoopDetectionAdkPlugin`, `toAdkTool`. All bodies are TODO; compile green; no behavior change. Acceptance: module compiles, file structure matches the architectural sketch, all symbols importable.
-
-**PR #2 — Flag + factory.** Add `experimental.adk.runtimeEnabled` to the settings schema. Implement the session factory: builds an `AdkAgentProtocol` when the runtime flag is on, otherwise the existing legacy implementation. Define precedence with `experimental.adk.agentSessionNoninteractiveEnabled` (the new flag is the runtime selector; the old one continues to gate the non-interactive code path). Acceptance: flag visible in settings, factory unit-tested with both flag states, no production caller wired yet.
-
-**PR #3 — Event-type cleanup.** Delete unused `elicitation_request`, `elicitation_response`, and `elicitations` references that the protocol surface no longer uses.
-
-(`/rewind` is intentionally NOT a foundation PR. It stays in the slash-command/runtime-adapter layer and is wired during Phase C — see Surface Phases above.)

docs/adk-replat/replatforming_design.md

@@ -1,472 +0,0 @@
-# Gemini CLI Replatforming Design
-
-## Goals
-
-1. **Fast ADK Replatforming:** Transition the default Gemini CLI agent to use
-   the ADK execution engine to reduce maintenance overhead on the legacy run
-   loop.
-2. **Reuse Existing Frameworks:** Minimize UI and internal API churn by keeping
-   existing callback mechanisms and frameworks. Specifically, we will _not_
-   rewrite the existing tool approval and model fallback mechanisms to use ADK's
-   `elicitation_request`/`elicitation_response` events. We will reuse the
-   existing message bus and scheduler integrations.
-3. **Unified Core Engine:** Ensure the main interactive chat, non-interactive
-   mode, and subagents execute via the exact same core ADK engine.
-
-## Non-Goals
-
-1. **No Public SDK Readiness:** We are no longer refactoring the core codebase
-   to expose a polished, public-facing SDK.
-2. **No BYOA / Multi-Agent Orchestration:** We are explicitly not building
-   extensibility for third-party agents or external runtime orchestration.
-3. **No UI Modernization for Elicitations:** We will not refactor the React TUI
-   or underlying message bus to adopt standard ADK elicitation events. Tool
-   approvals and system interrupts will continue to use the legacy callback
-   bridges.
-
----
-
-## Open Questions
-
-Where we want feedback. Each links to the section with more context — please weigh in there.
-
-**Milestone 3 — TUI behind `AgentSession`:** scope to be fleshed out by @Jacob Richman; tracked in [#22702](https://github.com/google-gemini/gemini-cli/issues/22702). Exemplar areas listed in [Transition Plan](#transition-plan).
-
-**Milestone 5 — ADK Execution Engine:**
-
-- Loop detection: which event stream feeds the detector, how does soft-recovery get into the next request, and which terminate mechanism (abort / throw / replacement response)? See [Loop detection](#loop-detection).
-- MCP: upstream the missing surface into `MCPToolset`, or keep `McpClient` and pass its outputs as functional tools? See [MCP](#mcp).
-- Slash commands: live outside the protocol layer — scope of the slash-command/runtime-adapter layer TBD. See [Slash commands](#slash-commands).
-
----
-
-## Milestones
-
-1. AgentSession Interface Create `AgentSession` abstraction flexible enough to
-   support the legacy runtime and ADK.
-2. Adapting the Non-Interactive Runtime Adapt the existing non-interactive CLI
-   to conform to the new `AgentSession` API.
-3. Initial TUI Adaptation & Session Creation Move the main agent behind the
-   `AgentSession` interface, adapting the TUI via `useAgentStream` and
-   `LegacyAgentProtocol` while reusing the message bus. **Includes implementing
-   the Agent Creation Factory/Function.**
-4. Subagent Orchestration Decouple subagents from the legacy runtime by wrapping
-   them in the `AgentSession` interface.
-5. ADK Execution Engine Build the unified ADK agent conforming to
-   `AgentSession`, handling all modes (Main, Non-Interactive, Subagents).
-   Adopts ADK's loop and request processors; retains gemini-cli's scheduler,
-   routing, fallback, masking, hooks, compression, recording, and loop
-   detection. See [Detailed Design §5](#5-milestone-5-adk-execution-engine).
-
-## Progress
-
-| Milestone                                    | Owner                            | Status      | Relevant PRs / Branches                                                                                                                                                                                                                                                                                                                                      | Time Estimate |
-| :------------------------------------------- | :------------------------------- | :---------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------ |
-| 1. AgentSession Interface                    | Adam Weidman, Michael Bleigh     | ✅ Complete | [PR #22270](https://github.com/google-gemini/gemini-cli/pull/22270), [PR #23159](https://github.com/google-gemini/gemini-cli/pull/23159), [PR #23548](https://github.com/google-gemini/gemini-cli/pull/23548)                                                                                                                                                | -             |
-| 2. Adapting the Non-Interactive Runtime      | Adam Weidman                     | ✅ Complete | [PR #22984](https://github.com/google-gemini/gemini-cli/pull/22984), [PR #22985](https://github.com/google-gemini/gemini-cli/pull/22985), [PR #22986](https://github.com/google-gemini/gemini-cli/pull/22986), [PR #24439](https://github.com/google-gemini/gemini-cli/pull/24439), [PR #22987](https://github.com/google-gemini/gemini-cli/pull/22987)      | -             |
-| 3. Initial TUI Adaptation & Session Creation | Michael Bleigh                   | 🚧 WIP      | [PR #24275](https://github.com/google-gemini/gemini-cli/pull/24275), [PR #24287](https://github.com/google-gemini/gemini-cli/pull/24287), [PR #24292](https://github.com/google-gemini/gemini-cli/pull/24292), [PR #24297](https://github.com/google-gemini/gemini-cli/pull/24297), [Issue #25046](https://github.com/google-gemini/gemini-cli/issues/25046) | 2-3 weeks     |
-| 4. Subagent Orchestration                    | Adam Weidman                     | 🚧 WIP      | [PR #25302](https://github.com/google-gemini/gemini-cli/pull/25302), [PR #25303](https://github.com/google-gemini/gemini-cli/pull/25303)<br>Branches: `agent-session/local-invocation`, `agent-session/remote-invocation`, `agent-session/agent-tool`                                                                                                        | 1 week        |
-| 5. ADK Execution Engine                      | Adam Weidman, Alexey Kalenkevich | 🚧 WIP      | Alexey Prototype: `eeb9301`. See [M5 Execution Plan](#m5-execution-plan) below for the PR breakdown.                                                                                                                                                                                                                                                          | 4 weeks       |
-| 6. Testing / Validation / Bug fixing         | Adam Weidman, Alexey Kalenkevich | ⏳ Upcoming | Folded into each phase below: non-interactive first, then subagents, then interactive. See [M5 Execution Plan](#m5-execution-plan).                                                                                                                                                                                                                            | 2 weeks       |
-
-_(Note: Previous milestones related to "Unified Elicitations" and "Adopt ADK
-Primitives" have been removed as per the updated Non-Goals)._
-
----
-
-## Detailed Design
-
-### 1. Milestone 1: AgentSession Interface
-
-The `AgentSession` interface is the core abstraction that decouples the TUI from
-the specific agent implementation by proposing a purely event-driven loop
-boundary (`AgentEvent` streams). _For full rationale and design, see the
-[Gemini CLI Agents design document](https://docs.google.com/document/d/1Zv2_VuVNc-PtsFIU5HYApdmaC3EyK5_fNeivYUtL1fs/edit?tab=t.0#heading=h.ok5bx3z7fmr8)._
-
-### 2. Milestone 2: Adapting the Non-Interactive Runtime
-
-The non-interactive runtime conforms to the `AgentSession` API via a legacy
-protocol adapter. This adapter translates internal message bus and scheduler
-events into standard agent event streams. Because this mode does not require
-user interaction, it bypasses complex UI features like tool approvals.
-
-This capability is enabled via the following experimental setting in
-`.gemini/settings.json`:
-
-```json
-{
-  "experimental": {
-    "adk": {
-      "agentSessionNoninteractiveEnabled": true
-    }
-  }
-}
-```
-
-### 3. Milestone 3: Initial TUI Adaptation & Session Creation
-
-Adapting the interactive TUI to consume the `AgentSession` interface is a
-complex, multi-layered effort. The core mechanism is an event-streaming hook
-that subscribes to the session.
-
-#### Current Event Handling State (Legacy Mechanism)
-
-The legacy system relies on a central `Scheduler` and a `MessageBus` to
-orchestrate tool execution and approvals. This is the mechanism we are retaining
-to avoid a full UI refactor:
-
-- **Tool Approvals**: When a tool requires user confirmation, the scheduler
-  calls `resolveConfirmation`
-  ([`scheduler.ts:L663`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/scheduler/scheduler.ts#L663))
-  and updates the tool's status to `AwaitingApproval` in `confirmation.ts`
-  ([`confirmation.ts:L162`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/scheduler/confirmation.ts#L162)).
-- **UI Notification**: The `SchedulerStateManager` publishes a
-  `TOOL_CALLS_UPDATE` event on the message bus
-  ([`state-manager.ts:L254`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/scheduler/state-manager.ts#L254)).
-  The UI hook `useToolScheduler.ts` subscribes to this event to update the React
-  state
-  ([`useToolScheduler.ts:L178`](https://github.com/google-gemini/gemini-cli/blob/main/packages/cli/src/ui/hooks/useToolScheduler.ts#L178)).
-- **User Interaction**: If any tool requires approval, the TUI transitions to a
-  waiting state
-  ([`useGeminiStream.ts:L174`](https://github.com/google-gemini/gemini-cli/blob/main/packages/cli/src/ui/hooks/useGeminiStream.ts#L174))
-  and renders the `ToolConfirmationQueue.tsx` component.
-- **Response Loop**: Once the user makes a decision, `ToolActionsContext.tsx`
-  publishes a `TOOL_CONFIRMATION_RESPONSE`
-  ([`ToolActionsContext.tsx:L150`](https://github.com/google-gemini/gemini-cli/blob/main/packages/cli/src/ui/contexts/ToolActionsContext.tsx#L150)).
-  The scheduler, which is blocked in `waitForConfirmation`
-  ([`confirmation.ts:L168`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/scheduler/confirmation.ts#L168)),
-  receives the response via the message bus and resumes execution.
-
-#### Transition Plan
-
-The interactive `AgentSession` adapter continues to leverage the legacy message bus and scheduler rather than migrating tool approvals to ADK elicitations — minimizing UI churn. The adapter subscribes to the message bus and translates read-only observational events (`tool_update`, `message`, `usage`) into `AgentEvent` streams; interactive/blocking events (tool approvals) stay on the legacy callback path.
-
-Work areas (scope is settled; implementation within each owned by @Jacob Richman in [#22702](https://github.com/google-gemini/gemini-cli/issues/22702)):
-
-- **Event Parity:** standard tool calls, MCP tool calls, and subagent display.
-- **UI Coalescence:** using `agent_start` / `agent_end` for robust UI state management.
-- **Tool-Controlled Display:** per-tool render variants (`FileDiff`, `TodoList`, `AnsiOutput`, etc.) passing through `AgentEvent`, plus tool-triggered out-of-band display state (e.g., IDE diff overlay, plan-mode toggle).
-- **Command Routing:** client-initiated commands (slash commands) routed down to the session; ensuring `abort` works properly.
-- **System Notices:** generic notice events for system notifications.
-
-### 4. Milestone 4: Subagent Orchestration
-
-Subagents invoke both local and remote execution via a unified `AgentTool` that
-wraps them in `AgentSession` instances. This pattern translates low-level
-execution events into standard `AgentEvent`s for the parent session.
-
-### 5. Milestone 5: ADK Execution Engine
-
-Replaces the legacy `GeminiClient` + `Turn` loop with an ADK `Runner` + `LlmAgent`
-behind the existing `AgentSession` interface. ADK contributes the agent loop;
-gemini-cli contributes everything else.
-
-Reference implementation:
-[commit `eeb9301a`](https://github.com/google-gemini/gemini-cli/commit/eeb9301a489a1609f7d74e6c61569d82c5742821).
-
-#### Approach: progressive integration
-
-Start by landing the initial scaffolding: the `adk-agent/` module, the runtime
-flag, the top-level session factory, and the event-type cleanup. These changes
-should compile green, keep the flag off by default, and avoid behavior changes.
-
-Once the initial scaffolding lands, M5 proceeds by **runnable surface**, not
-by isolated subsystem. Each phase wires one call site end-to-end before
-moving to the next:
-
-1. **Non-interactive first.** Run the ADK loop end-to-end without UI. This phase brings up the translator, model dispatch through `GcliAgentModel`, routing, scheduler-backed tool execution, output masking, abort propagation, loop detection, and native MCP. The 429 retry path lands here too: `handleFallback` silently swaps to an available model when the policy allows. The TUI-side prompt that lets a user pick `retry_once` or `stop` is a separate callback registered in Phase C; non-interactive runs without it.
-
-2. **Local subagents second.** Same ADK runtime — no second implementation. The new work is the subagent-only behavior that doesn't exist on the top-level loop: `complete_task` as a mandatory terminator, grace-period retry, scoped workspace/memory wrappers, and the confirmation-waiting activity signal. Event propagation back to the parent already works through the M4 wrapper.
-
-3. **Interactive last.** Wire the TUI once the runtime is proven. Stream rendering, `session_update` behavior, hooks and notifications, plan mode, between-turn steering, the TUI fallback prompt callback, and `/rewind`. All slash commands live outside the protocol layer — `/rewind` is owned by the slash-command/runtime-adapter layer, not `AgentProtocol`.
-
-#### Architectural sketch
-
-```
-                  User input
-                       │
-                       ▼
-            ┌──────────────────────┐
-            │  AgentSession        │  existing wrapper (agent-session.ts:18)
-            └──────────┬───────────┘   SessionStart / SessionEnd hooks
-                       ▼
-            ┌──────────────────────┐
-            │  AdkAgentProtocol    │  send/subscribe/abort/events
-            │                      │  agent_start/end → Before/AfterAgent hooks
-            └──────────┬───────────┘
-                       ▼
-            ┌──────────────────────┐
-            │  GeminiCliAgent      │  extends BaseAgent
-            │   .runAsyncImpl(ctx) │  yields ADK Events
-            └──────────┬───────────┘
-                       ▼
-   ┌─────────────────────────────────────────────┐
-   │  ADK Runner with:                            │
-   │   • GcliSessionService (live event state)    │
-   │   • RequestProcessors (ordered):             │
-   │       ADK defaults through content build     │
-   │       ToolOutputMaskingProcessor             │
-   │       GcliRoutingProcessor                   │
-   │       remaining ADK defaults                 │
-   │   • Plugins:                                 │
-   │       MaxTurns / TokenLimit / MaxTime        │
-   │       HookBridgePlugin                       │
-   │       LoopDetectionAdkPlugin                 │
-   │       Steering injection                     │
-   │                                              │
-   │   LlmAgent loop: call → parse → dispatch →   │
-   │                  feed back → iterate         │
-   └────────┬──────────────────────┬──────────────┘
-            │                      │
-   ┌────────▼─────────┐  ┌─────────▼──────────────┐
-   │ GcliAgentModel   │  │  toAdkTool              │
-   │ • dispatch       │  │  scheduler.schedule({   │
-   │ • fallback retry │  │    callId, name, args   │
-   │ • abort          │  │  }, signal)             │
-   │     │            │  │   → BeforeTool hook     │
-   │     ▼            │  │   → MessageBus policy   │
-   │ ContentGenerator │  │   → tool exec           │
-   │ (auth lives here)│  │   → AfterTool hook      │
-   └──────────────────┘  │   → CompletedToolCall[] │
-                         └─────────────────────────┘
-
-   Runner yields Events → adk-event-translator → AgentEvent[]
-     → AdkAgentProtocol._emit → subscribers (TUI, non-interactive, etc.)
-     └─ ChatRecordingService.recordMessage on final (non-partial) events:
-        user messages, consolidated model responses, usage, tool calls
-```
-
-Per-flow walkthroughs (typical message, 429 fallback, loop detection,
-`/rewind`, subagent invocation) and scaffold sketches live in
-[`implementation_details.md`](./implementation_details.md).
-
-#### Session entry point
-
-`AgentProtocol` is the interface ([`types.ts:11`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agent/types.ts#L11)). `AgentSession` is the
-existing wrapper class that implements `AgentProtocol`
-([`agent-session.ts:18`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agent/agent-session.ts#L18)). M5 adds `AdkAgentProtocol` as a second
-implementation; the existing `AgentSession` wrapper composes either one.
-The whole ADK runtime sits inside one constructor:
-
-```ts
-class AdkAgentProtocol implements AgentProtocol {
-  constructor(opts: {
-    config: Config;                            // model + workspace + services
-                                               // (auth lives inside the ContentGenerator
-                                               //  returned by config.getContentGenerator())
-    instructionProvider: InstructionProvider;  // system prompt (mode-aware)
-    tools: BaseTool[];                         // gemini-cli tools wrapped via toAdkTool;
-                                               // MCP tools come from MCPToolset
-    plugins: BasePlugin[];                     // HookBridge, LoopDetection, MaxTurns, ...
-    requestProcessors: RequestProcessor[];     // full ordered ADK + GCLI processor list
-    sessionService: BaseSessionService;        // GcliSessionService (live in-memory events)
-    parentSessionId?: string;                  // present iff this is a subagent
-  });
-  send(input: AgentSend): Promise<{ streamId: string | null }>;
-  subscribe(cb: (e: AgentEvent) => void): Unsubscribe;
-  abort(): Promise<void>;
-  get events(): readonly AgentEvent[];
-}
-```
-
-#### Hooks
-
-Gemini CLI's `HookSystem` (`packages/core/src/hooks/`) ships 11 events
-that user-defined hooks integrate against. We keep it as the user-facing
-surface; exposing ADK plugins to users would force every existing hook
-to rewrite against different signatures.
-
-Eight of the 11 fire at boundaries our own code controls. Three fire
-mid-loop where only ADK knows the timing. We fire the eight directly;
-the three go through a small ADK plugin.
-
-Owned — fire from our own code:
-
-| Hook | Fires from |
-| --- | --- |
-| `BeforeTool` / `AfterTool` | `scheduler.schedule()` |
-| `BeforeAgent` / `AfterAgent` | `AdkAgentProtocol` on `agent_start` / `agent_end` |
-| `SessionStart` / `SessionEnd` | `AdkAgentProtocol` constructor / `.dispose()` |
-| `PreCompress` | `ChatCompressionService` |
-| `Notification` | `AdkAgentProtocol._emit` on tool-notification events |
-
-Bridged — fire from an ADK plugin callback:
-
-| Hook | Fires from |
-| --- | --- |
-| `BeforeToolSelection` | `HookBridgePlugin.beforeModelCallback` |
-| `BeforeModel` | `HookBridgePlugin.beforeModelCallback` |
-| `AfterModel` | `HookBridgePlugin.afterModelCallback` |
-
-`HookBridgePlugin` is a `BasePlugin` registered with the runner. ADK
-invokes its model callbacks; the body fires the matching gemini-cli
-hook events. One-way, no state.
-
-#### MCP
-
-Today. `mcp-client.ts` is a full server-lifecycle layer: tool discovery, prompt and resource registries, OAuth refresh and 401 recovery, list-change notifications, stdio crash restart, and progress routing.
-
-What ADK provides. `MCPToolset` is tool-scoped — tools/list and tools/call only, for stdio and streamable HTTP ([`mcp_toolset.ts:58`](https://github.com/google/adk-js/blob/main/core/src/tools/mcp/mcp_toolset.ts#L58), [`mcp_tool.ts:65`](https://github.com/google/adk-js/blob/main/core/src/tools/mcp/mcp_tool.ts#L65)), with HTTP auth material set at connection construction ([`mcp_session_manager.ts:38-50`](https://github.com/google/adk-js/blob/main/core/src/tools/mcp/mcp_session_manager.ts#L38-L50)). It builds its own session manager rather than reusing ours, and exposes no path to prompts or resources even though the underlying `@modelcontextprotocol/sdk` client supports them. Stored-token refresh, 401 recovery, list-change handlers, progress notifications, and stdio crash restart are absent.
-
-Open Questions:
-
-- Upstream the missing surface into `MCPToolset`, or keep `McpClient` and pass its outputs (tools, prompts, resources) into the ADK runtime as functional tools?
-
-#### Subagents
-
-A subagent is an `AgentProtocol` with a different system prompt, tool subset, and termination policy. Local subagents run through the same `AdkAgentProtocol` constructor as the top-level session; the session factory selects the runtime and picks which plugins ride along per session. The factory omits `LoopDetectionAdkPlugin` for subagents — they have no loop detection today and terminate via `complete_task` plus the executor's turn/time guards. `Config` and `MessageBus` pass through.
-
-Remote subagents (`RemoteAgentInvocation`, [`remote-invocation.ts:41`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/remote-invocation.ts#L41)) are unaffected — they run on our own A2A integration, and M4's `AgentTool` routes remote vs. local on `definition.kind`. The wiring change is at [`subagent-tool-wrapper.ts:97`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/subagent-tool-wrapper.ts#L97), which today directly constructs `LocalSubagentInvocation` ([`local-invocation.ts:48`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-invocation.ts#L48)) and instead delegates to the session factory.
-
-Legacy reference points for the behaviors Phase B reimplements as plugins / wrappers:
-
-- `complete_task` mandatory terminator ([`local-executor.ts:355`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-executor.ts#L355)) — subagent must call this tool or it errors with `ERROR_NO_COMPLETE_TASK_CALL`.
-- Grace-period recovery turn ([`local-executor.ts:460`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-executor.ts#L460), [`:724`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-executor.ts#L724)) — single final retry with an injected "you must call `complete_task` now" message on recoverable terminate reasons.
-- Scoped execution wrappers ([`local-executor.ts:530-545`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-executor.ts#L530-L545), memory injection at [`:624`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-executor.ts#L624) and [`:1339`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/agents/local-executor.ts#L1339)) — workspace, memory-inbox, auto-memory-extraction wrap the run.
-- `onWaitingForConfirmation` UI signal — propagated through the executor's activity callback today; maps to `BeforeTool` under ADK.
-
-#### Loop detection
-
-Today. `LoopDetectionService` runs two detectors against one strike counter: a sliding-window hash over text/tool-call chunks as they stream ([`loopDetectionService.ts:339-437`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/services/loopDetectionService.ts#L339-L437)), and a per-N-turn semantic check via a side LLM call ([`loopDetectionService.ts:261-311`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/services/loopDetectionService.ts#L261-L311)). Below threshold, `GeminiClient` prepends a "System: Potential loop detected..." nudge to the next request ([`client.ts:1246-1279`](https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/core/client.ts#L1246-L1279)); at threshold, it throws and the turn unwinds.
-
-What ADK provides. Plugin callbacks at every event, around every model call, and on model error (the latter can return a replacement response to keep the loop going). Model output is double-emitted — partial deltas per chunk AND a single consolidated event for the same response — so anything reading the stream has to pick one to avoid double-counting. Exit mechanisms ([`llm_agent.js:634-686`](https://github.com/google/adk-js/blob/main/core/src/agents/llm_agent.ts#L634-L686)): a tripped abort signal returns the generator silently; a thrown Error from inside the model call yields a synthetic error event and ends the turn; a replacement response from `onModelErrorCallback` keeps the loop going. ADK has no direct equivalent of "prepend a system message to the next request"; the closest path is mutating the request contents inside `beforeModelCallback`.
-
-Open Questions:
-
-- Which event stream feeds the detector — partial deltas vs consolidated events?
-- How does the soft-recovery nudge get into the next request?
-- Which terminate mechanism — abort, throw, or replacement response ([`llm_agent.js:634-686`](https://github.com/google/adk-js/blob/main/core/src/agents/llm_agent.ts#L634-L686))?
-
-#### Slash commands
-
-Slash commands live outside the core `AgentProtocol` layer, in a slash-command/runtime-adapter layer wired during Phase C. Specific commands (`/clear`, `/help`, `/memory`, `/compress`, `/rewind`, `/agents`, ...) route differently — some are pure TUI commands, some need to talk to the session, some restart the engine. Implementation details for the adapter layer (per-command routing, abort propagation, and the `ConversationRecord → ADK Event` conversion that `/rewind` requires) are still being expanded.
-
-#### What we reuse from gemini-cli
-
-These existing services remain the source of truth under the ADK runtime.
-M5 adapts to them rather than replacing them:
-
-- `scheduler.schedule()` — tool execution, approval, telemetry, truncation/distillation, `BeforeTool`/`AfterTool` hooks all run inside it (masking is separate — see Tool output masking row)
-- `MessageBus` + `PolicyEngine` — tool approval correlation; legacy approval UI continues to consume bus events
-- `handleFallback` + `ModelAvailabilityService` — 429 fallback + model pool
-- `ModelRouterService` — per-turn model selection (sequence-sticky), authoritative for routing
-- `ModelConfigService` — model resolution per request
-- `LoopDetectionService` — strike-tracked detector
-- `ChatRecordingService` — product-facing conversation persistence + `rewindTo`
-- `ChatCompressionService` — outgoing-history projection only; ADK `Session.events` stays as in-memory loop state, `ConversationRecord` stays authoritative for persistence and `/rewind`
-- `InjectionService` — user steering queue
-- `ToolOutputMaskingService` — masking
-- `HookSystem` + 11 hook events — see Hooks section
-- Existing tool catalog and slash commands
-
-#### What old logic gets dropped under ADK
-
-These are the legacy bits the ADK runtime actually replaces:
-
-- `GeminiClient.processTurn` — replaced by ADK `Runner` + request processors.
-- `GeminiChat` — replaced by ADK `Session` events.
-- `Turn` loop — replaced by ADK `LlmAgent.runAsyncImpl`.
-- `ServerGeminiStreamEvent` — replaced by ADK `Event` → translator → `AgentEvent`.
-
-#### What we don't reuse from ADK
-
-ADK is a framework; we adopt the loop and a few extension points. The
-exclusions below would each be plausible mistakes without explicit
-rejection:
-
-- ADK's built-in `Gemini` (`BaseLlm`) — we run our own `BaseLlm` subclass (`GcliAgentModel`) that dispatches through `config.getContentGenerator()`. Auth (OAuth / Gemini API key / Vertex), fallback retry, recording/logging wrappers, and telemetry all live in our content generator; using ADK's bare client would bypass all of that.
-- `BasePolicyEngine` / `SecurityPlugin` — legacy `MessageBus` + `PolicyEngine` stays. ADK's security plugin would force the approval UI to re-bind against ADK elicitations.
-- `BaseContextCompactor` — `ChatCompressionService` stays. ADK's compactor doesn't know about our token-budget projection rules.
-- ADK `RoutedLlm` — not the routing source of truth. Gemini CLI routing (`ModelRouterService` + `ModelConfigService` + `ModelAvailabilityService`, sequence-sticky model, model-specific tool/config updates) remains authoritative. Routing lives in a custom ADK `RequestProcessor` — see Model routing in implementation_details.md.
-- `BaseSessionService` (file-backed) — `ChatRecordingService` stays. M5 uses a small `GcliSessionService` implementation for in-memory ADK event state.
-- Most ADK plugin callbacks — see Hooks section.
-
-#### Supported under ADK runtime
-
-| Feature | Seam |
-| --- | --- |
-| Auth (OAuth / Gemini API key / Vertex) | `GcliAgentModel` maps ADK `LlmRequest` to `GenerateContentParameters` and dispatches through `config.getContentGenerator()`; auth lives in the content generator implementation |
-| Model fallback (429) | `GcliAgentModel` ports the existing `retryWithBackoff` + `handleFallback` + `ModelAvailabilityService` path; retry stays inside the model wrapper, not ADK Runner |
-| Dynamic routing & availability | `GcliRoutingProcessor` (a custom ADK `RequestProcessor`) consults `ModelRouterService`, `ModelConfigService`, `ModelAvailabilityService`, and the sequence-sticky model, then rewrites `LlmRequest.model` + tool/config before tool preprocessing. No ADK `RoutedLlm` — see Model routing in implementation_details.md |
-| Tool execution | Existing `scheduler.schedule()` |
-| Tool approval | Existing `MessageBus` + `ToolConfirmationQueue.tsx` |
-| Tool output masking | `ToolOutputMaskingProcessor` (a custom ADK `RequestProcessor`) runs `ToolOutputMaskingService.mask`, writes the masked view back to `LlmRequest.contents`, and applies the same masked function responses back to the live ADK session events by event/part identity rather than request-content index; then calls `ChatRecordingService.updateMessagesFromHistory` to sync the transcript. Per-call truncation rides for free inside `scheduler.schedule`. |
-| Chat compression | Existing `ChatCompressionService` (outgoing-history projection only) |
-| Loop detection | `LoopDetectionAdkPlugin` + `LoopDetectionService` — see Loop detection section |
-| Plan mode | `InstructionProvider` + mode-aware tools (mode-change side effects fire from `Config`, runtime-independent) |
-| User steering (between turns) | `beforeModelCallback` consumes `InjectionService` queue |
-| MCP `tools/list` + `tools/call` | Native `MCPToolset` — see MCP section |
-| MCP OAuth | Scoping open — see MCP section |
-| Subagents | M4 `AgentTool` + session factory — see Subagents section |
-| `/rewind` and all `/slash commands` | Live outside the protocol layer. `/rewind` is a slash-command/runtime-adapter concern: the adapter truncates `ConversationRecord` via `ChatRecordingService.rewindTo` and drops the ADK session; next `send()` rebuilds via `appendEvent`. Wired in Phase C (interactive). |
-| User hooks (11 events) | See Hooks section |
-| Max turns / tokens / time | Custom plugins (`MaxTurnsAdkPlugin`, `TokenLimitAdkPlugin`, `MaxTimeAdkPlugin`) |
-| Telemetry / Clearcut | Translator + plugin instrumentation; no new telemetry architecture |
-| Session persistence | `ChatRecordingService` remains the persisted conversation record; ADK `Session.events` (held in `GcliSessionService`) is runtime state only. `streamId` parity only; `eventId` resume is preserved on the protocol interface, see Rewind PR |
-| Skills, slash commands, ACP | Unchanged surfaces (ACP picks runtime by feature flag) |
-| VSCode IDE companion | Unaffected — side-channel to CLI process |
-
-#### Not supported under ADK runtime
-
-| Feature | Status | Rationale |
-| --- | --- | --- |
-| MCP `/mcp prompts` (`prompts/list`, `prompts/get`) | Scoping open — see MCP section | `MCPToolset` exposes no prompts API today. |
-| MCP `/mcp resources` (`resources/list`, `resources/read`) | Scoping open — see MCP section | Same gap as prompts. |
-
----
-
-## M5 Execution Plan
-
-**Foundation** — sequenced first:
-
-| # | Title | Type |
-| --- | --- | --- |
-| 1 | `[AdkAgent] Scaffold adk-agent/ module: AdkAgentProtocol skeleton, GcliSessionService, seam names` | Feature |
-| 2 | `[AdkAgent] Add experimental.adk.runtimeEnabled flag + session factory + define precedence vs existing agentSessionNoninteractiveEnabled` | Feature |
-| 3 | `[AdkAgent] Delete unused elicitation_request/response from AgentEvent types` | Bug |
-
-**Phase A — Non-interactive.** Wires the non-interactive AgentSession entry
-point through the ADK runtime. Proves the core loop without TUI complexity.
-
-| # | Title | Type |
-| --- | --- | --- |
-| A1 | `[AdkAgent] Translator: text + thought + functionCall + functionResponse + usage + error (with _meta.code) + partial/consolidation + agent_start/end; matches event-translator.test.ts shape` | Feature |
-| A2 | `[AdkAgent] GcliAgentModel: dispatch ADK LlmRequest through config.getContentGenerator() + AbortSignal propagation` | Feature |
-| A3 | `[AdkAgent] GcliAgentModel: 429 retry via retryWithBackoff + handleFallback + ModelAvailabilityService (retry inside the model wrapper); silent-policy branch covers non-interactive without a UI handler; covers concrete-model changes` | Feature |
-| A4 | `[AdkAgent] GcliRoutingProcessor (custom ADK RequestProcessor) + move sequence-sticky model owner from GeminiClient to Config with named reset points` | Feature |
-| A5 | `[AdkAgent] Invalid-stream retry + next-speaker continuation (client.ts:818, :845) — port or explicitly mark Not Supported` | Feature |
-| A6 | `[AdkAgent] toAdkTool: route execution through existing scheduler.schedule()` | Feature |
-| A7 | `[AdkAgent] GcliSessionService: BaseSessionService implementation with authoritative live session map and single-append semantics` | Feature |
-| A8 | `[AdkAgent] ToolOutputMaskingProcessor: ToolOutputMaskingService.mask + apply masks back to live session events by event/part identity + sync ChatRecordingService.updateMessagesFromHistory` | Feature |
-| A8a | `[Cleanup] Migrate toolDistillationService off GeminiClient onto BaseLlmClient` | Bug |
-| A9 | `[AdkAgent] Plugins: MaxTurnsAdkPlugin + TokenLimitAdkPlugin + MaxTimeAdkPlugin (beforeModelCallback / before+after)` | Feature |
-| A10 | `[AdkAgent] LoopDetectionAdkPlugin: feed partial:true deltas to detector; on terminate call protocol.abort() with LOOP_DETECTED; protocol emits synthetic error event` | Feature |
-| A11 | `[AdkAgent] MCP: adopt native MCPToolset for stdio + HTTP (tools/list + tools/call only)` | Feature |
-| A11a–d | `[adk-js upstream] MCPToolset capability gaps: prompts/resources, auth lifecycle (token reuse/refresh/401), server lifecycle (list-change, stdio restart, progress, close), and wire upstream prompts/resources into PromptRegistry + ResourceRegistry` | Feature |
-| A12 | `[AdkAgent] Wire non-interactive entry point through session factory to select ADK runtime` | Feature |
-
-**Phase B — Local subagents.** Reuses the Phase-A runtime for child sessions
-once Phase A is wired and runs cleanly.
-
-| # | Title | Type |
-| --- | --- | --- |
-| B1 | `[AdkAgent] Route subagent-tool-wrapper.ts:97 constructor through session factory; return ADK-backed AgentProtocol when the parent runtime is ADK` | Feature |
-| B2 | `[AdkAgent] Subagent: complete_task mandatory terminator plugin (afterModelCallback)` | Feature |
-| B3 | `[AdkAgent] Subagent: grace-period recovery turn (inject "you must call complete_task now" + final retry)` | Feature |
-| B4 | `[AdkAgent] Subagent: scoped execution wrappers (workspace, memory-inbox, auto-memory-extraction)` | Feature |
-| B5 | `[AdkAgent] Subagent: onWaitingForConfirmation activity signal via BeforeTool` | Feature |
-
-**Phase C — Interactive.** Wires the TUI last. By this point the runtime
-loop, model path, tools, fallback, masking, and subagents are already proven
-outside the TUI. **All `/slash commands` live outside the protocol layer.**
-
-| # | Title | Type |
-| --- | --- | --- |
-| C1 | `[AdkAgent] Wire interactive AgentSession through session factory; TUI stream rendering parity` | Feature |
-| C2 | `[AdkAgent] User steering injection via beforeModelCallback` | Feature |
-| C3 | `[AdkAgent] Plan mode: InstructionProvider for system-prompt swapping + mode-aware tool filtering via BaseToolset` | Feature |
-| C4 | `[AdkAgent] HookBridgePlugin: fire BeforeModel / AfterModel / BeforeToolSelection from beforeModelCallback / afterModelCallback` | Feature |
-| C5 | `[AdkAgent] Wire SessionStart / SessionEnd / BeforeAgent / AfterAgent / Notification hooks (Notification fires from AdkAgentProtocol._emit on tool-notification events)` | Feature |
-| C6 | `[AdkAgent] Register TUI fallbackModelHandler callback so non-silent intents (retry_once / stop / upgrade / retry_with_credits) work; handleFallback machinery is already wired in Phase A` | Feature |
-| C7 | `[AdkAgent] /rewind: slash-command/runtime-adapter truncates ConversationRecord via ChatRecordingService.rewindTo, drops ADK session, next send() rebuilds via appendEvent (NOT an AgentProtocol method)` | Feature |
-| C8 | `[AdkAgent] Make ADK runtime the default for all wired surfaces` | Feature |

docs/changelogs/index.md

@@ -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

docs/changelogs/latest.md

@@ -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

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: v0.37.0-preview.1
+# Preview release: v0.38.0-preview.0
 
-Released: April 02, 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).
@@ -13,410 +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 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.1
+https://github.com/google-gemini/gemini-cli/compare/v0.37.0-preview.2...v0.38.0-preview.0

docs/cli/settings.md

@@ -75,7 +75,7 @@ they appear in the UI.
 | Show User Identity                   | `ui.showUserIdentity`                  | Show the signed-in user's identity (e.g. email) in the UI.                                                                                                        | `true`  |
 | Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false` |
 | Render Process                       | `ui.renderProcess`                     | Enable Ink render process for the UI.                                                                                                                             | `true`  |
-| Terminal Buffer                      | `ui.terminalBuffer`                    | Use the new terminal buffer architecture for rendering.                                                                                                           | `true`  |
+| Terminal Buffer                      | `ui.terminalBuffer`                    | Use the new terminal buffer architecture for rendering.                                                                                                           | `false` |
 | Use Background Color                 | `ui.useBackgroundColor`                | Whether to use background colors in the UI.                                                                                                                       | `true`  |
 | Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`  |
 | Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`  |
@@ -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
 

docs/integration-tests.md

@@ -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

docs/reference/configuration.md

@@ -346,7 +346,7 @@ their corresponding top-level category object in your `settings.json` file.
 
 - **`ui.terminalBuffer`** (boolean):
   - **Description:** Use the new terminal buffer architecture for rendering.
-  - **Default:** `true`
+  - **Default:** `false`
   - **Requires restart:** Yes
 
 - **`ui.useBackgroundColor`** (boolean):
@@ -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
 
@@ -1606,6 +1609,12 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
+- **`experimental.adk.agentSessionInteractiveEnabled`** (boolean):
+  - **Description:** Enable the agent session implementation for the interactive
+    CLI.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 - **`experimental.enableAgents`** (boolean):
   - **Description:** Enable local and remote subagents.
   - **Default:** `true`

docs/reference/keyboard-shortcuts.md

@@ -86,13 +86,14 @@ available combinations.
 
 #### Text Input
 
-| Command                    | Action                                                                    | Keys                                                                                |
-| -------------------------- | ------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- |
-| `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+X`                                                                            |
-| `input.paste`              | Paste from the clipboard.                                                 | `Ctrl+V`<br />`Cmd/Win+V`<br />`Alt+V`                                              |
+| Command                              | Action                                                                    | Keys                                                                                |
+| ------------------------------------ | ------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- |
+| `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`<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`                                              |
 
 #### App Controls
 
@@ -100,7 +101,7 @@ available combinations.
 | ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------ |
 | `app.showErrorDetails`        | Toggle detailed error information.                                                                                                                 | `F12`              |
 | `app.showFullTodos`           | Toggle the full TODO list.                                                                                                                         | `Ctrl+T`           |
-| `app.showIdeContextDetail`    | Show IDE context details.                                                                                                                          | `Ctrl+G`           |
+| `app.showIdeContextDetail`    | Show IDE context details.                                                                                                                          | `F4`               |
 | `app.toggleMarkdown`          | Toggle Markdown rendering.                                                                                                                         | `Alt+M`            |
 | `app.toggleCopyMode`          | Toggle copy mode when in alternate buffer mode.                                                                                                    | `F9`               |
 | `app.toggleMouseMode`         | Toggle mouse mode (scrolling and clicking).                                                                                                        | `Ctrl+S`           |

docs/tools/mcp-server.md

@@ -290,7 +290,7 @@ When connecting to an OAuth-enabled server:
 > OAuth authentication requires that your local machine can:
 >
 > - Open a web browser for authentication
-> - Receive redirects on `http://localhost:7777/oauth/callback`
+> - Receive redirects on `http://localhost:<random-port>/oauth/callback` (or a specific port if configured via `redirectUri`)
 
 This feature will not work in:
 
@@ -323,8 +323,8 @@ Use the `/mcp auth` command to manage OAuth authentication:
   if omitted)
 - **`tokenUrl`** (string): OAuth token endpoint (auto-discovered if omitted)
 - **`scopes`** (string[]): Required OAuth scopes
-- **`redirectUri`** (string): Custom redirect URI (defaults to
-  `http://localhost:7777/oauth/callback`)
+- **`redirectUri`** (string): Custom redirect URI (defaults to an OS-assigned
+  random port, e.g., `http://localhost:<random-port>/oauth/callback`)
 - **`tokenParamName`** (string): Query parameter name for tokens in SSE URLs
 - **`audiences`** (string[]): Audiences the token is valid for
 

evals/answer-vs-act.eval.ts

@@ -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,

evals/app-test-helper.ts

@@ -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);
 }

evals/ask_user.eval.ts

@@ -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({

evals/automated-tool-use.eval.ts

@@ -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(

evals/cli_help_delegation.eval.ts

@@ -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: {

evals/component-test-helper.ts

@@ -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);
+}

evals/concurrency-safety.eval.ts

@@ -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: {

evals/edit-locations-eval.eval.ts

@@ -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(

evals/frugalReads.eval.ts

@@ -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({

evals/frugalSearch.eval.ts

@@ -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: {

evals/generalist_agent.eval.ts

@@ -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: {

evals/generalist_delegation.eval.ts

@@ -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: {

evals/gitRepo.eval.ts

@@ -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.',

evals/grep_search_functionality.eval.ts

@@ -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',

evals/hierarchical_memory.eval.ts

@@ -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: {

evals/interactive-hang.eval.ts

@@ -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) => {

evals/model_steering.eval.ts

@@ -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,

evals/plan_mode.eval.ts

@@ -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,

evals/redundant_casts.eval.ts

@@ -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': `

evals/sandbox_recovery.eval.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.',

evals/save_memory.eval.ts

@@ -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: {

evals/shell-efficiency.eval.ts

@@ -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: {

evals/subagents.eval.ts

@@ -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) => {

evals/test-helper.test.ts

@@ -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: {

evals/test-helper.ts

@@ -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>[];

evals/tool_output_masking.eval.ts

@@ -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: {

evals/tracker.eval.ts

@@ -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 } },

evals/unsafe-cloning.eval.ts

@@ -0,0 +1,64 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { evalTest, TestRig } from './test-helper.js';
+
+evalTest('USUALLY_PASSES', {
+  name: 'Reproduction: Agent uses Object.create() for cloning/delegation',
+  prompt:
+    'Create a utility function `createScopedConfig(config: Config, additionalDirectories: string[]): Config` in `packages/core/src/config/scoped-config.ts` that returns a new Config instance. This instance should override `getWorkspaceContext()` to include the additional directories, but delegate all other method calls (like `isPathAllowed` or `validatePathAccess`) to the original config. Note that `Config` is a complex class with private state and cannot be easily shallow-copied or reconstructed.',
+  files: {
+    'packages/core/src/config/config.ts': `
+export class Config {
+  private _internalState = 'secret';
+  constructor(private workspaceContext: any) {}
+  getWorkspaceContext() { return this.workspaceContext; }
+  isPathAllowed(path: string) {
+    return this.getWorkspaceContext().isPathWithinWorkspace(path);
+  }
+  validatePathAccess(path: string) {
+    if (!this.isPathAllowed(path)) return 'Denied';
+    return null;
+  }
+}`,
+    'packages/core/src/utils/workspaceContext.ts': `
+export class WorkspaceContext {
+  constructor(private root: string, private additional: string[] = []) {}
+  getDirectories() { return [this.root, ...this.additional]; }
+  isPathWithinWorkspace(path: string) {
+    return this.getDirectories().some(d => path.startsWith(d));
+  }
+}`,
+    'package.json': JSON.stringify({
+      name: 'test-project',
+      version: '1.0.0',
+      type: 'module',
+    }),
+  },
+  assert: async (rig: TestRig) => {
+    const filePath = 'packages/core/src/config/scoped-config.ts';
+    const content = rig.readFile(filePath);
+
+    if (!content) {
+      throw new Error(`File ${filePath} was not created.`);
+    }
+
+    // Strip comments to avoid false positives.
+    const codeWithoutComments = content.replace(/\/\*[\s\S]*?\*\/|\/\/.*/g, '');
+
+    // Ensure that the agent did not use Object.create() in the implementation.
+    // We check for the call pattern specifically using a regex to avoid false positives in comments.
+    const hasObjectCreate = /\bObject\.create\s*\(/.test(codeWithoutComments);
+    if (hasObjectCreate) {
+      throw new Error(
+        'Evaluation Failed: Agent used Object.create() for cloning. ' +
+          'This behavior is forbidden by the project lint rules (no-restricted-syntax). ' +
+          'Implementation found:\n\n' +
+          content,
+      );
+    }
+  },
+});

evals/update_topic.eval.ts

@@ -215,4 +215,47 @@ export default app;
       expect(fs.existsSync(path.join(rig.testDir, 'src/routes.ts'))).toBe(true);
     },
   });
+
+  /**
+   * Regression test for a bug where update_topic was called multiple times in a
+   * row. We have seen cases of this occurring in earlier versions of the update_topic
+   * system instruction, prior to https://github.com/google-gemini/gemini-cli/pull/24640.
+   * This test demonstrated that there are cases where it can still occur and validates
+   * the prompt change that improves the behavior.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'update_topic should not be called twice in a row',
+    prompt: `
+      We need to build a C compiler.
+
+      Before you write any code, you must formally declare your strategy.
+      First, declare that you will build a Lexer.
+      Then, immediately realize that is wrong and declare that you will actually build a Parser instead.
+
+      Finally, create 'parser.c'.
+    `,
+    files: {
+      'package.json': JSON.stringify({ name: 'test-project' }),
+      '.gemini/settings.json': JSON.stringify({
+        experimental: {
+          topicUpdateNarration: true,
+        },
+      }),
+    },
+    assert: async (rig) => {
+      const toolLogs = rig.readToolLogs();
+
+      // Check for back-to-back update_topic calls
+      for (let i = 1; i < toolLogs.length; i++) {
+        if (
+          toolLogs[i - 1].toolRequest.name === UPDATE_TOPIC_TOOL_NAME &&
+          toolLogs[i].toolRequest.name === UPDATE_TOPIC_TOOL_NAME
+        ) {
+          throw new Error(
+            `Detected back-to-back ${UPDATE_TOPIC_TOOL_NAME} calls at index ${i - 1} and ${i}`,
+          );
+        }
+      }
+    },
+  });
 });

evals/validation_fidelity.eval.ts

@@ -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': `

evals/validation_fidelity_pre_existing_errors.eval.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': `

evals/vitest.config.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: {

integration-tests/browser-agent.concurrent.responses

@@ -0,0 +1,8 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll launch two browser agents concurrently to check both repositories."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to https://example.com and get the page title"}}},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to https://example.com and get the page title"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":20,"totalTokenCount":120}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":15,"totalTokenCount":165}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":15,"totalTokenCount":165}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is Example Domain."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is Example Domain."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":30,"totalTokenCount":230}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Both browser agents completed successfully. Agent 1 and Agent 2 both navigated to their respective pages and confirmed the page titles."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":40,"totalTokenCount":340}}]}

integration-tests/browser-agent.persistent-session.responses

@@ -0,0 +1,8 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I'll browse to example.com twice to verify the content. Let me first check the page title, then check the links on the page."},{"functionCall":{"name":"browser_agent","args":{"task":"Navigate to https://example.com and tell me the page title using the accessibility tree"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":50,"totalTokenCount":150}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"navigate_page","args":{"url":"https://example.com"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":100,"candidatesTokenCount":30,"totalTokenCount":130}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Page title is 'Example Domain'."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"The page title is 'Example Domain'. Now let me check the links on the page."},{"functionCall":{"name":"browser_agent","args":{"task":"Take a snapshot of the accessibility tree on the currently open page and tell me about any links"}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":50,"totalTokenCount":250}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"take_snapshot","args":{}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":150,"candidatesTokenCount":20,"totalTokenCount":170}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"functionCall":{"name":"complete_task","args":{"result":{"success":true,"summary":"Found a link 'More information...' pointing to iana.org."}}}}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":200,"candidatesTokenCount":40,"totalTokenCount":240}}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"I browsed example.com twice using persistent browser sessions:\n\n1. **First visit**: Page title is 'Example Domain'\n2. **Second visit**: Found a link 'More information...' pointing to iana.org\n\nThe browser stayed open between both visits, confirming persistent session management works correctly."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":300,"candidatesTokenCount":60,"totalTokenCount":360}}]}

integration-tests/browser-agent.test.ts

@@ -229,6 +229,51 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
     assertModelHasOutput(result);
   });
 
+  it('should keep browser open across multiple browser_agent invocations', async () => {
+    rig.setup('browser-persistent-session', {
+      fakeResponsesPath: join(
+        __dirname,
+        'browser-agent.persistent-session.responses',
+      ),
+      settings: {
+        agents: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
+            headless: true,
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    const result = await rig.run({
+      args: 'Browse to example.com twice: first get the page title, then check for links.',
+    });
+
+    const toolLogs = rig.readToolLogs();
+    const browserCalls = toolLogs.filter(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+
+    // Both browser_agent invocations must succeed — if the browser was
+    // incorrectly closed after the first call (regression #24210),
+    // the second call would fail.
+    expect(
+      browserCalls.length,
+      'Expected browser_agent to be called twice',
+    ).toBe(2);
+    expect(
+      browserCalls.every((c) => c.toolRequest.success),
+      'Both browser_agent calls should succeed',
+    ).toBe(true);
+
+    assertModelHasOutput(result);
+  });
+
   it('should handle tool confirmation for write_file without crashing', async () => {
     rig.setup('tool-confirmation', {
       fakeResponsesPath: join(
@@ -262,4 +307,48 @@ describe.skipIf(!chromeAvailable)('browser-agent', () => {
 
     await run.expectText('successfully written', 15000);
   });
+
+  it('should handle concurrent browser agents with isolated session mode', async () => {
+    rig.setup('browser-concurrent', {
+      fakeResponsesPath: join(__dirname, 'browser-agent.concurrent.responses'),
+      settings: {
+        agents: {
+          overrides: {
+            browser_agent: {
+              enabled: true,
+            },
+          },
+          browser: {
+            headless: true,
+            // Isolated mode supports concurrent browser agents.
+            // Persistent/existing modes reject concurrent calls to prevent
+            // Chrome profile lock conflicts.
+            sessionMode: 'isolated',
+          },
+        },
+      },
+    });
+
+    const result = await rig.run({
+      args: 'Launch two browser agents concurrently to check example.com',
+    });
+
+    assertModelHasOutput(result);
+
+    const toolLogs = rig.readToolLogs();
+    const browserCalls = toolLogs.filter(
+      (t) => t.toolRequest.name === 'browser_agent',
+    );
+
+    // Both browser_agent invocations should have been called
+    expect(browserCalls.length).toBe(2);
+
+    // Both should complete successfully (no errors)
+    for (const call of browserCalls) {
+      expect(
+        call.toolRequest.success,
+        `browser_agent call failed: ${JSON.stringify(call.toolRequest)}`,
+      ).toBe(true);
+    }
+  });
 });

integration-tests/globalSetup.ts

@@ -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}`);

integration-tests/utf-bom-encoding.test.ts

@@ -5,8 +5,8 @@
  */
 
 import { describe, it, expect, beforeEach, afterEach } from 'vitest';
-import { writeFileSync, readFileSync } from 'node:fs';
-import { join, resolve } from 'node:path';
+import { writeFileSync } from 'node:fs';
+import { join } from 'node:path';
 import { TestRig } from './test-helper.js';
 
 // BOM encoders
@@ -116,21 +116,4 @@ describe('BOM end-to-end integraion', () => {
       'BOM_OK UTF-32BE',
     );
   });
-
-  it('Can describe a PNG file', async () => {
-    const imagePath = resolve(
-      process.cwd(),
-      'docs/assets/gemini-screenshot.png',
-    );
-    const imageContent = readFileSync(imagePath);
-    const filename = 'gemini-screenshot.png';
-    writeFileSync(join(rig.testDir!, filename), imageContent);
-    const prompt = `What is shown in the image ${filename}?`;
-    const output = await rig.run({ args: prompt });
-    await rig.waitForToolCall('read_file');
-    const lower = output.toLowerCase();
-    // The response is non-deterministic, so we just check for some
-    // keywords that are very likely to be in the response.
-    expect(lower.includes('gemini')).toBeTruthy();
-  });
 });

memory-tests/baselines.json

@@ -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"
+    }
+  }
+}

memory-tests/globalSetup.ts

@@ -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);
+    }
+  }
+}

memory-tests/memory-usage.test.ts

@@ -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);
+    }
+  });
+});

memory-tests/memory.idle-startup.responses

@@ -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}]}}]}

memory-tests/memory.multi-function-call.responses

@@ -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}]}}]}

memory-tests/memory.multi-turn.responses

@@ -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}]}}]}

memory-tests/memory.simple-prompt.responses

@@ -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}]}}]}

memory-tests/tsconfig.json

@@ -0,0 +1,12 @@
+{
+  "extends": "../tsconfig.json",
+  "compilerOptions": {
+    "noEmit": true,
+    "allowJs": true
+  },
+  "include": ["**/*.ts"],
+  "references": [
+    { "path": "../packages/core" },
+    { "path": "../packages/test-utils" }
+  ]
+}

memory-tests/vitest.config.ts

@@ -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',
+    },
+  },
+});

package-lock.json

@@ -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",

package.json

@@ -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",

packages/a2a-server/package.json

@@ -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",

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

@@ -1,4 +1,4 @@
-#!/usr/bin/env -S node --no-warnings=DEP0040
+#!/usr/bin/env node
 
 /**
  * @license

packages/cli/index.ts

@@ -1,4 +1,4 @@
-#!/usr/bin/env -S node --no-warnings=DEP0040
+#!/usr/bin/env node
 
 /**
  * @license
@@ -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();

packages/cli/package.json

@@ -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",

packages/cli/src/acp/acpClient.ts

@@ -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);
 

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

@@ -29,5 +29,8 @@ describe('CommandHandler', () => {
 
     const about = parse('/about');
     expect(about.commandToExecute?.name).toBe('about');
+
+    const help = parse('/help');
+    expect(help.commandToExecute?.name).toBe('help');
   });
 });

packages/cli/src/acp/commandHandler.ts

@@ -11,6 +11,7 @@ import { ExtensionsCommand } from './commands/extensions.js';
 import { InitCommand } from './commands/init.js';
 import { RestoreCommand } from './commands/restore.js';
 import { AboutCommand } from './commands/about.js';
+import { HelpCommand } from './commands/help.js';
 
 export class CommandHandler {
   private registry: CommandRegistry;
@@ -26,6 +27,7 @@ export class CommandHandler {
     registry.register(new InitCommand());
     registry.register(new RestoreCommand());
     registry.register(new AboutCommand());
+    registry.register(new HelpCommand(registry));
     return registry;
   }
 

packages/cli/src/acp/commands/help.test.ts

@@ -0,0 +1,53 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect } from 'vitest';
+import { HelpCommand } from './help.js';
+import { CommandRegistry } from './commandRegistry.js';
+import type { Command, CommandContext } from './types.js';
+
+describe('HelpCommand', () => {
+  it('returns formatted help text with sorted commands', async () => {
+    const registry = new CommandRegistry();
+
+    const cmdB: Command = {
+      name: 'bravo',
+      description: 'Bravo command',
+      execute: async () => ({ name: 'bravo', data: '' }),
+    };
+
+    const cmdA: Command = {
+      name: 'alpha',
+      description: 'Alpha command',
+      execute: async () => ({ name: 'alpha', data: '' }),
+    };
+
+    registry.register(cmdB);
+    registry.register(cmdA);
+
+    const helpCommand = new HelpCommand(registry);
+
+    const context = {} as CommandContext;
+
+    const response = await helpCommand.execute(context, []);
+
+    expect(response.name).toBe('help');
+
+    const data = response.data as string;
+
+    expect(data).toContain('Gemini CLI Help:');
+    expect(data).toContain('### Basics');
+    expect(data).toContain('### Commands');
+
+    const lines = data.split('\n');
+    const alphaIndex = lines.findIndex((l) => l.includes('/alpha'));
+    const bravoIndex = lines.findIndex((l) => l.includes('/bravo'));
+
+    expect(alphaIndex).toBeLessThan(bravoIndex);
+    expect(alphaIndex).not.toBe(-1);
+    expect(bravoIndex).not.toBe(-1);
+  });
+});

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

@@ -0,0 +1,50 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type {
+  Command,
+  CommandContext,
+  CommandExecutionResponse,
+} from './types.js';
+import type { CommandRegistry } from './commandRegistry.js';
+
+export class HelpCommand implements Command {
+  readonly name = 'help';
+  readonly description = 'Show available commands';
+
+  constructor(private registry: CommandRegistry) {}
+
+  async execute(
+    _context: CommandContext,
+    _args: string[] = [],
+  ): Promise<CommandExecutionResponse> {
+    const commands = this.registry
+      .getAllCommands()
+      .sort((a, b) => a.name.localeCompare(b.name));
+
+    const lines: string[] = [];
+
+    lines.push('Gemini CLI Help:');
+    lines.push('');
+    lines.push('### Basics');
+    lines.push(
+      '- **Add context**: Use `@` to specify files for context (e.g., `@src/myFile.ts`) to target specific files or folders.',
+    );
+    lines.push('');
+
+    lines.push('### Commands');
+    for (const cmd of commands) {
+      if (cmd.description) {
+        lines.push(`- **/${cmd.name}** - ${cmd.description}`);
+      }
+    }
+
+    return {
+      name: this.name,
+      data: lines.join('\n'),
+    };
+  }
+}

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

@@ -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')}`,
+    };
+  }
+}

packages/cli/src/commands/skills/list.test.ts

@@ -4,8 +4,16 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { vi, describe, it, expect, beforeEach, afterEach } from 'vitest';
-import { coreEvents, type Config } from '@google/gemini-cli-core';
+import {
+  vi,
+  describe,
+  it,
+  expect,
+  beforeEach,
+  afterEach,
+  type MockInstance,
+} from 'vitest';
+import { type Config } from '@google/gemini-cli-core';
 import { handleList, listCommand } from './list.js';
 import { loadSettings, type LoadedSettings } from '../../config/settings.js';
 import { loadCliConfig } from '../../config/config.js';
@@ -32,12 +40,16 @@ vi.mock('../utils.js', () => ({
 describe('skills list command', () => {
   const mockLoadSettings = vi.mocked(loadSettings);
   const mockLoadCliConfig = vi.mocked(loadCliConfig);
+  let stdoutWriteSpy: MockInstance<typeof process.stdout.write>;
 
   beforeEach(async () => {
     vi.clearAllMocks();
     mockLoadSettings.mockReturnValue({
       merged: {},
     } as unknown as LoadedSettings);
+    stdoutWriteSpy = vi
+      .spyOn(process.stdout, 'write')
+      .mockImplementation(() => true);
   });
 
   afterEach(() => {
@@ -56,10 +68,7 @@ describe('skills list command', () => {
 
       await handleList({});
 
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
-        'No skills discovered.',
-      );
+      expect(stdoutWriteSpy).toHaveBeenCalledWith('No skills discovered.\n');
     });
 
     it('should list all discovered skills', async () => {
@@ -87,24 +96,19 @@ describe('skills list command', () => {
 
       await handleList({});
 
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
-        chalk.bold('Discovered Agent Skills:'),
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
+        chalk.bold('Discovered Agent Skills:') + '\n\n',
       );
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining('skill1'),
       );
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining(chalk.green('[Enabled]')),
       );
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining('skill2'),
       );
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining(chalk.red('[Disabled]')),
       );
     });
@@ -135,12 +139,10 @@ describe('skills list command', () => {
 
       // Default
       await handleList({ all: false });
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining('regular'),
       );
-      expect(coreEvents.emitConsoleLog).not.toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).not.toHaveBeenCalledWith(
         expect.stringContaining('builtin'),
       );
 
@@ -148,16 +150,13 @@ describe('skills list command', () => {
 
       // With all: true
       await handleList({ all: true });
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining('regular'),
       );
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining('builtin'),
       );
-      expect(coreEvents.emitConsoleLog).toHaveBeenCalledWith(
-        'log',
+      expect(stdoutWriteSpy).toHaveBeenCalledWith(
         expect.stringContaining(chalk.gray(' [Built-in]')),
       );
     });

packages/cli/src/commands/skills/list.ts

@@ -5,7 +5,6 @@
  */
 
 import type { CommandModule } from 'yargs';
-import { debugLogger } from '@google/gemini-cli-core';
 import { loadSettings } from '../../config/settings.js';
 import { loadCliConfig, type CliArgs } from '../../config/config.js';
 import { exitCli } from '../utils.js';
@@ -42,12 +41,11 @@ export async function handleList(args: { all?: boolean }) {
   });
 
   if (skills.length === 0) {
-    debugLogger.log('No skills discovered.');
+    process.stdout.write('No skills discovered.\n');
     return;
   }
 
-  debugLogger.log(chalk.bold('Discovered Agent Skills:'));
-  debugLogger.log('');
+  process.stdout.write(chalk.bold('Discovered Agent Skills:') + '\n\n');
 
   for (const skill of skills) {
     const status = skill.disabled
@@ -56,10 +54,11 @@ export async function handleList(args: { all?: boolean }) {
 
     const builtinSuffix = skill.isBuiltin ? chalk.gray(' [Built-in]') : '';
 
-    debugLogger.log(`${chalk.bold(skill.name)} ${status}${builtinSuffix}`);
-    debugLogger.log(`  Description: ${skill.description}`);
-    debugLogger.log(`  Location:    ${skill.location}`);
-    debugLogger.log('');
+    process.stdout.write(
+      `${chalk.bold(skill.name)} ${status}${builtinSuffix}\n`,
+    );
+    process.stdout.write(`  Description: ${skill.description}\n`);
+    process.stdout.write(`  Location:    ${skill.location}\n\n`);
   }
 }
 

packages/cli/src/config/config.ts

@@ -938,6 +938,8 @@ export async function loadCliConfig(
       : undefined,
     blockedEnvironmentVariables:
       settings.security?.environmentVariableRedaction?.blocked,
+    allowedEnvironmentVariables:
+      settings.security?.environmentVariableRedaction?.allowed,
     enableEnvironmentVariableRedaction:
       settings.security?.environmentVariableRedaction?.enabled,
     userMemory: memoryContent,

packages/cli/src/config/policy-engine.integration.test.ts

@@ -520,8 +520,8 @@ describe('Policy Engine Integration Tests', () => {
       const readOnlyToolRule = rules.find(
         (r) => r.toolName === 'glob' && !r.subagent,
       );
-      // Priority 70 in default tier → 1.07 (Overriding Plan Mode Deny)
-      expect(readOnlyToolRule?.priority).toBeCloseTo(1.07, 5);
+      // Priority 50 in default tier → 1.05 (Overriding Plan Mode Deny)
+      expect(readOnlyToolRule?.priority).toBeCloseTo(1.05, 5);
 
       // Verify the engine applies these priorities correctly
       expect(
@@ -677,8 +677,8 @@ describe('Policy Engine Integration Tests', () => {
       expect(server1Rule?.priority).toBe(4.1); // Allowed servers (user tier)
 
       const globRule = rules.find((r) => r.toolName === 'glob' && !r.subagent);
-      // Priority 70 in default tier → 1.07
-      expect(globRule?.priority).toBeCloseTo(1.07, 5); // Auto-accept read-only
+      // Priority 50 in default tier → 1.05
+      expect(globRule?.priority).toBeCloseTo(1.05, 5); // Auto-accept read-only
 
       // The PolicyEngine will sort these by priority when it's created
       const engine = new PolicyEngine(config);

packages/cli/src/config/settingsSchema.ts

@@ -757,7 +757,7 @@ const SETTINGS_SCHEMA = {
         label: 'Terminal Buffer',
         category: 'UI',
         requiresRestart: true,
-        default: true,
+        default: false,
         description: 'Use the new terminal buffer architecture for rendering.',
         showInDialog: true,
       },
@@ -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: {
@@ -1970,6 +1971,16 @@ const SETTINGS_SCHEMA = {
             description: 'Enable non-interactive agent sessions.',
             showInDialog: false,
           },
+          agentSessionInteractiveEnabled: {
+            type: 'boolean',
+            label: 'Interactive Agent Session Enabled',
+            category: 'Experimental',
+            requiresRestart: true,
+            default: false,
+            description:
+              'Enable the agent session implementation for the interactive CLI.',
+            showInDialog: false,
+          },
         },
       },
       enableAgents: {

packages/cli/src/gemini.test.tsx

@@ -379,15 +379,30 @@ describe('initializeOutputListenersAndFlush', () => {
 describe('getNodeMemoryArgs', () => {
   let osTotalMemSpy: MockInstance;
   let v8GetHeapStatisticsSpy: MockInstance;
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  let originalConfig: any;
 
   beforeEach(() => {
     osTotalMemSpy = vi.spyOn(os, 'totalmem');
     v8GetHeapStatisticsSpy = vi.spyOn(v8, 'getHeapStatistics');
     delete process.env['GEMINI_CLI_NO_RELAUNCH'];
+
+    originalConfig = process.config;
+    Object.defineProperty(process, 'config', {
+      value: {
+        ...originalConfig,
+        variables: { ...originalConfig?.variables, v8_enable_sandbox: 1 },
+      },
+      configurable: true,
+    });
   });
 
   afterEach(() => {
     vi.restoreAllMocks();
+    Object.defineProperty(process, 'config', {
+      value: originalConfig,
+      configurable: true,
+    });
   });
 
   it('should return empty array if GEMINI_CLI_NO_RELAUNCH is set', () => {
@@ -400,8 +415,10 @@ describe('getNodeMemoryArgs', () => {
     v8GetHeapStatisticsSpy.mockReturnValue({
       heap_size_limit: 8 * 1024 * 1024 * 1024, // 8GB
     });
-    // Target is 50% of 16GB = 8GB. Current is 8GB. No relaunch needed.
-    expect(getNodeMemoryArgs(false)).toEqual([]);
+    // Target is 50% of 16GB = 8GB. Current is 8GB. Relaunch needed for EPT size only.
+    expect(getNodeMemoryArgs(false)).toEqual([
+      '--max-external-pointer-table-size=268435456',
+    ]);
   });
 
   it('should return memory args if current heap limit is insufficient', () => {
@@ -409,8 +426,11 @@ describe('getNodeMemoryArgs', () => {
     v8GetHeapStatisticsSpy.mockReturnValue({
       heap_size_limit: 4 * 1024 * 1024 * 1024, // 4GB
     });
-    // Target is 50% of 16GB = 8GB. Current is 4GB. Relaunch needed.
-    expect(getNodeMemoryArgs(false)).toEqual(['--max-old-space-size=8192']);
+    // Target is 50% of 16GB = 8GB. Current is 4GB. Relaunch needed for both.
+    expect(getNodeMemoryArgs(false)).toEqual([
+      '--max-external-pointer-table-size=268435456',
+      '--max-old-space-size=8192',
+    ]);
   });
 
   it('should log debug info when isDebugMode is true', () => {

packages/cli/src/gemini.tsx

@@ -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';
@@ -111,6 +109,8 @@ export function validateDnsResolutionOrder(
   return defaultValue;
 }
 
+const DEFAULT_EPT_SIZE = (256 * 1024 * 1024).toString();
+
 export function getNodeMemoryArgs(isDebugMode: boolean): string[] {
   const totalMemoryMB = os.totalmem() / (1024 * 1024);
   const heapStats = v8.getHeapStatistics();
@@ -130,16 +130,35 @@ export function getNodeMemoryArgs(isDebugMode: boolean): string[] {
     return [];
   }
 
+  const args: string[] = [];
+
+  // Automatically expand the V8 External Pointer Table to 256MB to prevent
+  // out-of-memory crashes during high native-handle concurrency.
+  // Note: Only supported in specific Node.js versions compiled with V8 Sandbox enabled.
+  const eptFlag = `--max-external-pointer-table-size=${DEFAULT_EPT_SIZE}`;
+  const isV8SandboxEnabled =
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any, @typescript-eslint/no-unsafe-type-assertion
+    (process.config?.variables as any)?.v8_enable_sandbox === 1;
+
+  if (
+    isV8SandboxEnabled &&
+    !process.execArgv.some((arg) =>
+      arg.startsWith('--max-external-pointer-table-size'),
+    )
+  ) {
+    args.push(eptFlag);
+  }
+
   if (targetMaxOldSpaceSizeInMB > currentMaxOldSpaceSizeMb) {
     if (isDebugMode) {
       debugLogger.debug(
         `Need to relaunch with more memory: ${targetMaxOldSpaceSizeInMB.toFixed(2)} MB`,
       );
     }
-    return [`--max-old-space-size=${targetMaxOldSpaceSizeInMB}`];
+    args.push(`--max-old-space-size=${targetMaxOldSpaceSizeInMB}`);
   }
 
-  return [];
+  return args;
 }
 
 export function setupUnhandledRejectionHandler() {
@@ -164,6 +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,
@@ -259,6 +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)
@@ -382,6 +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.
@@ -439,10 +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);
     }
   }
 
@@ -578,40 +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.

packages/cli/src/gemini_cleanup.test.tsx

@@ -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'),
       }),
     );
 

packages/cli/src/interactiveCli.tsx

@@ -107,7 +107,7 @@ export async function startInteractiveUI(
               <TerminalProvider>
                 <ScrollProvider>
                   <OverflowProvider>
-                    <SessionStatsProvider>
+                    <SessionStatsProvider sessionId={config.getSessionId()}>
                       <VimModeProvider>
                         <AppContainer
                           config={config}
@@ -156,8 +156,9 @@ export async function startInteractiveUI(
         useAlternateBuffer || config.getUseTerminalBuffer(),
       patchConsole: false,
       alternateBuffer: useAlternateBuffer,
-      renderProcess: config.getUseRenderProcess(),
       terminalBuffer: config.getUseTerminalBuffer(),
+      renderProcess:
+        config.getUseRenderProcess() && config.getUseTerminalBuffer(),
       incrementalRendering:
         settings.merged.ui.incrementalRendering !== false &&
         useAlternateBuffer &&

packages/cli/src/nonInteractiveCli.test.ts

@@ -71,6 +71,7 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     Scheduler: class {
       schedule = mockSchedulerSchedule;
       cancelAll = vi.fn();
+      dispose = vi.fn();
     },
     isTelemetrySdkInitialized: vi.fn().mockReturnValue(true),
     ChatRecordingService: MockChatRecordingService,

packages/cli/src/nonInteractiveCli.ts

@@ -187,6 +187,7 @@ export async function runNonInteractive(
     };
 
     let errorToHandle: unknown | undefined;
+    let scheduler: Scheduler | undefined;
     try {
       consolePatcher.patch();
 
@@ -215,7 +216,7 @@ export async function runNonInteractive(
       });
 
       const geminiClient = config.getGeminiClient();
-      const scheduler = new Scheduler({
+      scheduler = new Scheduler({
         context: config,
         messageBus: config.getMessageBus(),
         getPreferredEditor: () => undefined,
@@ -528,6 +529,7 @@ export async function runNonInteractive(
       // Cleanup stdin cancellation before other cleanup
       cleanupStdinCancellation();
 
+      scheduler?.dispose();
       consolePatcher.cleanup();
       coreEvents.off(CoreEvent.UserFeedback, handleUserFeedback);
     }

packages/cli/src/nonInteractiveCliAgentSession.test.ts

@@ -71,6 +71,7 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     Scheduler: class {
       schedule = mockSchedulerSchedule;
       cancelAll = vi.fn();
+      dispose = vi.fn();
     },
     isTelemetrySdkInitialized: vi.fn().mockReturnValue(true),
     ChatRecordingService: MockChatRecordingService,

packages/cli/src/nonInteractiveCliAgentSession.ts

@@ -37,6 +37,7 @@ import {
   LegacyAgentSession,
   ToolErrorType,
   geminiPartsToContentParts,
+  debugLogger,
 } from '@google/gemini-cli-core';
 
 import type { Part } from '@google/genai';
@@ -183,6 +184,7 @@ export async function runNonInteractive({
     };
 
     let errorToHandle: unknown | undefined;
+    let scheduler: Scheduler | undefined;
     let abortSession = () => {};
     try {
       consolePatcher.patch();
@@ -214,7 +216,7 @@ export async function runNonInteractive({
       });
 
       const geminiClient = config.getGeminiClient();
-      const scheduler = new Scheduler({
+      scheduler = new Scheduler({
         context: config,
         messageBus: config.getMessageBus(),
         getPreferredEditor: () => undefined,
@@ -599,6 +601,7 @@ export async function runNonInteractive({
             // Explicitly ignore these non-interactive events
             break;
           default:
+            debugLogger.error('Unknown agent event type:', event);
             event satisfies never;
             break;
         }
@@ -610,6 +613,7 @@ export async function runNonInteractive({
       cleanupStdinCancellation();
       abortController.signal.removeEventListener('abort', abortSession);
 
+      scheduler?.dispose();
       consolePatcher.cleanup();
       coreEvents.off(CoreEvent.UserFeedback, handleUserFeedback);
     }

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

@@ -136,6 +136,7 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
     getRetryFetchErrors: vi.fn().mockReturnValue(true),
     getEnableShellOutputEfficiency: vi.fn().mockReturnValue(true),
     getShellToolInactivityTimeout: vi.fn().mockReturnValue(300000),
+    getRequestTimeoutMs: vi.fn().mockReturnValue(undefined),
     getShellExecutionConfig: vi.fn().mockReturnValue({
       sandboxManager: new NoopSandboxManager(),
       sanitizationConfig: {

packages/cli/src/test-utils/render.tsx

@@ -504,6 +504,8 @@ const baseMockUiState = {
   history: [],
   renderMarkdown: true,
   streamingState: StreamingState.Idle,
+  isConfigInitialized: true,
+  isAuthenticating: false,
   terminalWidth: 100,
   terminalHeight: 40,
   currentModel: 'gemini-pro',
@@ -598,6 +600,9 @@ const mockUIActions: UIActions = {
   clearAccountSuspension: vi.fn(),
 };
 
+import { type TextBuffer } from '../ui/components/shared/text-buffer.js';
+import { InputContext, type InputState } from '../ui/contexts/InputContext.js';
+
 let capturedOverflowState: OverflowState | undefined;
 let capturedOverflowActions: OverflowActions | undefined;
 const ContextCapture: React.FC<{ children: React.ReactNode }> = ({
@@ -614,6 +619,7 @@ export const renderWithProviders = async (
     shellFocus = true,
     settings = mockSettings,
     uiState: providedUiState,
+    inputState: providedInputState,
     width,
     mouseEventsEnabled = false,
     config,
@@ -625,6 +631,7 @@ export const renderWithProviders = async (
     shellFocus?: boolean;
     settings?: LoadedSettings;
     uiState?: Partial<UIState>;
+    inputState?: Partial<InputState>;
     width?: number;
     mouseEventsEnabled?: boolean;
     config?: Config;
@@ -659,6 +666,18 @@ export const renderWithProviders = async (
     },
   ) as UIState;
 
+  const inputState = {
+    buffer: { text: '' } as unknown as TextBuffer,
+    userMessages: [],
+    shellModeActive: false,
+    showEscapePrompt: false,
+    copyModeEnabled: false,
+    inputWidth: 80,
+    suggestionsWidth: 40,
+    ...(providedUiState as unknown as Partial<InputState>),
+    ...providedInputState,
+  };
+
   if (persistentState?.get) {
     persistentStateMock.get.mockImplementation(persistentState.get);
   }
@@ -708,63 +727,65 @@ export const renderWithProviders = async (
     <AppContext.Provider value={appState}>
       <ConfigContext.Provider value={config}>
         <SettingsContext.Provider value={settings}>
-          <UIStateContext.Provider value={finalUiState}>
-            <VimModeProvider>
-              <ShellFocusContext.Provider value={shellFocus}>
-                <SessionStatsProvider>
-                  <StreamingContext.Provider
-                    value={finalUiState.streamingState}
-                  >
-                    <UIActionsContext.Provider value={finalUIActions}>
-                      <OverflowProvider>
-                        <ToolActionsProvider
-                          config={config}
-                          toolCalls={allToolCalls}
-                          isExpanded={
-                            toolActions?.isExpanded ??
-                            vi.fn().mockReturnValue(false)
-                          }
-                          toggleExpansion={
-                            toolActions?.toggleExpansion ?? vi.fn()
-                          }
-                          toggleAllExpansion={
-                            toolActions?.toggleAllExpansion ?? vi.fn()
-                          }
-                        >
-                          <AskUserActionsProvider
-                            request={null}
-                            onSubmit={vi.fn()}
-                            onCancel={vi.fn()}
+          <InputContext.Provider value={inputState}>
+            <UIStateContext.Provider value={finalUiState}>
+              <VimModeProvider>
+                <ShellFocusContext.Provider value={shellFocus}>
+                  <SessionStatsProvider sessionId={config.getSessionId()}>
+                    <StreamingContext.Provider
+                      value={finalUiState.streamingState}
+                    >
+                      <UIActionsContext.Provider value={finalUIActions}>
+                        <OverflowProvider>
+                          <ToolActionsProvider
+                            config={config}
+                            toolCalls={allToolCalls}
+                            isExpanded={
+                              toolActions?.isExpanded ??
+                              vi.fn().mockReturnValue(false)
+                            }
+                            toggleExpansion={
+                              toolActions?.toggleExpansion ?? vi.fn()
+                            }
+                            toggleAllExpansion={
+                              toolActions?.toggleAllExpansion ?? vi.fn()
+                            }
                           >
-                            <KeypressProvider>
-                              <MouseProvider
-                                mouseEventsEnabled={mouseEventsEnabled}
-                              >
-                                <TerminalProvider>
-                                  <ScrollProvider>
-                                    <ContextCapture>
-                                      <Box
-                                        width={terminalWidth}
-                                        flexShrink={0}
-                                        flexGrow={0}
-                                        flexDirection="column"
-                                      >
-                                        {comp}
-                                      </Box>
-                                    </ContextCapture>
-                                  </ScrollProvider>
-                                </TerminalProvider>
-                              </MouseProvider>
-                            </KeypressProvider>
-                          </AskUserActionsProvider>
-                        </ToolActionsProvider>
-                      </OverflowProvider>
-                    </UIActionsContext.Provider>
-                  </StreamingContext.Provider>
-                </SessionStatsProvider>
-              </ShellFocusContext.Provider>
-            </VimModeProvider>
-          </UIStateContext.Provider>
+                            <AskUserActionsProvider
+                              request={null}
+                              onSubmit={vi.fn()}
+                              onCancel={vi.fn()}
+                            >
+                              <KeypressProvider>
+                                <MouseProvider
+                                  mouseEventsEnabled={mouseEventsEnabled}
+                                >
+                                  <TerminalProvider>
+                                    <ScrollProvider>
+                                      <ContextCapture>
+                                        <Box
+                                          width={terminalWidth}
+                                          flexShrink={0}
+                                          flexGrow={0}
+                                          flexDirection="column"
+                                        >
+                                          {comp}
+                                        </Box>
+                                      </ContextCapture>
+                                    </ScrollProvider>
+                                  </TerminalProvider>
+                                </MouseProvider>
+                              </KeypressProvider>
+                            </AskUserActionsProvider>
+                          </ToolActionsProvider>
+                        </OverflowProvider>
+                      </UIActionsContext.Provider>
+                    </StreamingContext.Provider>
+                  </SessionStatsProvider>
+                </ShellFocusContext.Provider>
+              </VimModeProvider>
+            </UIStateContext.Provider>
+          </InputContext.Provider>
         </SettingsContext.Provider>
       </ConfigContext.Provider>
     </AppContext.Provider>

packages/cli/src/ui/AppContainer.test.tsx

@@ -122,13 +122,17 @@ vi.mock('ink', async (importOriginal) => {
   };
 });
 
+import { InputContext, type InputState } from './contexts/InputContext.js';
+
 // Helper component will read the context values provided by AppContainer
 // so we can assert against them in our tests.
 let capturedUIState: UIState;
+let capturedInputState: InputState;
 let capturedUIActions: UIActions;
 let capturedOverflowActions: OverflowActions;
 function TestContextConsumer() {
   capturedUIState = useContext(UIStateContext)!;
+  capturedInputState = useContext(InputContext)!;
   capturedUIActions = useContext(UIActionsContext)!;
   capturedOverflowActions = useOverflowActions()!;
   return null;
@@ -3036,7 +3040,7 @@ describe('AppContainer State Management', () => {
       });
 
       const { unmount } = await act(async () => renderAppContainer());
-      expect(capturedUIState.userMessages).toContain('previous message');
+      expect(capturedInputState.userMessages).toContain('previous message');
 
       const { onCancelSubmit } = extractUseGeminiStreamArgs(
         mockedUseGeminiStream.mock.lastCall!,
@@ -3064,8 +3068,8 @@ describe('AppContainer State Management', () => {
       const { rerender, unmount } = await act(async () => renderAppContainer());
 
       // Verify userMessages is populated from inputHistory
-      expect(capturedUIState.userMessages).toContain('first prompt');
-      expect(capturedUIState.userMessages).toContain('second prompt');
+      expect(capturedInputState.userMessages).toContain('first prompt');
+      expect(capturedInputState.userMessages).toContain('second prompt');
 
       // Clear the conversation history (simulating /clear command)
       const mockClearItems = vi.fn();
@@ -3084,8 +3088,8 @@ describe('AppContainer State Management', () => {
 
       // Verify that userMessages still contains the input history
       // (it should not be affected by clearing conversation history)
-      expect(capturedUIState.userMessages).toContain('first prompt');
-      expect(capturedUIState.userMessages).toContain('second prompt');
+      expect(capturedInputState.userMessages).toContain('first prompt');
+      expect(capturedInputState.userMessages).toContain('second prompt');
 
       unmount();
     });

packages/cli/src/ui/AppContainer.tsx

@@ -36,9 +36,11 @@ import {
   type ConfirmationRequest,
   type PermissionConfirmationRequest,
   type QuotaStats,
+  MessageType,
+  StreamingState,
+  type HistoryItemInfo,
 } from './types.js';
 import { checkPermissions } from './hooks/atCommandProcessor.js';
-import { MessageType, StreamingState } from './types.js';
 import { ToolActionsProvider } from './contexts/ToolActionsContext.js';
 import { MouseProvider } from './contexts/MouseContext.js';
 import { ScrollProvider } from './contexts/ScrollProvider.js';
@@ -51,6 +53,7 @@ import {
   type UserTierId,
   type GeminiUserTier,
   type UserFeedbackPayload,
+  type HookSystemMessagePayload,
   type AgentDefinition,
   type ApprovalMode,
   IdeClient,
@@ -194,6 +197,8 @@ import {
 } from './hooks/useVisibilityToggle.js';
 import { useKeyMatchers } from './hooks/useKeyMatchers.js';
 
+import { InputContext } from './contexts/InputContext.js';
+
 /**
  * The fraction of the terminal width to allocate to the shell.
  * This provides horizontal padding.
@@ -439,7 +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();
 
@@ -2109,7 +2114,19 @@ Logging in with Google... Restarting Gemini CLI to continue.
       }
     };
 
+    const handleHookSystemMessage = (payload: HookSystemMessagePayload) => {
+      historyManager.addItem(
+        {
+          type: MessageType.INFO,
+          text: payload.message,
+          source: payload.hookName,
+        } as HistoryItemInfo,
+        Date.now(),
+      );
+    };
+
     coreEvents.on(CoreEvent.UserFeedback, handleUserFeedback);
+    coreEvents.on(CoreEvent.HookSystemMessage, handleHookSystemMessage);
 
     // Flush any messages that happened during startup before this component
     // mounted.
@@ -2117,6 +2134,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
 
     return () => {
       coreEvents.off(CoreEvent.UserFeedback, handleUserFeedback);
+      coreEvents.off(CoreEvent.HookSystemMessage, handleHookSystemMessage);
     };
   }, [historyManager]);
 
@@ -2328,6 +2346,27 @@ Logging in with Google... Restarting Gemini CLI to continue.
     };
   }, [config, refreshStatic]);
 
+  const inputState = useMemo(
+    () => ({
+      buffer,
+      userMessages: inputHistory,
+      shellModeActive,
+      showEscapePrompt,
+      copyModeEnabled,
+      inputWidth,
+      suggestionsWidth,
+    }),
+    [
+      buffer,
+      inputHistory,
+      shellModeActive,
+      showEscapePrompt,
+      copyModeEnabled,
+      inputWidth,
+      suggestionsWidth,
+    ],
+  );
+
   const uiState: UIState = useMemo(
     () => ({
       history: historyManager.history,
@@ -2371,11 +2410,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       initError,
       pendingGeminiHistoryItems,
       thought,
-      shellModeActive,
-      userMessages: inputHistory,
-      buffer,
-      inputWidth,
-      suggestionsWidth,
       isInputActive,
       isResuming,
       shouldShowIdePrompt,
@@ -2391,7 +2425,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       renderMarkdown,
       ctrlCPressedOnce: ctrlCPressCount >= 1,
       ctrlDPressedOnce: ctrlDPressCount >= 1,
-      showEscapePrompt,
       shortcutsHelpVisible,
       cleanUiDetailsVisible,
       isFocused,
@@ -2443,7 +2476,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       embeddedShellFocused,
       showDebugProfiler,
       customDialog,
-      copyModeEnabled,
       transientMessage,
       bannerData,
       bannerVisible,
@@ -2498,11 +2530,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       initError,
       pendingGeminiHistoryItems,
       thought,
-      shellModeActive,
-      inputHistory,
-      buffer,
-      inputWidth,
-      suggestionsWidth,
       isInputActive,
       isResuming,
       shouldShowIdePrompt,
@@ -2518,7 +2545,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       renderMarkdown,
       ctrlCPressCount,
       ctrlDPressCount,
-      showEscapePrompt,
       shortcutsHelpVisible,
       cleanUiDetailsVisible,
       isFocused,
@@ -2570,7 +2596,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       customDialog,
       apiKeyDefaultValue,
       authState,
-      copyModeEnabled,
       transientMessage,
       bannerData,
       bannerVisible,
@@ -2757,32 +2782,34 @@ Logging in with Google... Restarting Gemini CLI to continue.
 
   return (
     <UIStateContext.Provider value={uiState}>
-      <UIActionsContext.Provider value={uiActions}>
-        <ConfigContext.Provider value={config}>
-          <AppContext.Provider
-            value={{
-              version: props.version,
-              startupWarnings: props.startupWarnings || [],
-            }}
-          >
-            <ToolActionsProvider
-              config={config}
-              toolCalls={allToolCalls}
-              isExpanded={isExpanded}
-              toggleExpansion={toggleExpansion}
-              toggleAllExpansion={toggleAllExpansion}
+      <InputContext.Provider value={inputState}>
+        <UIActionsContext.Provider value={uiActions}>
+          <ConfigContext.Provider value={config}>
+            <AppContext.Provider
+              value={{
+                version: props.version,
+                startupWarnings: props.startupWarnings || [],
+              }}
             >
-              <ShellFocusContext.Provider value={isFocused}>
-                <MouseProvider mouseEventsEnabled={mouseMode}>
-                  <ScrollProvider>
-                    <App key={`app-${forceRerenderKey}`} />
-                  </ScrollProvider>
-                </MouseProvider>
-              </ShellFocusContext.Provider>
-            </ToolActionsProvider>
-          </AppContext.Provider>
-        </ConfigContext.Provider>
-      </UIActionsContext.Provider>
+              <ToolActionsProvider
+                config={config}
+                toolCalls={allToolCalls}
+                isExpanded={isExpanded}
+                toggleExpansion={toggleExpansion}
+                toggleAllExpansion={toggleAllExpansion}
+              >
+                <ShellFocusContext.Provider value={isFocused}>
+                  <MouseProvider mouseEventsEnabled={mouseMode}>
+                    <ScrollProvider>
+                      <App key={`app-${forceRerenderKey}`} />
+                    </ScrollProvider>
+                  </MouseProvider>
+                </ShellFocusContext.Provider>
+              </ToolActionsProvider>
+            </AppContext.Provider>
+          </ConfigContext.Provider>
+        </UIActionsContext.Provider>
+      </InputContext.Provider>
     </UIStateContext.Provider>
   );
 };

packages/cli/src/ui/__snapshots__/App.test.tsx.snap

@@ -55,6 +55,12 @@ Footer
  Gemini CLI v1.2.3
 
 
+
+Tips for getting started:
+1. Create GEMINI.md files to customize your interactions
+2. /help for more information
+3. Ask coding questions, edit code or run commands
+4. Be specific for the best results
 Composer
 "
 `;

packages/cli/src/ui/__snapshots__/ToolConfirmationFullFrame-Full-Terminal-Tool-Confirmation-Snapshot-renders-tool-confirmation-box-in-the-frame-of-the-entire-terminal.snap.svg

@@ -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>

packages/cli/src/ui/__snapshots__/ToolConfirmationFullFrame.test.tsx.snap

@@ -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;                                                                   │ │

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

@@ -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: () => [],

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

@@ -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}