Refine ADK migration design doc

Auth:
- Coast Assist / LOGIN_WITH_GOOGLE uses AuthClient.request() against a
  Code Assist backend, NOT the standard Gemini API
- GcliAgentModel must extend BaseLlm directly with dual transport
  (API-key via httpOptions.headers, Coast Assist via AuthClient.request())
- OAuth flow, token refresh, credential caching all work as-is

Telemetry:
- Stream-interceptor approach replaced with BasePlugin recommendation
- ClearcutTelemetryPlugin for token counts (afterModelCallback),
  per-tool timing (beforeToolCallback/afterToolCallback with functionCallId),
  agent lifecycle, and model errors
- Corrects earlier claim: token usage IS available on ADK events
  (llm_agent.ts spreads LlmResponse into events)
- HTTP-level metrics captured in GcliAgentModel wrapper
- ~70% of Clearcut metrics stay in existing call sites unchanged

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.dockerignore

@@ -1,17 +0,0 @@
-# Git history - not needed in build context
-.git
-
-# Root node_modules - reinstalled inside container via npm ci
-node_modules
-
-# Package-level node_modules - reinstalled inside container
-packages/*/node_modules
-
-# Development and IDE files
-.github
-.vscode
-npm-debug.log*
-
-# Misc
-.DS_Store
-*.tmp

.gemini/commands/strict-development-rules.md

@@ -53,27 +53,11 @@ Gemini CLI project.
   overriding values. Refer to `text-buffer.ts` for a canonical example.
 - **Logging**: Do not leave `console.log`, `console.warn`, or `console.error` in
   the code.
-- **State**: Ensure state initialization is explicit (e.g., use `undefined`
-  rather than `true` as a default if the state is truly unknown). Prefer a
-  reducer whenever practical. NEVER disable `react-hooks/exhaustive-deps`; fix
-  the code to correctly declare dependencies instead. Evaluate all the React
-  states in a component and ensure that the `useState` calls are necessary and
-  not cases where values could be derived on render. Ensure there are no stale
-  closures that are relying on a value from a previous render. React Components
-  that modify Settings should effectively use the `useSettingsStore` pattern.
-  Components that configure application Settings (e.g settings.json) are the
-  only reasonable case for unsaved changes to drive UX; in these cases, the
-  Settings store should only be written to on save. If the user experience does
-  not utilize unsaved changes because there is no option to exit without saving
-  or reverting the unsaved changes, then the component should directly read from
-  and write to the Settings store without holding pending changes in component
-  level UI state.
-- **Effect**: `useEffect` should not be used to synchronize React states, it
-  should only be used for genuine side effects that occur outside of React.
-  Contributors should be able to strongly justify the need for an effect.
-  Consider whether the effect should instead be inside an event handler, or
-  whether it is better off being computed on render. Carefully manage
-  `useEffect` dependencies.
+- **State & Effects**: Ensure state initialization is explicit (e.g., use
+  `undefined` rather than `true` as a default if the state is truly unknown).
+  Carefully manage `useEffect` dependencies. Prefer a reducer whenever
+  practical. NEVER disable `react-hooks/exhaustive-deps`; fix the code to
+  correctly declare dependencies instead.
 - **Context & Props**: Avoid excessive property drilling. Leverage existing
   providers, extend them, or propose a new one if necessary. Only use providers
   for properties that are consistent across the entire application.

.gemini/settings.json

@@ -2,12 +2,8 @@
   "experimental": {
     "extensionReloading": true,
     "modelSteering": true,
-    "autoMemory": true,
-    "topicUpdateNarration": true,
-    "voiceMode": true,
-    "adk": {
-      "agentSessionNoninteractiveEnabled": true
-    }
+    "memoryManager": false,
+    "topicUpdateNarration": true
   },
   "general": {
     "devtools": true

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

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

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

@@ -33,35 +33,6 @@ 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

.gemini/skills/docs-changelog/SKILL.md

@@ -162,7 +162,5 @@ instructions for the other section.
 
 ## Finalize
 
-- After making changes, if `npm run format` fails, it may be necessary to run
-  `npm install` first to ensure all formatting dependencies are available.
-  Then, run `npm run format` to ensure consistency.
+- After making changes, run `npm run format` ONLY to ensure consistency.
 - Delete any temporary files created during the process.

.gemini/skills/docs-writer/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: docs-writer
 description:
-  Always use this skill when the task involves writing, reviewing, or editing
+  Always use this skill when the task involves writing, reviewing, or editing 
   files in the `/docs` directory or any `.md` files in the repository.
 ---
 
@@ -24,7 +24,7 @@ approach.
 
 - **Perspective and tense:** Address the reader as "you." Use active voice and
   present tense (e.g., "The API returns...").
-- **Tone:** Professional, friendly, and direct.
+- **Tone:** Professional, friendly, and direct. 
 - **Clarity:** Use simple vocabulary. Avoid jargon, slang, and marketing hype.
 - **Global Audience:** Write in standard US English. Avoid idioms and cultural
   references.
@@ -47,8 +47,8 @@ Write precisely to ensure your instructions are unambiguous.
   "foo" or "bar."
 - **Quota and limit terminology:** For any content involving resource capacity
   or using the word "quota" or "limit", strictly adhere to the guidelines in
-  the `quota-limit-style-guide.md` resource file. Generally, Use "quota" for
-  the administrative bucket and "limit" for the numerical ceiling.
+  the `quota-limit-style-guide.md` resource file. Generally, Use "quota" for the
+  administrative bucket and "limit" for the numerical ceiling.
 
 ### Formatting and syntax
 Apply consistent formatting to make documentation visually organized and
@@ -85,25 +85,17 @@ accessible.
 
 - **Callouts**: Use GitHub-flavored markdown alerts to highlight important
   information. To ensure the formatting is preserved by `npm run format`, place
-  an empty line, then a prettier ignore comment directly before the callout
-  block. Use `<!-- prettier-ignore -->` for standard Markdown files (`.md`) and
-  `{/* prettier-ignore */}` for MDX files (`.mdx`). The callout type (`[!TYPE]`)
-  should be on the first line, followed by a newline, and then the content, with
-  each subsequent line of content starting with `>`. Available types are `NOTE`,
-  `TIP`, `IMPORTANT`, `WARNING`, and `CAUTION`.
+  an empty line, then the `<!-- prettier-ignore -->` comment directly before
+  the callout block. The callout type (`[!TYPE]`) should be on the first line,
+  followed by a newline, and then the content, with each subsequent line of
+  content starting with `>`. Available types are `NOTE`, `TIP`, `IMPORTANT`,
+  `WARNING`, and `CAUTION`.
 
-  Example (.md):
+  Example:
 
 <!-- prettier-ignore -->
 > [!NOTE]
 > This is an example of a multi-line note that will be preserved
-> by Prettier.
-
-  Example (.mdx):
-
-{/* prettier-ignore */}
-> [!NOTE]
-> This is an example of a multi-line note that will be preserved
 > by Prettier.
 
 ### Links
@@ -126,10 +118,9 @@ accessible.
 <!-- prettier-ignore -->
 > [!NOTE]
 > This is an experimental feature currently under active development.
-(Note: Use `{/* prettier-ignore */}` if editing an `.mdx` file.)
 
 - **Headings:** Use hierarchical headings to support the user journey.
-- **Procedures:**
+- **Procedures:** 
   - Introduce lists of steps with a complete sentence.
   - Start each step with an imperative verb.
   - Number sequential steps; use bullets for non-sequential lists.
@@ -143,7 +134,7 @@ accessible.
 
 ## Phase 2: Preparation
 Before modifying any documentation, thoroughly investigate the request and the
-surrounding context.
+surrounding context. 
 
 1.  **Clarify:** Understand the core request. Differentiate between writing new
     content and editing existing content. If the request is ambiguous (e.g.,
@@ -154,8 +145,6 @@ surrounding context.
 4.  **Connect:** Identify all referencing pages if changing behavior. Check if
     `docs/sidebar.json` needs updates.
 5.  **Plan:** Create a step-by-step plan before making changes.
-6.  **Audit Docset:** If asked to audit the documentation, follow the procedural
-    guide in [docs-auditing.md](./references/docs-auditing.md).
 
 ## Phase 3: Execution
 Implement your plan by either updating existing files or creating new ones
@@ -168,7 +157,7 @@ documentation.
 
 - **Gaps:** Identify areas where the documentation is incomplete or no longer
   reflects existing code.
-- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when
+- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when 
   adding new sections to existing pages.
 - **Headers**: If you change a header, you must check for links that lead to
   that header and update them.
@@ -179,16 +168,15 @@ documentation.
   documents.
 
 ## Phase 4: Verification and finalization
-Perform a final quality check to ensure that all changes are correctly
-formatted and that all links are functional.
+Perform a final quality check to ensure that all changes are correctly formatted
+and that all links are functional.
 
 1.  **Accuracy:** Ensure content accurately reflects the implementation and
   technical behavior.
 2.  **Self-review:** Re-read changes for formatting, correctness, and flow.
-3.  **Link check:** Verify all new and existing links leading to or from
-    modified pages. If you changed a header, ensure that any links that lead to
-    it are updated.
-4.  **Format:** If `npm run format` fails, it may be necessary to run `npm
-    install` first to ensure all formatting dependencies are available. Once all
-    changes are complete, ask to execute `npm run format` to ensure consistent
-    formatting across the project. If the user confirms, execute the command.
+3.  **Link check:** Verify all new and existing links leading to or from modified
+    pages. If you changed a header, ensure that any links that lead to it are
+    updated.
+4.  **Format:** Once all changes are complete, ask to execute `npm run format`
+    to ensure consistent formatting across the project. If the user confirms,
+    execute the command.

.gemini/skills/docs-writer/references/docs-auditing.md

@@ -1,195 +0,0 @@
-# Procedural Guide: Auditing the Docset
-
-This guide outlines the process for auditing the Gemini CLI documentation for
-correctness and adherence to style guidelines. This process involves both an
-"Editor" and "Technical Writer" phase.
-
-## Objective
-
-To ensure all public-facing documentation is accurate, up-to-date, adheres to
-the Gemini CLI documentation style guide, and reflects the current state of the
-codebase.
-
-## Phase 1: Editor Audit
-
-**Role:** The editor is responsible for identifying potential issues based on
-style guide violations and technical inaccuracies.
-
-### Steps
-
-1.  **Identify Documentation Scope:**
-    - Read `docs/sidebar.json` to get a list of all viewable documentation
-      pages.
-    - For each entry with a `slug`, convert it into a file path (e.g., `docs` ->
-      `docs/index.md`, `docs/get-started` -> `docs/get-started.md`). Ignore
-      entries with `link` properties.
-
-2.  **Prepare Audit Results File:**
-    - Create a new Markdown file named `audit-results-[YYYY-MM-DD].md` (e.g.,
-      `audit-results-2026-03-13.md`). This file will contain all identified
-      violations and recommendations.
-
-3.  **Retrieve Style Guidelines:**
-    - Familiarize yourself with the `docs-writer` skill instructions and the
-      included style guidelines.
-
-4.  **Audit Each Document:**
-    - For each documentation file identified in Step 1, read its content.
-    - **Review against Style Guide:**
-      - **Voice and Tone Violations:**
-        - **Unprofessional Tone:** Identify phrasing that is overly casual,
-          defensive, or lacks a professional and friendly demeanor.
-        - **Indirectness or Vagueness:** Identify sentences that are
-          unnecessarily wordy or fail to be concise and direct.
-        - **Incorrect Pronoun:** Identify any use of third-person pronouns
-          (e.g., "we," "they," "the user") when referring to the reader, instead
-          of the second-person pronoun **"you"**.
-        - **Passive Voice:** Identify sentences written in the passive voice.
-        - **Incorrect Tense:** Identify the use of past or future tense verbs,
-          instead of the **present tense**.
-        - **Poor Vocabulary:** Identify the use of jargon, slang, or overly
-          informal language.
-      - **Language and Grammar Violations:**
-        - **Lack of Conciseness:** Identify unnecessarily long phrases or
-          sentences.
-        - **Punctuation Errors:** Identify incorrect or missing punctuation.
-        - **Ambiguous Dates:** Identify dates that could be misinterpreted
-          (e.g., "next Monday" instead of "April 15, 2026").
-        - **Abbreviation Usage:** Identify the use of abbreviations that should
-          be spelled out (e.g., "e.g." instead of "for example").
-        - **Terminology:** Check for incorrect or inconsistent use of
-          product-specific terms (e.g., "quota" vs. "limit").
-      - **Formatting and Syntax Violations:**
-        - **Missing Overview:** Check for the absence of a brief overview
-          paragraph at the start of the document.
-        - **Line Length:** Identify any lines of text that exceed **80
-          characters** (text wrap violation).
-        - **Casing:** Identify incorrect casing for headings, titles, or named
-          entities (e.g., product names like `Gemini CLI`).
-        - **List Formatting:** Identify incorrectly formatted lists (e.g.,
-          inconsistent indentation or numbering).
-        - **Incorrect Emphasis:** Identify incorrect use of bold text (should
-          only be used for UI elements) or code font (should be used for code,
-          file names, or command-line input).
-        - **Link Quality:** Identify links with non-descriptive anchor text
-          (e.g., "click here").
-        - **Image Alt Text:** Identify images with missing or poor-quality
-          (non-descriptive) alt text.
-      - **Structure Violations:**
-        - **Missing BLUF:** Check for the absence of a "Bottom Line Up Front"
-          summary at the start of complex sections or documents.
-        - **Experimental Feature Notes:** Identify experimental features that
-          are not clearly labeled with a standard note.
-        - **Heading Hierarchy:** Check for skipped heading levels (e.g., going
-          from `##` to `####`).
-        - **Procedure Clarity:** Check for procedural steps that do not start
-          with an imperative verb or where a condition is placed _after_ the
-          instruction.
-        - **Element Misuse:** Identify the incorrect or inappropriate use of
-          special elements (e.g., Notes, Warnings, Cautions).
-        - **Table of Contents:** Identify the presence of a dynamically
-          generated or manually included table of contents.
-        - **Missing Next Steps:** Check for procedural documents that lack a
-          "Next steps" section (if applicable).
-    - **Verify Code Accuracy (if applicable):**
-      - If the document contains code snippets (e.g., shell commands, API calls,
-        file paths, Docker image versions), use `grep_search` and `read_file`
-        within the `packages/` directory (or other relevant parts of the
-        codebase) to ensure the code is still accurate and up-to-date. Pay close
-        attention to version numbers, package names, and command syntax.
-    - **Record Findings:** For each **violation** or inaccuracy found:
-      - Note the file path.
-      - Describe the violation (e.g., "Violation (Language and Grammar): Uses
-        'e.g.'").
-      - Provide a clear and actionable recommendation to correct the issue.
-        (e.g., "Recommendation: Replace 'e.g.' with 'for example'." or
-        "Recommendation: Replace '...' with '...' in active voice.).
-      - Append these findings to `audit-results-[YYYY-MM-DD].md`.
-
-## Phase 2: Software Engineer Audit
-
-**Role:** The software engineer is responsible for finding undocumented features
-by auditing the codebase and recent changelogs, and passing these findings to
-the technical writer.
-
-### Steps
-
-1.  **Proactive Codebase Audit:**
-    - Audit high-signal areas of the codebase to identify undocumented features.
-      You MUST review:
-      - `packages/cli/src/commands/`
-      - `packages/core/src/tools/`
-      - `packages/cli/src/config/settings.ts`
-
-2.  **Review Recent Updates:**
-    - Check recent changelogs in stable and announcements within the
-      documentation to see if newly introduced features are documented properly.
-
-3.  **Evaluate and Record Findings:**
-    - Determine if these features are adequately covered in the docs. They do
-      not need to be documented word for word, but major features that customers
-      should care about probably should have an article.
-    - Append your findings to the `audit-results-[YYYY-MM-DD].md` file,
-      providing a brief description of the feature and where it should be
-      documented.
-
-## Phase 3: Technical Writer Implementation
-
-**Role:** The technical writer handles input from both the editor and the
-software engineer, makes appropriate decisions about what to change, and
-implements the approved changes.
-
-### Steps
-
-1.  **Review Audit Results:**
-    - Read `audit-results-[YYYY-MM-DD].md` to understand all identified issues,
-      undocumented features, and recommendations from both the Editor and
-      Software Engineer phases.
-
-2.  **Make Decisions and Log Reasoning:**
-    - Create or update an implementation log (e.g.,
-      `audit-implementation-log-[YYYY-MM-DD].md`).
-    - Make sure the logs are updated for all steps, documenting your reasoning
-      for each recommendation (why it was accepted, modified, or rejected). This
-      is required for a final check by a human in the PR.
-
-3.  **Implement Changes:**
-    - For each approved recommendation:
-      - Read the target documentation file.
-      - Apply the recommended change using the `replace` tool. Pay close
-        attention to `old_string` for exact matches, including whitespace and
-        newlines. For multiple occurrences of the same simple string (e.g.,
-        "e.g."), use `allow_multiple: true`.
-      - **String replacement safeguards:** When applying these fixes across the
-        docset, you must verify the following:
-        - **Preserve Code Blocks:** Explicitly verify that no code blocks,
-          inline code snippets, terminal commands, or file paths have been
-          erroneously capitalized or modified.
-        - **Preserve Literal Strings:** Never alter the wording of literal error
-          messages, UI quotes, or system logs. For example, if a style rule says
-          to remove the word "please", you must NOT remove it if it appears
-          inside a quoted error message (e.g.,
-          `Error: Please contact your administrator`).
-        - **Verify Sentence Casing:** When removing filler words (like "please")
-          from the beginning of a sentence or list item, always verify that the
-          new first word of the sentence is properly capitalized.
-      - For structural changes (e.g., adding an overview paragraph), use
-        `replace` or `write_file` as appropriate.
-      - For broken links, determine the correct new path or update the link
-        text.
-      - For creating new files (e.g., `docs/get-started.md` to fix a broken
-        link, or a new feature article), use `write_file`.
-
-4.  **Execute Auto-Generation Scripts:**
-    - Some documentation pages are auto-generated from the codebase and should
-      be updated using npm scripts rather than manual edits. After implementing
-      manual changes (especially if you edited settings or configurations based
-      on SWE recommendations), ensure you run:
-      - `npm run docs:settings` to generate/update the configuration reference.
-      - `npm run docs:keybindings` to generate/update the keybindings reference.
-
-5.  **Format Code:**
-    - **Dependencies:** If `npm run format` fails, it may be necessary to run
-      `npm install` first to ensure all formatting dependencies are available.
-    - After all changes have been implemented, run `npm run format` to ensure
-      consistent formatting across the project.

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

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

.geminiignore

@@ -1,2 +1 @@
 packages/core/src/services/scripts/*.exe
-gha-creds-*.json

.github/actions/calculate-vars/action.yml

@@ -14,6 +14,12 @@ outputs:
 runs:
   using: 'composite'
   steps:
+    - name: 'Print inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
+
     - name: 'Set vars for simplified logic'
       id: 'set_vars'
       shell: 'bash'

.github/actions/create-pull-request/action.yml

@@ -30,6 +30,11 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
     - name: 'Creates a Pull Request'
       if: "inputs.dry-run != 'true'"
       env:

.github/actions/download-mac-binaries/action.yml

@@ -1,23 +0,0 @@
-name: 'Download Mac Binaries'
-description: 'Downloads the unsigned macOS binaries (x64 and arm64)'
-inputs:
-  path:
-    description: 'The base path to download the binaries to'
-    required: true
-    default: 'dist'
-runs:
-  using: 'composite'
-  steps:
-    - name: 'Download macOS arm64 binary'
-      uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
-      continue-on-error: true
-      with:
-        name: 'gemini-darwin-arm64-unsigned'
-        path: '${{ inputs.path }}/darwin-arm64'
-
-    - name: 'Download macOS x64 binary'
-      uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
-      continue-on-error: true
-      with:
-        name: 'gemini-darwin-x64-unsigned'
-        path: '${{ inputs.path }}/darwin-x64'

.github/actions/post-coverage-comment/action.yml

@@ -27,6 +27,11 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
     - name: 'Prepare Coverage Comment'
       id: 'prep_coverage_comment'
       shell: 'bash'

.github/actions/publish-release/action.yml

@@ -75,6 +75,12 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
+
     - name: '👤 Configure Git User'
       working-directory: '${{ inputs.working-directory }}'
       shell: 'bash'
@@ -108,14 +114,13 @@ runs:
         BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
         DRY_RUN: '${{ inputs.dry-run }}'
         RELEASE_TAG: '${{ inputs.release-tag }}'
-        GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
       run: |-
         set -e
         git add package.json package-lock.json packages/*/package.json
         git commit -m "chore(release): ${RELEASE_TAG}"
         if [[ "${DRY_RUN}" == "false" ]]; then
           echo "Pushing release branch to remote..."
-          git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
+          git push --set-upstream origin "${BRANCH_NAME}" --follow-tags
         else
           echo "Dry run enabled. Skipping push."
         fi
@@ -167,12 +172,11 @@ runs:
       shell: 'bash'
       run: |
         npm publish \
-          --ignore-scripts \
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
-          --tag staging-tmp
+          --no-tag
         if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} staging-tmp
+          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
         fi
 
     - name: '🔗 Install latest core package'
@@ -197,29 +201,6 @@ runs:
       run: |
         node ${{ github.workspace }}/scripts/prepare-npm-release.js
 
-    - name: '📦 Pack CLI for verification'
-      if: "inputs.dry-run != 'true' && inputs.force-skip-tests != 'true'"
-      working-directory: '${{ inputs.working-directory }}'
-      shell: 'bash'
-      run: |
-        npm pack --workspace="${INPUTS_CLI_PACKAGE_NAME}"
-        # We restore the package.json so that `npm ci` in verify-release doesn't fail due to deleted dependencies
-        git checkout packages/cli/package.json
-      env:
-        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
-
-    - name: '🔬 Verify NPM release by version'
-      uses: './.github/actions/verify-release'
-      if: "${{ inputs.dry-run != 'true' && inputs.force-skip-tests != 'true' }}"
-      with:
-        npm-package: './google-gemini-cli-${{ inputs.release-version }}.tgz'
-        expected-version: '${{ inputs.release-version }}'
-        working-directory: '${{ inputs.working-directory }}'
-        gemini_api_key: '${{ inputs.gemini_api_key }}'
-        github-token: '${{ inputs.github-token }}'
-        npm-registry-url: '${{ inputs.npm-registry-url }}'
-        npm-registry-scope: '${{ inputs.npm-registry-scope }}'
-
     - name: 'Get CLI Token'
       uses: './.github/actions/npm-auth-token'
       id: 'cli-token'
@@ -236,22 +217,14 @@ runs:
         NODE_AUTH_TOKEN: '${{ steps.cli-token.outputs.auth-token }}'
         INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
         INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
-        INPUTS_RELEASE_VERSION: '${{ inputs.release-version }}'
       shell: 'bash'
       run: |
-        if [ -f "google-gemini-cli-${INPUTS_RELEASE_VERSION}.tgz" ]; then
-          PUBLISH_TARGET="google-gemini-cli-${INPUTS_RELEASE_VERSION}.tgz"
-        else
-          PUBLISH_TARGET="--workspace=${INPUTS_CLI_PACKAGE_NAME}"
-        fi
-
         npm publish \
-          --ignore-scripts \
           --dry-run="${INPUTS_DRY_RUN}" \
-          ${PUBLISH_TARGET} \
-          --tag staging-tmp
+          --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
+          --no-tag
         if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} staging-tmp
+          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} false
         fi
 
     - name: 'Get a2a-server Token'
@@ -274,14 +247,25 @@ runs:
       # Tag staging for initial release
       run: |
         npm publish \
-          --ignore-scripts \
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
-          --tag staging-tmp
+          --no-tag
           if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
-            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} staging-tmp
+            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
           fi
 
+    - name: '🔬 Verify NPM release by version'
+      uses: './.github/actions/verify-release'
+      if: "${{ inputs.dry-run != 'true' && inputs.force-skip-tests != 'true' }}"
+      with:
+        npm-package: '${{ inputs.cli-package-name }}@${{ inputs.release-version }}'
+        expected-version: '${{ inputs.release-version }}'
+        working-directory: '${{ inputs.working-directory }}'
+        gemini_api_key: '${{ inputs.gemini_api_key }}'
+        github-token: '${{ inputs.github-token }}'
+        npm-registry-url: '${{ inputs.npm-registry-url }}'
+        npm-registry-scope: '${{ inputs.npm-registry-scope }}'
+
     - name: '🏷️ Tag release'
       uses: './.github/actions/tag-npm-release'
       with:
@@ -324,21 +308,8 @@ runs:
         fi
         rm -rf test-bundle
 
-        RELEASE_ASSETS=("gemini-cli-bundle.zip")
-
-        # Check for and prepare macOS binaries if they exist
-        for arch in arm64 x64; do
-          BINARY_PATH="dist/darwin-${arch}/gemini"
-          if [[ -f "$BINARY_PATH" ]]; then
-            chmod +x "$BINARY_PATH"
-            ZIP_NAME="gemini-darwin-${arch}-unsigned.zip"
-            zip -j "$ZIP_NAME" "$BINARY_PATH"
-            RELEASE_ASSETS+=("$ZIP_NAME")
-          fi
-        done
-
         gh release create "${INPUTS_RELEASE_TAG}" \
-          "${RELEASE_ASSETS[@]}" \
+          gemini-cli-bundle.zip \
           --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
           --title "Release ${INPUTS_RELEASE_TAG}" \
           --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \
@@ -352,8 +323,7 @@ runs:
       shell: 'bash'
       run: |
         echo "Cleaning up release branch ${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}..."
-        git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
+        git push origin --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
 
       env:
-        GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
         STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'

.github/actions/push-docker/action.yml

@@ -18,6 +18,11 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
     - name: 'Checkout'
       uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
       with:

.github/actions/push-sandbox/action.yml

@@ -28,6 +28,11 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
     - name: 'Checkout'
       uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
       with:

.github/actions/run-tests/action.yml

@@ -13,6 +13,11 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
     - name: 'Install system dependencies'
       if: "runner.os == 'Linux'"
       run: |
@@ -23,7 +28,6 @@ runs:
     - name: 'Run Tests'
       env:
         GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
-        GEMINI_CLI_TRUST_WORKSPACE: true
       working-directory: '${{ inputs.working-directory }}'
       run: |-
         echo "::group::Build"

.github/actions/tag-npm-release/action.yml

@@ -40,6 +40,12 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
+
     - name: 'Setup Node.js'
       uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
       with:

.github/actions/verify-release/action.yml

@@ -29,6 +29,12 @@ inputs:
 runs:
   using: 'composite'
   steps:
+    - name: '📝 Print Inputs'
+      shell: 'bash'
+      env:
+        JSON_INPUTS: '${{ toJSON(inputs) }}'
+      run: 'echo "$JSON_INPUTS"'
+
     - name: 'setup node'
       uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
       with:
@@ -74,7 +80,7 @@ runs:
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |-
-        gemini_version=$(npx --yes --prefer-online "${INPUTS_NPM_PACKAGE}" --version)
+        gemini_version=$(npx --prefer-online "${INPUTS_NPM_PACKAGE}" --version)
         if [ "$gemini_version" != "${INPUTS_EXPECTED_VERSION}" ]; then
           echo "❌ NPX Run Version mismatch: Got $gemini_version from ${INPUTS_NPM_PACKAGE}, expected ${INPUTS_EXPECTED_VERSION}"
           exit 1
@@ -86,18 +92,15 @@ runs:
     - name: 'Install dependencies for integration tests'
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
-      run: 'npm ci --ignore-scripts'
+      run: 'npm ci'
 
     - name: '🔬 Run integration tests against NPM release'
       working-directory: '${{ inputs.working-directory }}'
       env:
         GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
-        GEMINI_CLI_TRUST_WORKSPACE: true
         INTEGRATION_TEST_USE_INSTALLED_GEMINI: 'true'
         # We must diable CI mode here because it interferes with interactive tests.
         # See https://github.com/google-gemini/gemini-cli/issues/10517
         CI: 'false'
       shell: 'bash'
-      run: |
-        export INTEGRATION_TEST_GEMINI_BINARY_PATH=$(which gemini)
-        npm run test:integration:sandbox:none
+      run: 'npm run test:integration:sandbox:none'

.github/dependabot.yml

@@ -8,10 +8,6 @@ updates:
     open-pull-requests-limit: 10
     reviewers:
       - 'joshualitt'
-    cooldown:
-      semver-major-days: 14
-      semver-minor-days: 14
-      semver-patch-days: 14
     groups:
       npm-dependencies:
         patterns:
@@ -28,10 +24,6 @@ updates:
     open-pull-requests-limit: 10
     reviewers:
       - 'joshualitt'
-    cooldown:
-      semver-major-days: 14
-      semver-minor-days: 14
-      semver-patch-days: 14
     groups:
       actions-dependencies:
         patterns:

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

@@ -1,278 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-module.exports = async ({ github, context, core }) => {
-  const extractJson = (raw) => {
-    if (!raw || raw === '[]' || raw === '') return [];
-    try {
-      // First, try to parse the raw output as JSON.
-      return JSON.parse(raw);
-    } catch {
-      // If that fails, check for a markdown code block.
-      core.info(
-        'Direct JSON parsing failed. Trying to extract from a markdown block.',
-      );
-      const jsonMatch = raw.match(/```json\s*([\s\S]*?)\s*```/);
-      if (jsonMatch && jsonMatch[1]) {
-        try {
-          return JSON.parse(jsonMatch[1].trim());
-        } catch (markdownError) {
-          core.warning(
-            `Failed to parse extracted JSON from markdown block: ${markdownError.message}`,
-          );
-        }
-      }
-
-      // Try to find a raw JSON array in the output.
-      const jsonArrayMatch = raw.match(
-        /\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/,
-      );
-      if (jsonArrayMatch) {
-        try {
-          return JSON.parse(jsonArrayMatch[0]);
-        } catch {
-          const fallbackMatch = raw.match(/(\[\s*\{\s*"issue_number"[\s\S]*)/);
-          if (fallbackMatch) {
-            try {
-              const cleaned = fallbackMatch[0].substring(
-                0,
-                fallbackMatch[0].lastIndexOf(']') + 1,
-              );
-              return JSON.parse(cleaned);
-            } catch (fallbackError) {
-              core.warning(
-                `Failed to parse extracted JSON using fallback regex: ${fallbackError.message}`,
-              );
-            }
-          }
-        }
-      }
-    }
-    core.warning('No valid JSON could be extracted from input.');
-    return [];
-  };
-
-  // Collect all outputs from environment variables
-  // Prioritize EFFORT results over STANDARD results by processing Effort FIRST
-  // so that its labels appear first in the merged arrays (and thus win in mutually exclusive logic)
-  const effortRaw = process.env.LABELS_OUTPUT_EFFORT;
-  const standardRaw = process.env.LABELS_OUTPUT_STANDARD;
-  const genericRaw = process.env.LABELS_OUTPUT;
-
-  const resultsByIssue = new Map();
-
-  const processResults = (results, _sourceName) => {
-    for (const entry of results) {
-      const issueNumber = entry.issue_number;
-      if (!issueNumber) continue;
-
-      if (!resultsByIssue.has(issueNumber)) {
-        resultsByIssue.set(issueNumber, {
-          issue_number: issueNumber,
-          labels_to_add: [...(entry.labels_to_add || [])],
-          labels_to_remove: [...(entry.labels_to_remove || [])],
-          explanation: entry.explanation || '',
-          effort_analysis: entry.effort_analysis || '',
-        });
-      } else {
-        const existing = resultsByIssue.get(issueNumber);
-        // Combine labels
-        existing.labels_to_add = [
-          ...new Set([
-            ...existing.labels_to_add,
-            ...(entry.labels_to_add || []),
-          ]),
-        ];
-        existing.labels_to_remove = [
-          ...new Set([
-            ...existing.labels_to_remove,
-            ...(entry.labels_to_remove || []),
-          ]),
-        ];
-
-        // Combine explanations (if different)
-        if (
-          entry.explanation &&
-          !existing.explanation.includes(entry.explanation)
-        ) {
-          existing.explanation = existing.explanation
-            ? `${existing.explanation}\n\n${entry.explanation}`
-            : entry.explanation;
-        }
-
-        // Take effort analysis if present
-        if (entry.effort_analysis && !existing.effort_analysis) {
-          existing.effort_analysis = entry.effort_analysis;
-        }
-      }
-    }
-  };
-
-  // Order matters: Effort first so its labels win in conflict resolution
-  processResults(extractJson(effortRaw), 'EFFORT');
-  processResults(extractJson(standardRaw), 'STANDARD');
-  processResults(extractJson(genericRaw), 'GENERIC');
-
-  const finalResults = Array.from(resultsByIssue.values());
-  core.info(`Aggregated triage results for ${finalResults.length} issues.`);
-
-  for (const entry of finalResults) {
-    const issueNumber = entry.issue_number;
-    let labelsToAdd = entry.labels_to_add || [];
-    let labelsToRemove = entry.labels_to_remove || [];
-    let existingLabels = [];
-
-    // Fetch existing labels early
-    try {
-      const { data: issueData } = await github.rest.issues.get({
-        owner: context.repo.owner,
-        repo: context.repo.repo,
-        issue_number: issueNumber,
-      });
-      existingLabels = issueData.labels.map((l) =>
-        typeof l === 'string' ? l : l.name,
-      );
-    } catch (e) {
-      core.warning(
-        `Failed to fetch existing labels for #${issueNumber}: ${e.message}`,
-      );
-    }
-
-    // Programmatic Priority Downgrade Logic
-    if (labelsToAdd.includes('status/need-information')) {
-      const targetPriority = labelsToAdd.find((l) => l.startsWith('priority/'));
-      if (targetPriority) {
-        let downgradedPriority = null;
-        if (targetPriority === 'priority/p0')
-          downgradedPriority = 'priority/p1';
-        if (targetPriority === 'priority/p1')
-          downgradedPriority = 'priority/p2';
-
-        if (downgradedPriority) {
-          core.info(
-            `Programmatically downgrading ${targetPriority} to ${downgradedPriority} due to status/need-information`,
-          );
-          labelsToAdd = labelsToAdd.filter((l) => l !== targetPriority);
-          labelsToAdd.push(downgradedPriority);
-        }
-      }
-    }
-
-    labelsToRemove.push('status/need-triage');
-
-    if (
-      labelsToAdd.includes('status/manual-triage') ||
-      existingLabels.includes('status/manual-triage')
-    ) {
-      labelsToRemove.push('status/bot-triaged');
-      labelsToAdd = labelsToAdd.filter((l) => l !== 'status/bot-triaged');
-    } else {
-      labelsToAdd.push('status/bot-triaged');
-    }
-
-    // Resolve internal conflicts (e.g., adding P1 and P2)
-    // We already resolved these by putting Effort first in the combined list
-
-    // Resolve external conflicts with existing labels
-    if (labelsToAdd.some((l) => l.startsWith('area/'))) {
-      labelsToRemove.push(
-        ...existingLabels.filter((l) => l.startsWith('area/')),
-      );
-    }
-    if (labelsToAdd.some((l) => l.startsWith('priority/'))) {
-      labelsToRemove.push(
-        ...existingLabels.filter((l) => l.startsWith('priority/')),
-      );
-    }
-    if (labelsToAdd.some((l) => l.startsWith('kind/'))) {
-      labelsToRemove.push(
-        ...existingLabels.filter((l) => l.startsWith('kind/')),
-      );
-    }
-
-    // Enforce mutual exclusivity in the TO-ADD list (Architect wins)
-    const exclusivePrefixes = ['area/', 'priority/', 'kind/'];
-    for (const prefix of exclusivePrefixes) {
-      const filtered = labelsToAdd.filter((l) => l.startsWith(prefix));
-      if (filtered.length > 1) {
-        const winner = filtered[0]; // First one wins
-        core.info(
-          `Issue #${issueNumber} has multiple ${prefix} labels suggested. Keeping "${winner}" and discarding others.`,
-        );
-        labelsToAdd = labelsToAdd.filter(
-          (l) => !l.startsWith(prefix) || l === winner,
-        );
-      }
-    }
-
-    // Final deduplication and cleanup
-    labelsToRemove = [...new Set(labelsToRemove)].filter(
-      (l) => !labelsToAdd.includes(l) && existingLabels.includes(l),
-    );
-    labelsToAdd = [...new Set(labelsToAdd)].filter(
-      (l) => !existingLabels.includes(l),
-    );
-
-    // Batch label operations
-    if (labelsToAdd.length > 0) {
-      await github.rest.issues.addLabels({
-        owner: context.repo.owner,
-        repo: context.repo.repo,
-        issue_number: issueNumber,
-        labels: labelsToAdd,
-      });
-      core.info(
-        `Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`,
-      );
-    }
-
-    if (labelsToRemove.length > 0) {
-      for (const label of labelsToRemove) {
-        try {
-          await github.rest.issues.removeLabel({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            issue_number: issueNumber,
-            name: label,
-          });
-        } catch (e) {
-          if (e.status !== 404)
-            core.warning(
-              `Failed to remove label ${label} from #${issueNumber}: ${e.message}`,
-            );
-        }
-      }
-      core.info(
-        `Successfully removed labels for #${issueNumber}: ${labelsToRemove.join(', ')}`,
-      );
-    }
-
-    // Post comment if needed
-    const needsInfoAdded =
-      labelsToAdd.includes('status/need-information') &&
-      !existingLabels.includes('status/need-information');
-    const hasEffortAnalysis = !!entry.effort_analysis;
-
-    if (needsInfoAdded || hasEffortAnalysis) {
-      let commentBody = '';
-      if (needsInfoAdded && entry.explanation) commentBody += entry.explanation;
-      if (hasEffortAnalysis) {
-        if (commentBody) commentBody += '\n\n';
-        commentBody += `**Effort Analysis:**\n${entry.effort_analysis}`;
-      }
-
-      if (commentBody) {
-        await github.rest.issues.createComment({
-          owner: context.repo.owner,
-          repo: context.repo.repo,
-          issue_number: issueNumber,
-          body: commentBody,
-        });
-        core.info(`Posted required comment for #${issueNumber}`);
-      }
-    }
-  }
-};

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

@@ -1,74 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-const fs = require('node:fs');
-
-module.exports = async ({ github, context, core }) => {
-  let issuesToCleanup = [];
-  try {
-    const fileContent = fs.readFileSync('issues_to_cleanup.json', 'utf8');
-    issuesToCleanup = JSON.parse(fileContent);
-  } catch (error) {
-    if (error.code === 'ENOENT') {
-      core.info('No issues found to clean up.');
-      return;
-    }
-    core.setFailed(`Failed to read issues_to_cleanup.json: ${error.message}`);
-    return;
-  }
-
-  for (const issue of issuesToCleanup) {
-    try {
-      const { data: issueData } = await github.rest.issues.get({
-        owner: context.repo.owner,
-        repo: context.repo.repo,
-        issue_number: issue.number,
-      });
-
-      const labels = issueData.labels.map((l) =>
-        typeof l === 'string' ? l : l.name,
-      );
-
-      if (
-        labels.includes('status/bot-triaged') &&
-        labels.includes('status/need-triage')
-      ) {
-        await github.rest.issues.removeLabel({
-          owner: context.repo.owner,
-          repo: context.repo.repo,
-          issue_number: issue.number,
-          name: 'status/need-triage',
-        });
-        core.info(
-          `Successfully removed status/need-triage from #${issue.number}`,
-        );
-      }
-
-      if (
-        labels.includes('status/bot-triaged') &&
-        labels.includes('status/manual-triage')
-      ) {
-        await github.rest.issues.removeLabel({
-          owner: context.repo.owner,
-          repo: context.repo.repo,
-          issue_number: issue.number,
-          name: 'status/bot-triaged',
-        });
-        core.info(
-          `Successfully removed status/bot-triaged from #${issue.number} because it requires manual triage`,
-        );
-      }
-    } catch (error) {
-      core.warning(
-        `Failed to clean up labels for #${issue.number}: ${error.message}`,
-      );
-    }
-  }
-
-  core.info(
-    `Cleaned up conflicting labels from ${issuesToCleanup.length} issues.`,
-  );
-};

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

@@ -1,380 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-/**
- * Gemini Scheduled Lifecycle Manager Script
- * @param {object} param0
- * @param {import('@octokit/rest').Octokit} param0.github
- * @param {import('@actions/github/lib/context').Context} param0.context
- * @param {import('@actions/core')} param0.core
- */
-module.exports = async ({ github, context, core }) => {
-  const dryRun = process.env.DRY_RUN === 'true';
-  const owner = context.repo.owner;
-  const repo = context.repo.repo;
-
-  core.info(`Running in ${dryRun ? 'DRY RUN' : 'PRODUCTION'} mode.`);
-
-  const STALE_LABEL = 'stale';
-  const NEED_INFO_LABEL = 'status/need-information';
-  const EXEMPT_LABELS = [
-    'pinned',
-    'security',
-    '🔒 maintainer only',
-    'help wanted',
-    '🗓️ Public Roadmap',
-  ];
-
-  const STALE_DAYS = 60;
-  const CLOSE_DAYS = 14;
-  const NO_RESPONSE_DAYS = 14;
-
-  const now = new Date();
-  const staleThreshold = new Date(
-    now.getTime() - STALE_DAYS * 24 * 60 * 60 * 1000,
-  );
-  const closeThreshold = new Date(
-    now.getTime() - CLOSE_DAYS * 24 * 60 * 60 * 1000,
-  );
-  const noResponseThreshold = new Date(
-    now.getTime() - NO_RESPONSE_DAYS * 24 * 60 * 60 * 1000,
-  );
-
-  const maintainerCache = new Map();
-  async function isMaintainer(user, association) {
-    if (user?.type === 'Bot') return true;
-    if (['OWNER', 'MEMBER', 'COLLABORATOR'].includes(association)) return true;
-
-    const username = user?.login;
-    if (!username) return false;
-
-    if (maintainerCache.has(username)) {
-      return maintainerCache.get(username);
-    }
-
-    try {
-      const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
-        owner,
-        repo,
-        username,
-      });
-      // Permission can be admin, write, read, none.
-      // Roles like 'maintain' or 'triage' often map to 'write' or 'read' in the top-level field.
-      const isM =
-        ['admin', 'write'].includes(data.permission) ||
-        ['admin', 'maintain', 'write'].includes(data.role_name);
-
-      maintainerCache.set(username, isM);
-      return isM;
-    } catch (err) {
-      core.warning(
-        `Could not check permissions for ${username}: ${err.message}`,
-      );
-      maintainerCache.set(username, false);
-      return false;
-    }
-  }
-
-  async function processItems(query, callback) {
-    core.info(`Searching: ${query}`);
-    try {
-      let items = await github.paginate(
-        github.rest.search.issuesAndPullRequests,
-        {
-          q: query,
-          per_page: 100,
-          sort: 'updated',
-          order: 'asc',
-        },
-      );
-      core.info(`Found ${items.length} items.`);
-      for (const item of items) {
-        try {
-          await callback(item);
-        } catch (err) {
-          core.error(`Error processing #${item.number}: ${err.message}`);
-        }
-      }
-    } catch (err) {
-      core.error(`Search failed: ${err.message}`);
-    }
-  }
-
-  // 1. Handle No-Response (status/need-information)
-  // Removal: Check issues updated in the last 48h that have the label
-  const twoDaysAgo = new Date(now.getTime() - 2 * 24 * 60 * 60 * 1000);
-  await processItems(
-    `repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:>${twoDaysAgo.toISOString()}`,
-    async (item) => {
-      const { data: comments } = await github.rest.issues.listComments({
-        owner,
-        repo,
-        issue_number: item.number,
-        sort: 'created',
-        direction: 'desc',
-        per_page: 5,
-      });
-
-      // Check if the last comment is from a non-maintainer and not a bot
-      const lastComment = comments[0];
-      if (
-        lastComment &&
-        lastComment.user?.type !== 'Bot' &&
-        !(await isMaintainer(lastComment.user, lastComment.author_association))
-      ) {
-        if (dryRun) {
-          core.info(
-            `[DRY RUN] Would remove ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
-          );
-        } else {
-          core.info(
-            `Removing ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
-          );
-          await github.rest.issues
-            .removeLabel({
-              owner,
-              repo,
-              issue_number: item.number,
-              name: NEED_INFO_LABEL,
-            })
-            .catch(() => {});
-        }
-      }
-    },
-  );
-
-  // Closure: Check issues with the label that haven't been updated in 14 days
-  await processItems(
-    `repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:<${noResponseThreshold.toISOString()}`,
-    async (item) => {
-      if (dryRun) {
-        core.info(
-          `[DRY RUN] Would close #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
-        );
-      } else {
-        core.info(
-          `Closing #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
-        );
-        await github.rest.issues.createComment({
-          owner,
-          repo,
-          issue_number: item.number,
-          body: `This item was marked as needing more information and has not received a response in ${NO_RESPONSE_DAYS} days. Closing it for now. If you still face this problem, feel free to reopen with more details. Thank you!`,
-        });
-        await github.rest.issues.update({
-          owner,
-          repo,
-          issue_number: item.number,
-          state: 'closed',
-          state_reason: 'not_planned',
-        });
-      }
-    },
-  );
-
-  // 2. Handle Stale Mark (60 days inactivity, no stale label)
-  const exemptQuery = EXEMPT_LABELS.map((l) => `-label:"${l}"`).join(' ');
-
-  await processItems(
-    `repo:${owner}/${repo} is:open -label:"${STALE_LABEL}" ${exemptQuery} updated:<${staleThreshold.toISOString()}`,
-    async (item) => {
-      const isBug = item.labels.some((l) =>
-        (typeof l === 'string' ? l : l.name).toLowerCase().includes('bug'),
-      );
-      const bodyText = isBug
-        ? `This bug report has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. Many issues are resolved in newer releases. Please verify if the issue persists in the latest Gemini CLI version. If it does, please leave a comment to keep this open. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`
-        : `This item has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`;
-
-      if (dryRun) {
-        core.info(`[DRY RUN] Would mark #${item.number} as stale.`);
-      } else {
-        core.info(`Marking #${item.number} as stale.`);
-        await github.rest.issues.addLabels({
-          owner,
-          repo,
-          issue_number: item.number,
-          labels: [STALE_LABEL],
-        });
-        await github.rest.issues.createComment({
-          owner,
-          repo,
-          issue_number: item.number,
-          body: bodyText,
-        });
-      }
-    },
-  );
-
-  // 3. Handle Stale Removal & Close
-  await processItems(
-    `repo:${owner}/${repo} is:open label:"${STALE_LABEL}" ${exemptQuery}`,
-    async (item) => {
-      // Fetch full timeline to see events and comments
-      const timeline = await github.paginate(
-        github.rest.issues.listEventsForTimeline,
-        {
-          owner,
-          repo,
-          issue_number: item.number,
-          per_page: 100,
-        },
-      );
-
-      // Find exactly when the Stale label was added
-      // We look for the last 'labeled' event for STALE_LABEL
-      const staleEventIndex = timeline.findLastIndex(
-        (e) =>
-          e.event === 'labeled' &&
-          e.label?.name?.toLowerCase() === STALE_LABEL.toLowerCase(),
-      );
-
-      if (staleEventIndex === -1) return; // Fallback if no event found
-
-      const staleEvent = timeline[staleEventIndex];
-      const eventsAfterStale = timeline.slice(staleEventIndex + 1);
-
-      // Check for meaningful activity after the Stale label was applied
-      const meaningfulEvents = eventsAfterStale.filter((e) => {
-        const actor = e.actor?.login || '';
-        const isBot =
-          actor.includes('[bot]') || actor.includes('github-actions');
-
-        if (isBot) return false;
-
-        // Explicit whitelist of meaningful events for humans
-        if (
-          [
-            'commented',
-            'cross-referenced',
-            'connected',
-            'reopened',
-            'assigned',
-          ].includes(e.event)
-        ) {
-          return true;
-        }
-
-        return false;
-      });
-
-      if (meaningfulEvents.length > 0) {
-        // Activity detected, remove Stale label
-        if (dryRun) {
-          core.info(
-            `[DRY RUN] Would remove ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
-          );
-        } else {
-          core.info(
-            `Removing ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
-          );
-          await github.rest.issues
-            .removeLabel({
-              owner,
-              repo,
-              issue_number: item.number,
-              name: STALE_LABEL,
-            })
-            .catch(() => {});
-        }
-        return;
-      }
-
-      // No meaningful activity. Check if 14 days have passed.
-      const labeledDate = new Date(staleEvent.created_at);
-      if (labeledDate > closeThreshold) {
-        // Has not been 14 days since it was ACTUALLY marked stale
-        return;
-      }
-
-      if (dryRun) {
-        core.info(`[DRY RUN] Would close stale item #${item.number}.`);
-      } else {
-        core.info(`Closing stale item #${item.number}.`);
-        await github.rest.issues.createComment({
-          owner,
-          repo,
-          issue_number: item.number,
-          body: `This item has been closed due to ${CLOSE_DAYS} additional days of inactivity after being marked as stale. If you believe this is still relevant, feel free to comment or reopen. Thank you!`,
-        });
-        await github.rest.issues.update({
-          owner,
-          repo,
-          issue_number: item.number,
-          state: 'closed',
-          state_reason: 'not_planned',
-        });
-      }
-    },
-  );
-
-  // 4. Handle PR Contribution Policy (Nudge at 7d, Close at 14d)
-  const PR_NUDGE_DAYS = 7;
-  const PR_CLOSE_DAYS = 14;
-  const nudgeThreshold = new Date(
-    now.getTime() - PR_NUDGE_DAYS * 24 * 60 * 60 * 1000,
-  );
-  const prCloseThreshold = new Date(
-    now.getTime() - PR_CLOSE_DAYS * 24 * 60 * 60 * 1000,
-  );
-
-  // Nudge
-  await processItems(
-    `repo:${owner}/${repo} is:open is:pr -label:"help wanted" -label:"🔒 maintainer only" -label:"status/pr-nudge-sent" created:${prCloseThreshold.toISOString()}..${nudgeThreshold.toISOString()}`,
-    async (pr) => {
-      if (await isMaintainer(pr.user, pr.author_association)) return;
-
-      if (dryRun) {
-        core.info(
-          `[DRY RUN] Would nudge PR #${pr.number} for contribution policy.`,
-        );
-      } else {
-        core.info(`Nudging PR #${pr.number} for contribution policy.`);
-        await github.rest.issues.addLabels({
-          owner,
-          repo,
-          issue_number: pr.number,
-          labels: ['status/pr-nudge-sent'],
-        });
-        await github.rest.issues.createComment({
-          owner,
-          repo,
-          issue_number: pr.number,
-          body: "Hi there! Thank you for your interest in contributing to Gemini CLI. \n\nTo ensure we maintain high code quality and focus on our prioritized roadmap, we only guarantee review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'. \n\nThis PR will be closed in 7 days if it remains without that designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.",
-        });
-      }
-    },
-  );
-
-  // Close
-  await processItems(
-    `repo:${owner}/${repo} is:open is:pr -label:"help wanted" -label:"🔒 maintainer only" created:<${prCloseThreshold.toISOString()}`,
-    async (pr) => {
-      if (await isMaintainer(pr.user, pr.author_association)) return;
-
-      if (dryRun) {
-        core.info(
-          `[DRY RUN] Would close PR #${pr.number} per contribution policy (no 'help wanted').`,
-        );
-      } else {
-        core.info(
-          `Closing PR #${pr.number} per contribution policy (no 'help wanted').`,
-        );
-        await github.rest.issues.createComment({
-          owner,
-          repo,
-          issue_number: pr.number,
-          body: "This pull request is being closed as it has been open for 14 days without a 'help wanted' designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.",
-        });
-        await github.rest.pulls.update({
-          owner,
-          repo,
-          pull_number: pr.number,
-          state: 'closed',
-        });
-      }
-    },
-  );
-};

.github/scripts/sync-issue-types.cjs

@@ -1,99 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-const fs = require('node:fs');
-
-module.exports = async ({ github, context, core }) => {
-  const query = `
-    query($owner: String!, $repo: String!) {
-      repository(owner: $owner, name: $repo) {
-        issues(first: 50, states: OPEN, orderBy: {field: UPDATED_AT, direction: DESC}) {
-          nodes {
-            id
-            number
-            title
-            body
-            issueType {
-              name
-            }
-            labels(first: 20) {
-              nodes {
-                name
-              }
-            }
-          }
-        }
-      }
-    }
-  `;
-
-  try {
-    const result = await github.graphql(query, {
-      owner: context.repo.owner,
-      repo: context.repo.repo,
-    });
-
-    const issues = result.repository.issues.nodes;
-    const issuesNeedingAnalysis = [];
-    let syncedCount = 0;
-
-    for (const issue of issues) {
-      if (issue.issueType === null) {
-        const labelNames = issue.labels.nodes.map((l) => l.name);
-        const hasBug = labelNames.includes('kind/bug');
-        const hasFeature =
-          labelNames.includes('kind/feature') ||
-          labelNames.includes('kind/enhancement');
-
-        let issueTypeId = null;
-        if (hasBug) {
-          issueTypeId = 'IT_kwDOCaSVvs4BR7vP'; // Bug
-        } else if (hasFeature) {
-          issueTypeId = 'IT_kwDOCaSVvs4BR7vQ'; // Feature
-        }
-
-        if (issueTypeId) {
-          await github.graphql(
-            `
-            mutation($issueId: ID!, $issueTypeId: ID!) {
-              updateIssue(input: {id: $issueId, issueTypeId: $issueTypeId}) {
-                issue {
-                  id
-                }
-              }
-            }
-          `,
-            {
-              issueId: issue.id,
-              issueTypeId: issueTypeId,
-            },
-          );
-          core.info(`Successfully synced Issue Type for #${issue.number}`);
-          syncedCount++;
-        } else {
-          // Needs analysis to determine kind/type
-          issuesNeedingAnalysis.push({
-            number: issue.number,
-            title: issue.title,
-            body: issue.body,
-          });
-        }
-      }
-    }
-
-    // Write issues needing analysis to a file so the AI can process them
-    fs.writeFileSync(
-      'no_type_issues.json',
-      JSON.stringify(issuesNeedingAnalysis),
-    );
-    core.info(`Synced ${syncedCount} issues from labels.`);
-    core.info(
-      `Found ${issuesNeedingAnalysis.length} issues missing both type and kind label to be analyzed.`,
-    );
-  } catch (error) {
-    core.setFailed(`Failed to sync issue types: ${error.message}`);
-  }
-};

.github/workflows/agent-session-drift-check.yml

@@ -1,132 +0,0 @@
-# yaml-language-server: $schema=https://json.schemastore.org/github-workflow.json
-
-name: 'Agent Session Drift Check'
-
-on:
-  pull_request:
-    branches:
-      - 'main'
-      - 'release/**'
-    paths:
-      - 'packages/cli/src/nonInteractiveCli.ts'
-      - 'packages/cli/src/nonInteractiveCliAgentSession.ts'
-
-concurrency:
-  group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
-  cancel-in-progress: true
-
-jobs:
-  check-drift:
-    name: 'Check Agent Session Drift'
-    runs-on: 'ubuntu-latest'
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    permissions:
-      contents: 'read'
-      pull-requests: 'write'
-    steps:
-      - name: 'Detect drift and comment'
-        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea' # ratchet:actions/github-script@v8
-        with:
-          script: |-
-            // === Pair configuration — append here to cover more pairs ===
-            const PAIRS = [
-              {
-                legacy: 'packages/cli/src/nonInteractiveCli.ts',
-                session: 'packages/cli/src/nonInteractiveCliAgentSession.ts',
-                label: 'non-interactive CLI',
-              },
-              // Future pairs can be added here. Remember to also add both
-              // paths to the `paths:` filter at the top of this workflow.
-              // Example:
-              // {
-              //   legacy: 'packages/core/src/agents/local-invocation.ts',
-              //   session: 'packages/core/src/agents/local-session-invocation.ts',
-              //   label: 'local subagent invocation',
-              // },
-            ];
-            // ============================================================
-
-            const prNumber = context.payload.pull_request.number;
-            const { owner, repo } = context.repo;
-
-            // Use the API to list changed files — no checkout/git diff needed.
-            const files = await github.paginate(github.rest.pulls.listFiles, {
-              owner,
-              repo,
-              pull_number: prNumber,
-              per_page: 100,
-            });
-            const changed = new Set(files.map((f) => f.filename));
-
-            const warnings = [];
-            for (const { legacy, session, label } of PAIRS) {
-              const legacyChanged = changed.has(legacy);
-              const sessionChanged = changed.has(session);
-              if (legacyChanged && !sessionChanged) {
-                warnings.push(
-                  `**${label}**: \`${legacy}\` was modified but \`${session}\` was not.`,
-                );
-              } else if (!legacyChanged && sessionChanged) {
-                warnings.push(
-                  `**${label}**: \`${session}\` was modified but \`${legacy}\` was not.`,
-                );
-              }
-            }
-
-            const MARKER = '<!-- agent-session-drift-check -->';
-
-            // Look up our existing drift comment (for upsert/cleanup).
-            const comments = await github.paginate(github.rest.issues.listComments, {
-              owner,
-              repo,
-              issue_number: prNumber,
-              per_page: 100,
-            });
-            const existing = comments.find(
-              (c) => c.user?.type === 'Bot' && c.body?.includes(MARKER),
-            );
-
-            if (warnings.length === 0) {
-              core.info('No drift detected.');
-              // If drift was previously flagged and is now resolved, remove the comment.
-              if (existing) {
-                await github.rest.issues.deleteComment({
-                  owner,
-                  repo,
-                  comment_id: existing.id,
-                });
-                core.info(`Deleted stale drift comment ${existing.id}.`);
-              }
-              return;
-            }
-
-            const body = [
-              MARKER,
-              '### ⚠️ Invocation Drift Warning',
-              '',
-              'The following file pairs should generally be kept in sync during the AgentSession migration:',
-              '',
-              ...warnings.map((w) => `- ${w}`),
-              '',
-              'If this is intentional (e.g., a bug fix specific to one implementation), you can ignore this comment.',
-              '',
-              '_This check will be removed once the legacy implementations are deleted._',
-            ].join('\n');
-
-            if (existing) {
-              core.info(`Updating existing drift comment ${existing.id}.`);
-              await github.rest.issues.updateComment({
-                owner,
-                repo,
-                comment_id: existing.id,
-                body,
-              });
-            } else {
-              core.info('Creating new drift comment.');
-              await github.rest.issues.createComment({
-                owner,
-                repo,
-                issue_number: prNumber,
-                body,
-              });
-            }

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

@@ -1,65 +0,0 @@
-name: 'Build Unsigned Mac Binaries'
-
-on:
-  workflow_dispatch:
-  workflow_call:
-    inputs:
-      ref:
-        description: 'The branch, tag, or SHA to build from.'
-        required: true
-        type: 'string'
-
-permissions:
-  contents: 'read'
-
-defaults:
-  run:
-    shell: 'bash'
-
-jobs:
-  build-mac:
-    name: 'Build Unsigned (${{ matrix.arch }})'
-    runs-on: 'macos-latest'
-    strategy:
-      fail-fast: false
-      matrix:
-        arch: ['x64', 'arm64']
-
-    steps:
-      - name: 'Checkout'
-        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
-        with:
-          ref: '${{ inputs.ref || github.ref }}'
-          persist-credentials: false
-
-      - name: 'Set up Node.js'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
-        with:
-          node-version-file: '.nvmrc'
-          architecture: '${{ matrix.arch }}'
-          cache: 'npm'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-
-      - name: 'Build Binary'
-        env:
-          SKIP_SIGNING: 'true'
-        run: 'npm run build:binary'
-
-      - name: 'Verify Output Exists'
-        run: |
-          if [ -f "dist/darwin-${{ matrix.arch }}/gemini" ]; then
-            echo "Binary found at dist/darwin-${{ matrix.arch }}/gemini"
-          else
-            echo "Error: Binary not found in dist/darwin-${{ matrix.arch }}/"
-            ls -R dist/
-            exit 1
-          fi
-
-      - name: 'Upload Artifact'
-        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
-        with:
-          name: 'gemini-darwin-${{ matrix.arch }}-unsigned'
-          path: 'dist/darwin-${{ matrix.arch }}/gemini'
-          retention-days: 14

.github/workflows/chained_e2e.yml

@@ -148,7 +148,6 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
-          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -168,7 +167,6 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           VERBOSE: 'true'
           BUILD_SANDBOX_FLAGS: '--cache-from type=gha --cache-to type=gha,mode=max'
@@ -185,7 +183,7 @@ jobs:
     needs:
       - 'merge_queue_skipper'
       - 'parse_run_context'
-    runs-on: 'macos-latest-large'
+    runs-on: 'macos-latest'
     if: |
       github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     steps:
@@ -194,7 +192,6 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
-          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -215,7 +212,6 @@ jobs:
         if: "${{runner.os != 'Windows'}}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           SANDBOX: 'sandbox:none'
           VERBOSE: 'true'
@@ -235,7 +231,6 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
-          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -293,7 +288,6 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           SANDBOX: 'sandbox:none'
           VERBOSE: 'true'
@@ -317,7 +311,6 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
-          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Set up Node.js 20.x'
@@ -341,10 +334,7 @@ jobs:
         if: "${{ steps.check_evals.outputs.should_run == 'true' }}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           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/ci.yml

@@ -57,7 +57,6 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
           fetch-depth: 0
 
@@ -103,12 +102,6 @@ jobs:
       - name: 'Run yamllint'
         run: 'node scripts/lint.js --yamllint'
 
-      - name: 'Build project for typecheck'
-        run: 'npm run build'
-
-      - name: 'Run typecheck'
-        run: 'npm run typecheck'
-
       - name: 'Run Prettier'
         run: 'node scripts/lint.js --prettier'
 
@@ -131,8 +124,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
       - name: 'Link Checker'
         uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
         with:
@@ -160,8 +151,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -184,7 +173,6 @@ jobs:
       - name: 'Run tests and generate reports'
         env:
           NO_COLOR: true
-          GEMINI_CLI_TRUST_WORKSPACE: true
         run: |
           if [[ "${{ matrix.shard }}" == "cli" ]]; then
             npm run test:ci --workspace "@google/gemini-cli"
@@ -236,7 +224,7 @@ jobs:
 
   test_mac:
     name: 'Test (Mac) - ${{ matrix.node-version }}, ${{ matrix.shard }}'
-    runs-on: 'macos-latest-large'
+    runs-on: 'macos-latest'
     needs:
       - 'merge_queue_skipper'
     if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
@@ -257,8 +245,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -275,7 +261,6 @@ jobs:
       - name: 'Run tests and generate reports'
         env:
           NO_COLOR: true
-          GEMINI_CLI_TRUST_WORKSPACE: true
         run: |
           if [[ "${{ matrix.shard }}" == "cli" ]]; then
             npm run test:ci --workspace "@google/gemini-cli" -- --coverage.enabled=false
@@ -346,7 +331,6 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
 
       - name: 'Initialize CodeQL'
@@ -371,7 +355,6 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
           fetch-depth: 1
 
@@ -399,7 +382,6 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
 
       - name: 'Set up Node.js 20.x'
@@ -442,7 +424,6 @@ jobs:
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           NO_COLOR: true
-          GEMINI_CLI_TRUST_WORKSPACE: true
           NODE_OPTIONS: '--max-old-space-size=32768 --max-semi-space-size=256'
           UV_THREADPOOL_SIZE: '32'
           NODE_ENV: 'test'

.github/workflows/community-report.yml

@@ -173,7 +173,6 @@ jobs:
           GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
           REPOSITORY: '${{ github.repository }}'
         with:
-          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -183,14 +182,12 @@ jobs:
           use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
           settings: |-
             {
-              "tools": {
-                "core": [
-                  "run_shell_command(gh issue list)",
-                  "run_shell_command(gh pr list)",
-                  "run_shell_command(gh search issues)",
-                  "run_shell_command(gh search prs)"
-                ]
-              }
+              "coreTools": [
+                "run_shell_command(gh issue list)",
+                "run_shell_command(gh pr list)",
+                "run_shell_command(gh search issues)",
+                "run_shell_command(gh search prs)"
+              ]
             }
           prompt: |-
             You are a helpful assistant that analyzes community contribution reports.

.github/workflows/deflake.yml

@@ -43,7 +43,6 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
-          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -63,7 +62,6 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           IS_DOCKER: "${{ matrix.sandbox == 'sandbox:docker' }}"
           KEEP_OUTPUT: 'true'
           RUNS: '${{ github.event.inputs.runs }}'
@@ -79,7 +77,7 @@ jobs:
 
   deflake_e2e_mac:
     name: 'E2E Test (macOS)'
-    runs-on: 'macos-latest-large'
+    runs-on: 'macos-latest'
     if: "github.repository == 'google-gemini/gemini-cli'"
     steps:
       - name: 'Checkout'
@@ -87,7 +85,6 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
-          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -108,7 +105,6 @@ jobs:
         if: "runner.os != 'Windows'"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           RUNS: '${{ github.event.inputs.runs }}'
           SANDBOX: 'sandbox:none'
@@ -127,7 +123,6 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
-          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -164,7 +159,6 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           SANDBOX: 'sandbox:none'
           VERBOSE: 'true'

.github/workflows/docs-audit.yml

@@ -1,66 +0,0 @@
-name: 'Automated Documentation Audit'
-
-on:
-  schedule:
-    # Runs every Monday at 00:00 UTC
-    - cron: '0 0 * * MON'
-  workflow_dispatch:
-
-jobs:
-  audit-docs:
-    runs-on: 'ubuntu-latest'
-    permissions:
-      contents: 'write'
-      pull-requests: 'write'
-
-    steps:
-      - name: 'Checkout repository'
-        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5'
-        with:
-          fetch-depth: 0
-          ref: 'main'
-          persist-credentials: false
-
-      - name: 'Set up Node.js'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
-        with:
-          node-version: '20'
-
-      - name: 'Run Docs Audit with Gemini'
-        id: 'run_gemini'
-        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31'
-        env:
-          GEMINI_CLI_TRUST_WORKSPACE: true
-        with:
-          upload_artifacts: 'true'
-          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
-          prompt: |
-            Activate the 'docs-writer' skill.
-
-            **Task:** Execute the docs audit procedure, as defined in your 'docs-auditing.md' reference.
-            Provide a detailed summary of the changes you make.
-
-      - name: 'Get current date'
-        id: 'date'
-        run: |
-          echo "date=$(date +'%Y-%m-%d')" >> "$GITHUB_OUTPUT"
-
-      - name: 'Create Pull Request with Audit Results'
-        uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c'
-        with:
-          token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
-          commit-message: 'docs: weekly audit results for ${{ github.run_id }}'
-          title: 'Docs audit: ${{ steps.date.outputs.date }}'
-          body: |
-            This PR contains the auto-generated documentation audit for the week. It includes a new `audit-results-*.md` file with findings and any direct fixes applied by the agent.
-
-            ### Audit Summary:
-            ${{ steps.run_gemini.outputs.summary || 'No summary provided.' }}
-
-            Please review the suggestions and merge.
-
-            Related to #25152
-          branch: 'docs-audit-${{ github.run_id }}'
-          base: 'main'
-          team-reviewers: 'gemini-cli-docs, gemini-cli-maintainers'
-          delete-branch: true

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

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

.github/workflows/eval-pr.yml

@@ -1,7 +1,7 @@
 name: 'Evals: PR Evaluation & Regression'
 
 on:
-  pull_request_target:
+  pull_request:
     types: ['opened', 'synchronize', 'reopened', 'ready_for_review']
     paths:
       - 'packages/core/src/prompts/**'
@@ -23,74 +23,13 @@ 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
-          persist-credentials: false
-
-      - 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: |-
+      ${{ (github.event.pull_request.head.repo.full_name == github.repository) && 'internal' || 'external-evals' }}
     env:
       # CENTRALIZED MODEL LIST
       MODEL_LIST: 'gemini-3-flash-preview'
@@ -99,26 +38,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
         with:
-          # Check out the fork's PR code for the actual evaluation
-          # This only runs AFTER manual approval
-          ref: '${{ github.event.pull_request.head.sha }}'
           fetch-depth: 0
-          persist-credentials: false
-
-      - 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
@@ -126,14 +46,24 @@ jobs:
           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: "needs.detect-changes.outputs.STEERING_DETECTED == 'true'"
+        if: "steps.detect.outputs.STEERING_DETECTED == 'true'"
         id: 'analysis'
         env:
           GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
@@ -151,6 +81,7 @@ 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 }}'
@@ -165,7 +96,7 @@ jobs:
           fi
 
       - name: 'Post or Update PR Comment'
-        if: "always() && (needs.detect-changes.outputs.STEERING_DETECTED == 'true' || env.REPORT_FILE != '')"
+        if: "always() && (steps.detect.outputs.STEERING_DETECTED == 'true' || env.REPORT_FILE != '')"
         env:
           GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
         run: |
@@ -176,7 +107,7 @@ jobs:
               echo ""
             fi
 
-            if [[ "${{ needs.detect-changes.outputs.STEERING_DETECTED }}" == "true" ]]; then
+            if [[ "${{ steps.detect.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

@@ -5,18 +5,10 @@ on:
     - cron: '0 1 * * *' # Runs at 1 AM every day
   workflow_dispatch:
     inputs:
-      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'
+      run_all:
+        description: 'Run all evaluations (including usually passing)'
+        type: 'boolean'
+        default: true
       test_name_pattern:
         description: 'Test name pattern or file name'
         required: false
@@ -46,8 +38,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -68,11 +58,8 @@ jobs:
         continue-on-error: true
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
           GEMINI_MODEL: '${{ matrix.model }}'
-          RUN_EVALS: 'true'
-          EVAL_SUITE_TYPE: "${{ github.event.inputs.suite_type || 'behavioral' }}"
-          EVAL_SUITE_NAME: '${{ github.event.inputs.suite_name }}'
+          RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
           TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
           # Disable Vitest internal retries to avoid double-retrying;
           # custom retry logic is handled in evals/test-helper.ts
@@ -107,8 +94,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Download Logs'
         uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4

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

@@ -48,8 +48,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Log in to GitHub Container Registry'
         uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -68,9 +66,7 @@ jobs:
           ISSUE_NUMBER: '${{ github.event.issue.number }}'
           REPOSITORY: '${{ github.repository }}'
           FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
-          GEMINI_CLI_TRUST_WORKSPACE: 'true'
         with:
-          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -109,12 +105,10 @@ jobs:
                 }
               },
               "maxSessionTurns": 25,
-              "tools": {
-                "core": [
-                  "run_shell_command(echo)",
-                  "run_shell_command(gh issue view)"
-                ]
-              },
+              "coreTools": [
+                "run_shell_command(echo)",
+                "run_shell_command(gh issue view)"
+              ],
               "telemetry": {
                 "enabled": true,
                 "target": "gcp"

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

@@ -90,8 +90,6 @@ jobs:
 
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
@@ -131,31 +129,20 @@ jobs:
             core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
             return labelNames;
 
-      - name: 'Prepare Issue Data'
-        id: 'prepare_issue_data'
-        env:
-          ISSUE_TITLE: >-
-            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.title || github.event.issue.title }}
-          ISSUE_BODY: >-
-            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
-        run: |
-          set -euo pipefail
-          echo "Title: ${ISSUE_TITLE}" > issue_context.md
-          echo "Body:" >> issue_context.md
-          echo "${ISSUE_BODY}" >> issue_context.md
-
       - name: 'Run Gemini Issue Analysis'
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
         id: 'gemini_issue_analysis'
         env:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
+          ISSUE_TITLE: >-
+            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.title || github.event.issue.title }}
+          ISSUE_BODY: >-
+            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
           ISSUE_NUMBER: >-
             ${{ github.event_name == 'workflow_dispatch' && (github.event.inputs.issue_number || inputs.issue_number) || github.event.issue.number }}
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
-          GEMINI_CLI_TRUST_WORKSPACE: 'true'
         with:
-          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -170,12 +157,9 @@ jobs:
                 "enabled": true,
                 "target": "gcp"
               },
-              "tools": {
-                "core": [
-                  "run_shell_command(echo)",
-                  "read_file"
-                ]
-              }
+              "coreTools": [
+                "run_shell_command(echo)"
+              ]
             }
           prompt: |-
             ## Role
@@ -183,7 +167,7 @@ jobs:
             You are an issue triage assistant. Your role is to analyze a GitHub issue and determine the single most appropriate area/ label based on the definitions provided.
 
             ## Steps
-            1. Use the read_file tool to read the file "issue_context.md" which contains the issue title and body.
+            1. Review the issue title and body: ${{ env.ISSUE_TITLE }} and ${{ env.ISSUE_BODY }}.
             2. Review the available labels: ${{ env.AVAILABLE_LABELS }}.
             3. Select exactly one area/ label that best matches the issue based on Reference 1: Area Definitions.
             4. Fallback Logic:
@@ -338,41 +322,14 @@ jobs:
               return;
             }
 
-            const newAreaLabel = labelsToAdd[0];
-
-            // Get current labels to resolve conflicts
-            const { data: currentLabels } = await github.rest.issues.listLabelsOnIssue({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issueNumber,
-            });
-            const currentLabelNames = currentLabels.map(l => l.name);
-            const currentAreaLabels = currentLabelNames.filter(name => name.startsWith('area/'));
-
-            const labelsToRemove = currentAreaLabels.filter(name => name !== newAreaLabel);
-
-            for (const label of labelsToRemove) {
-              try {
-                await github.rest.issues.removeLabel({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issueNumber,
-                  name: label
-                });
-                core.info(`Removed conflicting area label: ${label}`);
-              } catch (e) {
-                core.warning(`Failed to remove label ${label}: ${e.message}`);
-              }
-            }
-
             // Set labels based on triage result
             await github.rest.issues.addLabels({
               owner: context.repo.owner,
               repo: context.repo.repo,
               issue_number: issueNumber,
-              labels: [newAreaLabel]
+              labels: labelsToAdd
             });
-            core.info(`Successfully added labels for #${issueNumber}: ${newAreaLabel}`);
+            core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
 
       - name: 'Post Issue Analysis Failure Comment'
         if: |-

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

@@ -1,350 +0,0 @@
-name: '🧠 Gemini CLI Bot: Brain'
-
-on:
-  schedule:
-    - cron: '0 0 * * *' # Every 24 hours
-  issue_comment:
-    types: ['created']
-  workflow_dispatch:
-    inputs:
-      run_interactive:
-        description: 'Run interactive flow (requires issue_number)'
-        type: 'boolean'
-        default: false
-      issue_number:
-        description: 'Issue/PR number to simulate context from'
-        type: 'string'
-        required: false
-      comment_id:
-        description: 'Specific comment ID to simulate'
-        type: 'string'
-        required: false
-      clear_memory:
-        description: 'Clear memory (drops learnings from previous runs)'
-        type: 'boolean'
-        default: false
-      enable_prs:
-        description: 'Enable PRs (automatically promote changes to PRs)'
-        type: 'boolean'
-        default: false
-
-concurrency:
-  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number || github.ref }}'
-  cancel-in-progress: true
-
-jobs:
-  reasoning:
-    name: 'Brain (Reasoning Layer)'
-    runs-on: 'ubuntu-latest'
-    if: |
-      github.repository == 'google-gemini/gemini-cli' && (
-        github.event_name == 'schedule' ||
-        (github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive != 'true') ||
-        (github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive == 'true') ||
-        (github.event_name == 'issue_comment' && github.event.comment.user.login != 'gemini-cli[bot]' && contains(github.event.comment.body, '@gemini-cli') && contains(fromJSON('["COLLABORATOR", "MEMBER", "OWNER"]'), github.event.comment.author_association))
-      )
-    # The reasoning phase is strictly readonly.
-    permissions:
-      contents: 'read'
-      issues: 'read'
-      actions: 'read'
-    env:
-      GEMINI_CLI_TRUST_WORKSPACE: 'true'
-    steps:
-      - name: 'Determine Checkout Ref'
-        id: 'determine_ref'
-        env:
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
-        run: |
-          REF="${{ github.ref }}"
-          if [ -n "$ISSUE_NUMBER" ]; then
-            PR_HEAD=$(gh pr view "$ISSUE_NUMBER" --repo "${{ github.repository }}" --json headRefName --jq .headRefName 2>/dev/null || echo "")
-            if [ -n "$PR_HEAD" ]; then
-              REF="$PR_HEAD"
-            fi
-          fi
-          echo "ref=$REF" >> "$GITHUB_OUTPUT"
-
-      - name: 'Checkout'
-        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          ref: '${{ steps.determine_ref.outputs.ref }}'
-          fetch-depth: 0
-          persist-credentials: false
-
-      - name: 'Setup Node.js'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
-        with:
-          node-version: '20'
-          cache: 'npm'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-
-      - name: 'Build Gemini CLI'
-        run: 'npm run bundle'
-
-      - name: 'Download Previous State'
-        env:
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-        run: |
-          if [ "${{ github.event.inputs.clear_memory }}" = "true" ]; then
-            echo "Memory clear requested. Skipping previous state download."
-            exit 0
-          fi
-
-          # Find the last successful run of this workflow
-          LAST_RUN_ID=$(gh run list --workflow "${{ github.workflow }}" --status success --limit 1 --json databaseId --jq '.[0].databaseId')
-
-          if [ -n "$LAST_RUN_ID" ]; then
-            echo "Found previous successful run: $LAST_RUN_ID"
-
-            # Download brain memory to a temp dir so we can selectively restore only persistent state
-            mkdir -p .temp_brain_data
-            gh run download "$LAST_RUN_ID" -n brain-data -D .temp_brain_data || echo "brain-data not found"
-
-            # Restore only persistent memory files
-            cp .temp_brain_data/tools/gemini-cli-bot/lessons-learned.md tools/gemini-cli-bot/lessons-learned.md 2>/dev/null || true
-            mkdir -p tools/gemini-cli-bot/history/
-            cp .temp_brain_data/tools/gemini-cli-bot/history/*.csv tools/gemini-cli-bot/history/ 2>/dev/null || true
-            rm -rf .temp_brain_data
-          else
-            echo "No previous successful run found."
-          fi
-
-      - name: 'Collect Current Metrics'
-        env:
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-        run: 'npx tsx tools/gemini-cli-bot/metrics/index.ts'
-
-      - name: 'Run Brain Phases'
-        env:
-          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          GEMINI_MODEL: 'gemini-3-flash-preview'
-          GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
-          ENABLE_PRS: "${{ github.event.inputs.enable_prs || 'false' }}"
-          TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
-          TRIGGER_COMMENT_ID: '${{ github.event.comment.id || github.event.inputs.comment_id }}'
-        run: |
-          PROMPT_PATH="tools/gemini-cli-bot/brain/scheduled.md"
-          if [ "${{ github.event_name }}" = "issue_comment" ] || [ "${{ github.event.inputs.run_interactive }}" = "true" ]; then
-            PROMPT_PATH="tools/gemini-cli-bot/brain/interactive.md"
-            export ENABLE_PRS="true"
-          fi
-
-          touch trigger_context.md
-          if [ -n "$TRIGGER_ISSUE_NUMBER" ]; then
-            echo "<untrusted_context>" > trigger_context.md
-            echo "# Interactive Trigger Context" >> trigger_context.md
-            echo "You were invoked by a user in issue/PR #$TRIGGER_ISSUE_NUMBER." >> trigger_context.md
-
-            if [ -n "$TRIGGER_COMMENT_ID" ]; then
-              echo "## User Comment" >> trigger_context.md
-              gh api "repos/${{ github.repository }}/issues/comments/$TRIGGER_COMMENT_ID" -q '.body' >> trigger_context.md 2>/dev/null || gh api "repos/${{ github.repository }}/pulls/comments/$TRIGGER_COMMENT_ID" -q '.body' >> trigger_context.md
-              echo "" >> trigger_context.md
-            fi
-
-            echo "## Issue/PR Context" >> trigger_context.md
-            gh issue view "$TRIGGER_ISSUE_NUMBER" >> trigger_context.md 2>/dev/null || gh pr view "$TRIGGER_ISSUE_NUMBER" >> trigger_context.md
-            echo "</untrusted_context>" >> trigger_context.md
-          fi
-
-          if [ "$ENABLE_PRS" = "true" ]; then
-            echo "**System Directive**: PR creation is ENABLED for this run. You MUST activate the **'prs' skill** to stage your changes and generate a \`pr-description.md\` file if you are proposing fixes." >> trigger_context.md
-            echo "**CRITICAL System Directive**: You MUST ONLY propose and implement a **SINGLE** improvement or fix per run. Bundling unrelated changes (e.g., a documentation update and a script fix, or a metrics update and a logic fix) into a single PR is STRICTLY FORBIDDEN and will result in immediate rejection during the critique phase. If you identify multiple issues, pick the most impactful one and ignore the others for now." >> trigger_context.md
-          else
-            echo "**System Directive**: PR creation is DISABLED for this run. You MUST NOT stage files or attempt to create a PR description." >> trigger_context.md
-          fi
-          echo "" >> trigger_context.md
-
-          cat trigger_context.md "$PROMPT_PATH" > combined_prompt.md
-          node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat combined_prompt.md)"
-
-          if [ -n "$TRIGGER_ISSUE_NUMBER" ] && [ ! -s "issue-comment.md" ] && [ ! -s "pr-comment.md" ]; then
-            echo "Agent failed to respond. Generating fallback error message."
-            echo "⚠️ **Gemini CLI Bot failed to generate a response.**" > "issue-comment.md"
-            echo "" >> "issue-comment.md"
-            echo "I encountered an error or failed to generate a complete response to your request. You can check the [GitHub Actions Run Log](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) for more details on what went wrong." >> "issue-comment.md"
-          fi
-
-      - name: 'Run Critique Phase'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
-        env:
-          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          GEMINI_MODEL: 'gemini-3-flash-preview'
-          GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
-        run: |
-          if git diff --staged --quiet; then
-             echo "No changes staged. Skipping critique."
-             echo "[APPROVED]" > critique_result.txt
-          else
-             node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat tools/gemini-cli-bot/.gemini/skills/critique/SKILL.md)" 2>&1 | tee critique_output.log
-
-             if [ "${PIPESTATUS[0]}" -eq 0 ] && grep -q "\[APPROVED\]" critique_output.log && ! grep -q "\[REJECTED\]" critique_output.log; then
-               echo "[APPROVED]" > critique_result.txt
-             else
-               echo "Critique failed, rejected, or did not explicitly approve changes. Skipping PR creation."
-               echo "[REJECTED]" > critique_result.txt
-             fi
-          fi
-
-      - name: 'Generate Patch'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
-        run: |
-          touch bot-changes.patch
-          touch pr-description.md
-          if [ -f critique_result.txt ] && grep -q "\[APPROVED\]" critique_result.txt && ! grep -q "\[REJECTED\]" critique_result.txt; then
-             git diff --staged > bot-changes.patch
-          else
-             echo "Critique did not approve. Skipping patch generation."
-          fi
-
-      - name: 'Archive Brain Data'
-        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
-        with:
-          name: 'brain-data'
-          path: |
-            tools/gemini-cli-bot/lessons-learned.md
-            tools/gemini-cli-bot/history/*.csv
-            bot-changes.patch
-            pr-description.md
-            branch-name.txt
-            pr-comment.md
-            pr-number.txt
-            issue-comment.md
-          retention-days: 90
-
-  publish:
-    name: 'Publish Artifacts (Archive Layer)'
-    needs: 'reasoning'
-    runs-on: 'ubuntu-latest'
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    # The publish phase is for archiving artifacts and optionally creating PRs.
-    permissions:
-      contents: 'write'
-      pull-requests: 'write'
-      actions: 'write'
-    steps:
-      - name: 'Generate GitHub App Token 🔑'
-        id: 'generate_token'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
-        uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
-        with:
-          app-id: '${{ secrets.APP_ID }}'
-          private-key: '${{ secrets.PRIVATE_KEY }}'
-          owner: '${{ github.repository_owner }}'
-          repositories: '${{ github.event.repository.name }}'
-          permission-contents: 'write'
-          permission-pull-requests: 'write'
-          permission-issues: 'write'
-
-      - name: 'Determine Checkout Ref'
-        id: 'determine_ref'
-        env:
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
-        run: |
-          REF="main"
-          if [ -n "$ISSUE_NUMBER" ]; then
-            PR_HEAD=$(gh pr view "$ISSUE_NUMBER" --repo "${{ github.repository }}" --json headRefName --jq .headRefName 2>/dev/null || echo "")
-            if [ -n "$PR_HEAD" ]; then
-              REF="$PR_HEAD"
-            fi
-          fi
-          echo "ref=$REF" >> "$GITHUB_OUTPUT"
-
-      - name: 'Checkout'
-        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          ref: '${{ steps.determine_ref.outputs.ref }}'
-          fetch-depth: 0
-          persist-credentials: false
-
-      - name: 'Download Brain Data'
-        uses: 'actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093' # ratchet:actions/download-artifact@v4
-        with:
-          name: 'brain-data'
-          path: '${{ runner.temp }}/brain-data/'
-
-      - name: 'Create or Update PR'
-        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
-        env:
-          GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
-          FALLBACK_PAT: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
-        run: |
-          if [ -s "${{ runner.temp }}/brain-data/bot-changes.patch" ]; then
-            git config user.name "gemini-cli[bot]"
-            git config user.email "gemini-cli[bot]@users.noreply.github.com"
-            git remote set-url origin "https://x-access-token:${GH_TOKEN}@github.com/${{ github.repository }}.git"
-
-            BRANCH_NAME="bot/productivity-updates-$(date +'%Y%m%d%H%M%S')-${{ github.run_id }}"
-            if [ -f "${{ runner.temp }}/brain-data/branch-name.txt" ]; then
-              BRANCH_NAME=$(cat "${{ runner.temp }}/brain-data/branch-name.txt")
-            fi
-
-            if [[ ! "$BRANCH_NAME" =~ ^bot/ ]]; then
-              echo "Error: Branch name '$BRANCH_NAME' does not start with 'bot/'. Safety abort."
-              exit 1
-            fi
-
-            git checkout -B "$BRANCH_NAME"
-            git apply "${{ runner.temp }}/brain-data/bot-changes.patch"
-            git add .
-
-            if [ -s "${{ runner.temp }}/brain-data/pr-description.md" ]; then
-              git commit -F "${{ runner.temp }}/brain-data/pr-description.md"
-            else
-              git commit -m "🤖 Gemini Bot Productivity Optimizations"
-            fi
-
-            PR_TITLE="🤖 Gemini Bot Productivity Optimizations"
-            if [ -s "${{ runner.temp }}/brain-data/pr-description.md" ]; then
-              PR_TITLE=$(head -n 1 "${{ runner.temp }}/brain-data/pr-description.md")
-            fi
-
-            if ! git push origin "$BRANCH_NAME" --force; then
-              echo "Push failed. Retrying with FALLBACK_PAT..."
-              export GH_TOKEN="$FALLBACK_PAT"
-              git remote set-url origin "https://x-access-token:${FALLBACK_PAT}@github.com/${{ github.repository }}.git"
-              git push origin "$BRANCH_NAME" --force
-            fi
-
-            if ! gh pr view "$BRANCH_NAME" > /dev/null 2>&1; then
-              gh pr create --draft --title "$PR_TITLE" --body-file "${{ runner.temp }}/brain-data/pr-description.md" --head "$BRANCH_NAME" --base main || \
-              gh pr create --draft --title "🤖 Gemini Bot Productivity Optimizations" --body "Automated changes generated by Gemini CLI Bot." --head "$BRANCH_NAME" --base main
-            else
-              PR_STATE=$(gh pr view "$BRANCH_NAME" --json state --jq .state)
-              if [ "$PR_STATE" = "CLOSED" ]; then
-                NEW_BRANCH_NAME="${BRANCH_NAME}-retry-${{ github.run_id }}"
-                git checkout -b "$NEW_BRANCH_NAME"
-                git push origin "$NEW_BRANCH_NAME" --force
-                gh pr create --draft --title "$PR_TITLE" --body-file "${{ runner.temp }}/brain-data/pr-description.md" --head "$NEW_BRANCH_NAME" --base main || \
-                gh pr create --draft --title "🤖 Gemini Bot Productivity Optimizations" --body "Automated changes generated by Gemini CLI Bot." --head "$NEW_BRANCH_NAME" --base main
-              fi
-            fi
-          fi
-
-      - name: 'Post PR/Issue Comment'
-        env:
-          GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
-          TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
-        run: |
-          if [ -s "${{ runner.temp }}/brain-data/issue-comment.md" ] && [ -n "$TRIGGER_ISSUE_NUMBER" ]; then
-            echo "Posting comment to triggering issue #$TRIGGER_ISSUE_NUMBER"
-            # Use REST API (gh api) instead of GraphQL (gh issue comment) to ensure robot identity
-            # while avoiding potential GraphQL-specific authorization hurdles with PATs.
-            gh api "repos/${{ github.repository }}/issues/$TRIGGER_ISSUE_NUMBER/comments" -F body=@"${{ runner.temp }}/brain-data/issue-comment.md"
-          fi
-
-          if [ -s "${{ runner.temp }}/brain-data/pr-comment.md" ] && [ -f "${{ runner.temp }}/brain-data/pr-number.txt" ]; then
-            PR_NUM=$(cat "${{ runner.temp }}/brain-data/pr-number.txt")
-
-            # Using GitHub App, so author check is no longer valid against gemini-cli-robot
-            # Skipping author validation here to let the app post.
-
-            # Use REST API (gh api) for consistency and robot identity
-            gh api "repos/${{ github.repository }}/issues/$PR_NUM/comments" -F body=@"${{ runner.temp }}/brain-data/pr-comment.md"
-          fi

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

@@ -1,49 +0,0 @@
-name: '🔄 Gemini CLI Bot: Pulse'
-
-on:
-  schedule:
-    - cron: '*/30 * * * *' # Every 30 minutes
-  workflow_dispatch:
-
-concurrency:
-  group: '${{ github.workflow }}-${{ github.ref }}'
-  cancel-in-progress: true
-
-permissions:
-  contents: 'write'
-  issues: 'write'
-  pull-requests: 'write'
-
-jobs:
-  pulse:
-    name: 'Pulse (Reflex Layer)'
-    runs-on: 'ubuntu-latest'
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    steps:
-      - name: 'Checkout'
-        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
-          fetch-depth: 0
-
-      - name: 'Setup Node.js'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
-        with:
-          node-version: '20'
-          cache: 'npm'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-
-      - name: 'Run Reflex Processes'
-        env:
-          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-        run: |
-          if [ -d "tools/gemini-cli-bot/reflexes/scripts" ] && [ "$(ls -A tools/gemini-cli-bot/reflexes/scripts)" ]; then
-            for script in tools/gemini-cli-bot/reflexes/scripts/*.ts; do
-              echo "Running reflex script: $script"
-              npx tsx "$script"
-            done
-          else
-            echo "No reflex scripts found."
-          fi

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

@@ -1,47 +0,0 @@
-name: '🔄 Gemini Scheduled Lifecycle Manager'
-
-on:
-  schedule:
-    - cron: '30 1 * * *' # Once a day
-  workflow_dispatch:
-    inputs:
-      dry_run:
-        description: 'Run in dry-run mode (no changes applied)'
-        required: false
-        default: false
-        type: 'boolean'
-
-concurrency:
-  group: '${{ github.workflow }}'
-  cancel-in-progress: true
-
-permissions:
-  issues: 'write'
-  pull-requests: 'write'
-
-jobs:
-  manage-lifecycle:
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    runs-on: 'ubuntu-latest'
-    steps:
-      - name: 'Generate GitHub App Token'
-        id: 'generate_token'
-        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
-        with:
-          app-id: '${{ secrets.APP_ID }}'
-          private-key: '${{ secrets.PRIVATE_KEY }}'
-
-      - name: 'Checkout repository'
-        uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
-        with:
-          persist-credentials: false
-
-      - name: 'Lifecycle Management'
-        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
-        env:
-          DRY_RUN: '${{ inputs.dry_run }}'
-        with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
-          script: |
-            const script = require('./.github/scripts/gemini-lifecycle-manager.cjs');
-            await script({github, context, core});

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

@@ -28,8 +28,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
 
       - name: 'Log in to GitHub Container Registry'
         uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -49,7 +47,6 @@ jobs:
           REPOSITORY: '${{ github.repository }}'
           FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
         with:
-          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -88,11 +85,9 @@ jobs:
                 }
               },
               "maxSessionTurns": 25,
-              "tools": {
-                "core": [
-                  "run_shell_command(echo)"
-                ]
-              },
+              "coreTools": [
+                "run_shell_command(echo)"
+              ],
               "telemetry": {
                 "enabled": true,
                 "target": "gcp"

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

@@ -1,6 +1,10 @@
 name: '📋 Gemini Scheduled Issue Triage'
 
 on:
+  issues:
+    types:
+      - 'opened'
+      - 'reopened'
   schedule:
     - cron: '0 * * * *' # Runs every hour
   workflow_dispatch:
@@ -19,27 +23,13 @@ permissions:
 
 jobs:
   triage-issues:
-    timeout-minutes: 60
+    timeout-minutes: 10
     if: |-
       ${{ github.repository == 'google-gemini/gemini-cli' }}
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
-        with:
-          persist-credentials: false
-
-      - name: 'Install Utilities'
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y ripgrep
-
-      - name: 'Get Current Version'
-        id: 'get_version'
-        run: |
-          VERSION=$(jq -r .version package.json | cut -d'-' -f1)
-          echo "version=${VERSION}" >> "${GITHUB_OUTPUT}"
-          echo "🚀 Current CLI Version: ${VERSION}"
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
@@ -57,38 +47,10 @@ jobs:
           ISSUE_EVENT: '${{ toJSON(github.event.issue) }}'
         run: |
           set -euo pipefail
-          echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]' > issues_to_triage.json
-          echo "has_issues=true" >> "${GITHUB_OUTPUT}"
+          ISSUE_JSON=$(echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]')
+          echo "issues_to_triage=${ISSUE_JSON}" >> "${GITHUB_OUTPUT}"
           echo "✅ Found issue #${{ github.event.issue.number }} from event to triage! 🎯"
 
-      - name: 'Sync Issue Types'
-        if: |-
-          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
-        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
-        with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
-          script: |-
-            const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
-            await syncIssueTypes({ github, context, core });
-
-      - name: 'Find Issues with Conflicting Labels'
-        if: |-
-          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
-        env:
-          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
-          GITHUB_REPOSITORY: '${{ github.repository }}'
-        run: |-
-          set -euo pipefail
-          echo '🔍 Fetching open issues to find conflicts...'
-          # Fetch up to 2000 open issues in one quick GraphQL-backed query
-          gh issue list --repo "${GITHUB_REPOSITORY}" --search "is:issue is:open" --limit 2000 --json number,title,body,labels > all_open_issues.json
-
-          echo '🧹 Filtering issues with multiple area/ or priority/ labels...'
-          jq -c '[ .[] | select( (.labels | map(select(.name | startswith("area/"))) | length) > 1 or (.labels | map(select(.name | startswith("priority/"))) | length) > 1 ) ] | .[0:50]' all_open_issues.json > conflicting_labels_issues.json
-
-          CONFLICT_COUNT=$(jq 'length' conflicting_labels_issues.json)
-          echo "Found ${CONFLICT_COUNT} issues with conflicting labels (capped at 50 for processing)."
-
       - name: 'Find untriaged issues'
         if: |-
           ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -100,56 +62,25 @@ jobs:
           set -euo pipefail
 
           echo '🔍 Finding issues missing area labels...'
-          gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 50 --json number,title,body,labels > no_area_issues.json
+          NO_AREA_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 100 --json number,title,body)"
 
           echo '🔍 Finding issues missing kind labels...'
-          gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 50 --json number,title,body,labels > no_kind_issues.json
+          NO_KIND_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 100 --json number,title,body)"
 
           echo '🏷️ Finding issues missing priority labels...'
-          gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 50 --json number,title,body,labels > no_priority_issues.json
+          NO_PRIORITY_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 100 --json number,title,body)"
 
-          echo '📏 Finding issues missing effort labels...'
-          gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:effort/small -label:effort/medium -label:effort/large label:area/core,area/extensions,area/site,area/non-interactive' --limit 20 --json number,title,body,labels > no_effort_issues.json
+          echo '🔄 Merging and deduplicating issues...'
+          ISSUES="$(echo "${NO_AREA_ISSUES}" "${NO_KIND_ISSUES}" "${NO_PRIORITY_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
 
-          echo '🔄 Merging and deduplicating standard triage issues...'
-          if [ ! -f conflicting_labels_issues.json ]; then echo "[]" > conflicting_labels_issues.json; fi
-          jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json conflicting_labels_issues.json > standard_issues_to_triage.json
+          echo '📝 Setting output for GitHub Actions...'
+          echo "issues_to_triage=${ISSUES}" >> "${GITHUB_OUTPUT}"
 
-          echo '📏 Deduplicating effort issues...'
-          jq -c -s 'add | unique_by(.number)' no_effort_issues.json > effort_issues_to_triage.json
-
-          STANDARD_COUNT="$(jq 'length' standard_issues_to_triage.json)"
-          EFFORT_COUNT="$(jq 'length' effort_issues_to_triage.json)"
-          if [ "$STANDARD_COUNT" -gt 0 ] || [ "$EFFORT_COUNT" -gt 0 ]; then
-            echo "has_issues=true" >> "${GITHUB_OUTPUT}"
-            echo "has_standard_issues=$([ "$STANDARD_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
-            echo "has_effort_issues=$([ "$EFFORT_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
-          else
-            echo "has_issues=false" >> "${GITHUB_OUTPUT}"
-            echo "has_standard_issues=false" >> "${GITHUB_OUTPUT}"
-            echo "has_effort_issues=false" >> "${GITHUB_OUTPUT}"
-          fi
-          echo "✅ Found ${STANDARD_COUNT} standard issues and ${EFFORT_COUNT} effort issues to triage! 🎯"
-
-      - name: 'Create Gemini CLI Experiments Override'
-        if: |-
-          steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_issues == 'true'
-        run: |
-          cat << 'EOF' > gemini_exp.json
-          {
-            "flags": [
-              {
-                "flagId": 45750526,
-                "boolValue": false
-              }
-            ],
-            "experimentIds": []
-          }
-          EOF
+          ISSUE_COUNT="$(echo "${ISSUES}" | jq 'length')"
+          echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
 
       - name: 'Get Repository Labels'
         id: 'get_labels'
@@ -166,22 +97,18 @@ jobs:
             core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
             return labelNames;
 
-      - name: 'Run Standard Triage Analysis'
+      - name: 'Run Gemini Issue Analysis'
         if: |-
-          steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_standard_issues == 'true'
+          (steps.get_issue_from_event.outputs.issues_to_triage != '' && steps.get_issue_from_event.outputs.issues_to_triage != '[]') ||
+          (steps.find_issues.outputs.issues_to_triage != '' && steps.find_issues.outputs.issues_to_triage != '[]')
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
-        id: 'gemini_standard_issue_analysis'
+        id: 'gemini_issue_analysis'
         env:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
+          ISSUES_TO_TRIAGE: '${{ steps.get_issue_from_event.outputs.issues_to_triage || steps.find_issues.outputs.issues_to_triage }}'
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
-          CLI_VERSION: '${{ steps.get_version.outputs.version }}'
-          GEMINI_CLI_TRUST_WORKSPACE: 'true'
-          GEMINI_EXP: 'gemini_exp.json'
-          GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
-          GEMINI_MODEL: 'gemini-3-flash-preview'
         with:
-          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -192,14 +119,11 @@ jobs:
           settings: |-
             {
               "maxSessionTurns": 25,
-              "tools": {
-                "core": [
-                  "run_shell_command(echo)",
-                  "read_file"
-                ]
-              },
+              "coreTools": [
+                "run_shell_command(echo)"
+              ],
               "telemetry": {
-                "enabled": false,
+                "enabled": true,
                 "target": "gcp"
               }
             }
@@ -212,16 +136,14 @@ jobs:
 
             ## Steps
 
-            1. You are only able to use the echo and read_file commands. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
-            2. Use the read_file tool to read the file "standard_issues_to_triage.json" which contains the JSON array of issues to triage (including their current labels).
-            3. Review the issue title, body, current labels, and any comments provided in the JSON file.
-            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/*, and priority/*.
+            1. You are only able to use the echo command. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
+            2. Check environment variable for issues to triage: $ISSUES_TO_TRIAGE (JSON array of issues)
+            3. Review the issue title, body and any comments provided in the environment variables.
+            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/* and priority/*.
             5. Label Policy:
                - If the issue already has a kind/ label, do not change it.
-               - If the issue has exactly ONE priority/ label, do not change it (unless you are explicitly re-evaluating an ambiguous priority).
-               - If the issue is missing a priority/ label, OR if the issue currently has MULTIPLE priority/ labels, you must evaluate the issue's impact to determine exactly ONE priority level (priority/p0, priority/p1, priority/p2, priority/p3, or priority/unknown) based the guidelines. If you are fixing an issue with multiple priority/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
-               - If the issue has exactly ONE area/ label, do not change it.
-               - If the issue is missing an area/ label, OR if the issue currently has MULTIPLE area/ labels, select exactly ONE area/ label that best fits the issue. Issues MUST NOT have multiple area/ labels. If you are fixing an issue with multiple area/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
+               - If the issue already has a priority/ label, do not change it.
+               - If the issue already has an area/ label, do not change it.
                - If any of these are missing, select exactly ONE appropriate label for the missing category.
             6. Identify other applicable labels based on the issue content, such as status/*, help wanted, good first issue, etc.
             7. Give me a single short explanation about why you are selecting each label in the process.
@@ -238,12 +160,11 @@ jobs:
                ]
                ```
               If an issue cannot be classified, do not include it in the output array.
-            9. For each issue, carefully check if the CLI version is present. It is usually found under the "### Client information" header, as a bullet point (e.g., "• CLI Version: 0.33.1", "* **CLI Version:** 0.42.0"), or in the output of the `/about` command.
-              - **Only for issues classified as kind/bug:** If the version is provided but is more than 6 minor versions older than the most recent release (current version is ${{ steps.get_version.outputs.version }}), apply the status/need-information label and leave a comment politely asking the user to verify if the issue persists in the latest version.
-            10. **Only for issues classified as kind/bug:** If the issue does not have sufficient information, recommend the status/need-information label and leave a comment politely requesting the missing details. For example, if repro steps are missing, ask for them; if the CLI version is completely missing, ask for the version information in the explanation section below. Do not ask for version info if it is already in the issue body. (Check both bullet points and bold text). For features and enhancements, the CLI version is NOT required.
-            11. If you think an issue is a Priority/P0, you MUST apply the priority/p1 label AND the status/manual-triage label, and include a note in your explanation that it likely requires P0 escalation.
-            12. If the issue is highly ambiguous, completely lacks a description, or you are torn between two lower priorities (like P2 vs P3), you MUST retain the existing priority label if one is already present. Do not toggle the priority if you do not have enough information to make a definitive change.
-            13. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
+            9. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
+              - Anything more than 6 versions older than the most recent should add the status/need-retesting label
+            10. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
+            11. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
+            12. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
 
             ## Guidelines
 
@@ -253,127 +174,10 @@ jobs:
               - Do not add comments or modify the issue content.
               - Do not remove the following labels maintainer, help wanted or good first issue.
               - Triage only the current issue.
-              - Identify exactly ONE area/ label. Do NOT assign multiple area/ labels to a single issue.
+              - Identify only one area/ label.
               - Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
-              - Identify exactly ONE priority/ label. Do NOT assign multiple priority/ labels to a single issue.
-              - **Do not manually downgrade the priority.** Always assign the true priority based on the guidelines. The system will handle downgrades programmatically if information is missing.
-              - **NEVER mention label names, label removals, or label additions in your `explanation`.** The explanation must be purely written for the user (e.g., "Please provide your CLI version.") without exposing internal triage mechanics (e.g., do NOT say "Removing area/unknown to leave only area/core").
-
-            Categorization Guidelines (Priority):
-            P0 - Urgent Blocking Issues:
-              - DO NOT APPLY THE priority/p0 LABEL AUTOMATICALLY. Instead apply priority/p1 and status/manual-triage.
-              - Definition: Critical failures breaking core functionality for a large portion of users. Examples: CLI fails to launch globally, core commands (gemini run) crash on valid input, unhandled promise rejections on boot, critical security vulnerability.
-              - Note: You must apply priority/p1 and status/manual-triage instead of priority/p0.
-            P1 - Critical but Workable:
-              - Definition: Severe issues without a reasonable workaround, significantly degrading the developer experience but not globally blocking. Examples: Specific tools failing consistently (e.g., `web_search` returns 500s), persistent PTY streaming hangs, memory leaks leading to OOM after short use.
-            P2 - Significant Issues:
-              - Definition: Affect some workflows but a clear workaround exists, or non-critical bugs. Examples: Theme flickering, confusing error messages, minor UI misalignment, failing to read deeply nested config files correctly.
-            P3 - Minor/Enhancements:
-              - Definition: Trivial bugs, typos, documentation requests, or feature requests.
-
-            Categorization Guidelines (Kind):
-            kind/bug: The issue is describing an unexpected behavior or failure in the application.
-            kind/enhancement: The issue is describing a feature request or an improvement to an existing feature.
-            kind/question: The issue is asking a question about how to use the CLI or about a specific feature.
-
-            Categorization Guidelines (Area):
-            area/agent: The "brain" of the CLI. Core agent logic, model quality, tool/function calling, memory, web search, generated code quality, sub-agents.
-            area/core: The fundamental CLI app. UI/UX, installation, OS compatibility, performance, command parsing, theming, flickering.
-            area/documentation: Website docs, READMEs, inline help text.
-            area/enterprise: Telemetry, Policy, Quota / Licensing
-            area/extensions: Gemini CLI extensions capability
-            area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation
-            area/platform: Platform specific behavior
-            area/security: Authentication, authorization, privacy, data leaks, credential storage.
-
-      - name: 'Stop Telemetry Collector'
-        if: |-
-          steps.find_issues.outputs.has_effort_issues == 'true'
-        run: 'docker rm -f gemini-telemetry-collector || true'
-
-      - name: 'Run Effort Triage Analysis'
-        if: |-
-          steps.find_issues.outputs.has_effort_issues == 'true'
-        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
-        id: 'gemini_effort_issue_analysis'
-        env:
-          GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
-          REPOSITORY: '${{ github.repository }}'
-          AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
-          CLI_VERSION: '${{ steps.get_version.outputs.version }}'
-          GEMINI_CLI_TRUST_WORKSPACE: 'true'
-          GEMINI_EXP: 'gemini_exp.json'
-          GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
-          GEMINI_MODEL: 'gemini-3-flash-preview'
-        with:
-          upload_artifacts: 'true'
-          gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
-          gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
-          gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
-          gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
-          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
-          use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
-          use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
-          settings: |-
-            {
-              "maxSessionTurns": 30,
-              "tools": {
-                "core": [
-                  "run_shell_command(echo)",
-                  "grep_search",
-                  "glob",
-                  "read_file"
-                ]
-              },
-              "telemetry": {
-                "enabled": false,
-                "target": "gcp"
-              }
-            }
-          prompt: |-
-            ## Role
-
-            You are an expert software architect. Analyze the provided GitHub issues and assign the correct `effort/*` label based on the codebase complexity.
-
-            ## Steps
-
-            1. Use the read_file tool to read "effort_issues_to_triage.json".
-            2. For each issue in the array:
-               - You must evaluate the architectural complexity to determine the effort level. You MUST NOT guess the root cause. You MUST actively use your codebase search tools (grep_search and glob) to search for keywords from the issue and explore the codebase. You must identify the specific files and components involved before deciding the effort.
-            3. Output a JSON array of objects, each containing the issue number and the effort label to add, along with an explanation and an effort_analysis field. This effort_analysis must be highly detailed, technical, and empirical. It MUST NOT contain vague guesses (e.g., avoid words like "likely points to" or "possibly"). You must explicitly cite the specific file paths and architectural mechanisms you discovered using your search tools, explain the root cause, and then explicitly state how that complexity maps to the chosen effort level guidelines. For example:
-               ```
-               [
-                 {
-                   "issue_number": 123,
-                   "labels_to_add": ["effort/small"],
-                   "explanation": "This is a simple logic fix.",
-                   "effort_analysis": "The `vscode-ide-companion` extension indiscriminately tracks active text editors via `vscode.window.onDidChangeActiveTextEditor` in `open-files-manager.ts`. When a user opens `.vscode/settings.json`, its content is sent to the CLI's context. The fix is highly localized to the VS Code companion extension's event listener. It involves adding a simple conditional check to exclude specific configuration files from the active editor tracking logic, which is a trivial logic adjustment with a clear root cause."
-                 }
-               ]
-               ```
-
-            ## Guidelines
-
-            - Output only valid JSON format
-            - Do not include any explanation or additional text, just the JSON
-            - Triage only the current issue.
-
-            Categorization Guidelines (Effort):
-            effort/small (1 day or less):
-              - Trivial Logic & Config: Schema updates (Zod), feature flag toggles, adding missing fields to package.json or settings.json.
-              - UI/Aesthetic Adjustments: Fixing minor layout bugs in Ink components (e.g., adding flexShrink, correcting padding in a single Box), text color changes.
-              - Documentation & Strings: Typos, log message updates, CLI argument descriptions.
-              - Localized Bug Fixes: Single-file logic errors, straightforward promise rejections (e.g., wrapping a known failure in a try/catch), simple regex or string parsing fixes.
-            effort/medium (2-3 days):
-              - React/Ink State Management: Debugging useState/useEffect/useReducer bugs, component lifecycle issues (memory leaks in the UI), terminal redraw flickering, or state synchronization between the CLI's internal input buffer and the interactive React components.
-              - Asynchronous Flow & Integration: Resolving complex Promise chains, ERR_STREAM_PREMATURE_CLOSE, debugging IDE companion extensions (VS Code, Android Studio) or resolving hanging HTTP requests/IPC between the CLI and external plugins, timeouts in non-interactive/ACP modes.
-              - Tooling & Output Parsers: Modifying how tools parse streaming stdout/stderr buffers, adding new built-in tools that don't require native bindings.
-              - Cross-Component Refactors: Changes that span across packages/cli and packages/core to pass new data models or telemetry state.
-            effort/large (3+ days):
-              - Platform-Specific Complexities (PTY/Signals): Any issue involving node-pty, child_process.spawn, OS-level shell behavior (Windows vs Linux vs macOS), pseudo-terminal exhaustion (ENXIO), raw mode terminal desyncs, or POSIX signal forwarding (SIGINT/SIGTERM).
-              - Core Architecture & Protocols: Refactoring the Scheduler, Agent-to-Agent (A2A) protocol implementation, low-level MCP (Model Context Protocol) transport mechanisms.
-              - Performance & Memory: Diagnosing massive disk/memory leaks, severe boot time regressions, high-throughput streaming optimizations (e.g., voice streaming pipelines).
-            Note: Any bug that is described as intermittent, flickering, difficult to reproduce, platform-specific, or requiring cross-environment setups (e.g., involving the VS Code IDE companion, GCA plugin, or Android Studio) MUST NOT be rated as effort/small because of the increased overhead of testing and reproducing.
+              - Identify only one priority/ label.
+              - Once you categorize the issue if it needs information bump down the priority by 1 eg.. a p0 would become a p1 a p1 would become a p2. P2 and P3 can stay as is in this scenario.
 
             Categorization Guidelines (Priority):
             P0 - Urgent Blocking Issues:
@@ -412,52 +216,64 @@ jobs:
             - This product is designed to use different models eg.. using pro, downgrading to flash etc.
             - When users report that they dont expect the model to change those would be categorized as feature requests.
 
-      - name: 'Apply Triaged Labels'
+      - name: 'Apply Labels to Issues'
         if: |-
-          always() &&
-          ( (steps.gemini_standard_issue_analysis.outcome == 'success' && steps.gemini_standard_issue_analysis.outputs.summary != '[]' && steps.gemini_standard_issue_analysis.outputs.summary != '') ||
-            (steps.gemini_effort_issue_analysis.outcome == 'success' && steps.gemini_effort_issue_analysis.outputs.summary != '[]' && steps.gemini_effort_issue_analysis.outputs.summary != '') )
+          ${{ steps.gemini_issue_analysis.outcome == 'success' &&
+              steps.gemini_issue_analysis.outputs.summary != '[]' }}
         env:
-          LABELS_OUTPUT_STANDARD: '${{ steps.gemini_standard_issue_analysis.outputs.summary }}'
-          LABELS_OUTPUT_EFFORT: '${{ steps.gemini_effort_issue_analysis.outputs.summary }}'
+          REPOSITORY: '${{ github.repository }}'
+          LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
           github-token: '${{ steps.generate_token.outputs.token }}'
           script: |-
-            const applyLabels = require('./.github/scripts/apply-issue-labels.cjs');
-            await applyLabels({ github, context, core });
+            const rawLabels = process.env.LABELS_OUTPUT;
+            core.info(`Raw labels JSON: ${rawLabels}`);
+            let parsedLabels;
+            try {
+              const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
+              if (!jsonMatch || !jsonMatch[1]) {
+                throw new Error("Could not find a ```json ... ``` block in the output.");
+              }
+              const jsonString = jsonMatch[1].trim();
+              parsedLabels = JSON.parse(jsonString);
+              core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
+            } catch (err) {
+              core.setFailed(`Failed to parse labels JSON from Gemini output: ${err.message}\nRaw output: ${rawLabels}`);
+              return;
+            }
 
-      - name: 'Sync Issue Types (Post-Analysis)'
-        if: |-
-          always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
-        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
-        with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
-          script: |-
-            const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
-            await syncIssueTypes({ github, context, core });
+            for (const entry of parsedLabels) {
+              const issueNumber = entry.issue_number;
+              if (!issueNumber) {
+                core.info(`Skipping entry with no issue number: ${JSON.stringify(entry)}`);
+                continue;
+              }
 
-      - name: 'Find Triaged Issues to Clean Up'
-        if: |-
-          always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
-        env:
-          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
-          GITHUB_REPOSITORY: '${{ github.repository }}'
-        run: |-
-          set -euo pipefail
-          echo '🧹 Finding issues that have conflicting status labels...'
-          gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue label:status/bot-triaged label:status/need-triage' --limit 50 --json number > cleanup_1.json
-          gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue label:status/bot-triaged label:status/manual-triage' --limit 50 --json number > cleanup_2.json
-          jq -c -s 'add | unique_by(.number)' cleanup_1.json cleanup_2.json > issues_to_cleanup.json
+              const labelsToAdd = entry.labels_to_add || [];
+              labelsToAdd.push('status/bot-triaged');
 
-      - name: 'Clean Up Triage Labels'
-        if: |-
-          always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
-        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
-        with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
-          script: |-
-            const cleanupLabels = require('./.github/scripts/cleanup-triage-labels.cjs');
-            await cleanupLabels({ github, context, core });
+              if (labelsToAdd.length > 0) {
+                await github.rest.issues.addLabels({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issueNumber,
+                  labels: labelsToAdd
+                });
+                const explanation = entry.explanation ? ` - ${entry.explanation}` : '';
+                core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`);
+              }
+
+              if (entry.explanation) {
+                await github.rest.issues.createComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issueNumber,
+                  body: entry.explanation,
+                });
+              }
+
+              if ((!entry.labels_to_add || entry.labels_to_add.length === 0) && (!entry.labels_to_remove || entry.labels_to_remove.length === 0)) {
+                core.info(`No labels to add or remove for #${issueNumber}, leaving as is`);
+              }
+            }

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

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

.github/workflows/gemini-scheduled-stale-issue-closer.yml

@@ -0,0 +1,159 @@
+name: '🔒 Gemini Scheduled Stale Issue Closer'
+
+on:
+  schedule:
+    - cron: '0 0 * * 0' # Every Sunday at midnight UTC
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: 'Run in dry-run mode (no changes applied)'
+        required: false
+        default: false
+        type: 'boolean'
+
+concurrency:
+  group: '${{ github.workflow }}'
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: 'bash'
+
+jobs:
+  close-stale-issues:
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    runs-on: 'ubuntu-latest'
+    permissions:
+      issues: 'write'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+          permission-issues: 'write'
+
+      - name: 'Process Stale Issues'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
+        env:
+          DRY_RUN: '${{ inputs.dry_run }}'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |
+            const dryRun = process.env.DRY_RUN === 'true';
+            if (dryRun) {
+              core.info('DRY RUN MODE ENABLED: No changes will be applied.');
+            }
+            const batchLabel = 'Stale';
+
+            const threeMonthsAgo = new Date();
+            threeMonthsAgo.setMonth(threeMonthsAgo.getMonth() - 3);
+
+            const tenDaysAgo = new Date();
+            tenDaysAgo.setDate(tenDaysAgo.getDate() - 10);
+
+            core.info(`Cutoff date for creation: ${threeMonthsAgo.toISOString()}`);
+            core.info(`Cutoff date for updates: ${tenDaysAgo.toISOString()}`);
+
+            const query = `repo:${context.repo.owner}/${context.repo.repo} is:issue is:open created:<${threeMonthsAgo.toISOString()}`;
+            core.info(`Searching with query: ${query}`);
+
+            const itemsToCheck = await github.paginate(github.rest.search.issuesAndPullRequests, {
+              q: query,
+              sort: 'created',
+              order: 'asc',
+              per_page: 100
+            });
+
+            core.info(`Found ${itemsToCheck.length} open issues to check.`);
+
+            let processedCount = 0;
+
+            for (const issue of itemsToCheck) {
+              const createdAt = new Date(issue.created_at);
+              const updatedAt = new Date(issue.updated_at);
+              const reactionCount = issue.reactions.total_count;
+
+              // Basic thresholds
+              if (reactionCount >= 5) {
+                continue;
+              }
+
+              // Skip if it has a maintainer, help wanted, or Public Roadmap label
+              const rawLabels = issue.labels.map((l) => l.name);
+              const lowercaseLabels = rawLabels.map((l) => l.toLowerCase());
+              if (
+                lowercaseLabels.some((l) => l.includes('maintainer')) ||
+                lowercaseLabels.includes('help wanted') ||
+                rawLabels.includes('🗓️ Public Roadmap')
+              ) {
+                continue;
+              }
+
+              let isStale = updatedAt < tenDaysAgo;
+
+              // If apparently active, check if it's only bot activity
+              if (!isStale) {
+                try {
+                  const comments = await github.rest.issues.listComments({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    per_page: 100,
+                    sort: 'created',
+                    direction: 'desc'
+                  });
+
+                  const lastHumanComment = comments.data.find(comment => comment.user.type !== 'Bot');
+                  if (lastHumanComment) {
+                    isStale = new Date(lastHumanComment.created_at) < tenDaysAgo;
+                  } else {
+                    // No human comments. Check if creator is human.
+                    if (issue.user.type !== 'Bot') {
+                       isStale = createdAt < tenDaysAgo;
+                    } else {
+                       isStale = true; // Bot created, only bot comments
+                    }
+                  }
+                } catch (error) {
+                  core.warning(`Failed to fetch comments for issue #${issue.number}: ${error.message}`);
+                  continue;
+                }
+              }
+
+              if (isStale) {
+                processedCount++;
+                const message = `Closing stale issue #${issue.number}: "${issue.title}" (${issue.html_url})`;
+                core.info(message);
+
+                if (!dryRun) {
+                  // Add label
+                  await github.rest.issues.addLabels({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    labels: [batchLabel]
+                  });
+
+                  // Add comment
+                  await github.rest.issues.createComment({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    body: 'Hello! As part of our effort to keep our backlog manageable and focus on the most active issues, we are tidying up older reports.\n\nIt looks like this issue hasn\'t been active for a while, so we are closing it for now. However, if you are still experiencing this bug on the latest stable build, please feel free to comment on this issue or create a new one with updated details.\n\nThank you for your contribution!'
+                  });
+
+                  // Close issue
+                  await github.rest.issues.update({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issue.number,
+                    state: 'closed',
+                    state_reason: 'not_planned'
+                  });
+                }
+              }
+            }
+
+            core.info(`\nTotal issues processed: ${processedCount}`);

.github/workflows/gemini-scheduled-stale-pr-closer.yml

@@ -0,0 +1,254 @@
+name: 'Gemini Scheduled Stale PR Closer'
+
+on:
+  schedule:
+    - cron: '0 2 * * *' # Every day at 2 AM UTC
+  pull_request:
+    types: ['opened', 'edited']
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: 'Run in dry-run mode'
+        required: false
+        default: false
+        type: 'boolean'
+
+jobs:
+  close-stale-prs:
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    runs-on: 'ubuntu-latest'
+    permissions:
+      pull-requests: 'write'
+      issues: 'write'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Process Stale PRs'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
+        env:
+          DRY_RUN: '${{ inputs.dry_run }}'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
+          script: |
+            const dryRun = process.env.DRY_RUN === 'true';
+            const fourteenDaysAgo = new Date();
+            fourteenDaysAgo.setDate(fourteenDaysAgo.getDate() - 14);
+            const thirtyDaysAgo = new Date();
+            thirtyDaysAgo.setDate(thirtyDaysAgo.getDate() - 30);
+
+            // 1. Fetch maintainers for verification
+            let maintainerLogins = new Set();
+            const teams = ['gemini-cli-maintainers', 'gemini-cli-askmode-approvers', 'gemini-cli-docs'];
+
+            for (const team_slug of teams) {
+              try {
+                const members = await github.paginate(github.rest.teams.listMembersInOrg, {
+                  org: context.repo.owner,
+                  team_slug: team_slug
+                });
+                for (const m of members) maintainerLogins.add(m.login.toLowerCase());
+                core.info(`Successfully fetched ${members.length} team members from ${team_slug}`);
+              } catch (e) {
+                // Silently skip if permissions are insufficient; we will rely on author_association
+                core.debug(`Skipped team fetch for ${team_slug}: ${e.message}`);
+              }
+            }
+
+            const isMaintainer = async (login, assoc) => {
+              // Reliably identify maintainers using authorAssociation (provided by GitHub)
+              // and organization membership (if available).
+              const isTeamMember = maintainerLogins.has(login.toLowerCase());
+              const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
+
+              if (isTeamMember || isRepoMaintainer) return true;
+
+              // Fallback: Check if user belongs to the 'google' or 'googlers' orgs (requires permission)
+              try {
+                const orgs = ['googlers', 'google'];
+                for (const org of orgs) {
+                  try {
+                    await github.rest.orgs.checkMembershipForUser({ org: org, username: login });
+                    return true;
+                  } catch (e) {
+                    if (e.status !== 404) throw e;
+                  }
+                }
+              } catch (e) {
+                // Gracefully ignore failures here
+              }
+
+              return false;
+            };
+
+            // 2. Fetch all open PRs
+            let prs = [];
+            if (context.eventName === 'pull_request') {
+              const { data: pr } = await github.rest.pulls.get({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                pull_number: context.payload.pull_request.number
+              });
+              prs = [pr];
+            } else {
+              prs = await github.paginate(github.rest.pulls.list, {
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                state: 'open',
+                per_page: 100
+              });
+            }
+
+            for (const pr of prs) {
+              const maintainerPr = await isMaintainer(pr.user.login, pr.author_association);
+              const isBot = pr.user.type === 'Bot' || pr.user.login.endsWith('[bot]');
+              if (maintainerPr || isBot) continue;
+
+              // Helper: Fetch labels and linked issues via GraphQL
+              const prDetailsQuery = `query($owner:String!, $repo:String!, $number:Int!) {
+                repository(owner:$owner, name:$repo) {
+                  pullRequest(number:$number) {
+                    closingIssuesReferences(first: 10) {
+                      nodes {
+                        number
+                        labels(first: 20) {
+                          nodes { name }
+                        }
+                      }
+                    }
+                  }
+                }
+              }`;
+
+              let linkedIssues = [];
+              try {
+                const res = await github.graphql(prDetailsQuery, {
+                  owner: context.repo.owner, repo: context.repo.repo, number: pr.number
+                });
+                linkedIssues = res.repository.pullRequest.closingIssuesReferences.nodes;
+              } catch (e) {
+                core.warning(`GraphQL fetch failed for PR #${pr.number}: ${e.message}`);
+              }
+
+              // Check for mentions in body as fallback (regex)
+              const body = pr.body || '';
+              const mentionRegex = /(?:#|https:\/\/github\.com\/[^\/]+\/[^\/]+\/issues\/)(\d+)/i;
+              const matches = body.match(mentionRegex);
+              if (matches && linkedIssues.length === 0) {
+                const issueNumber = parseInt(matches[1]);
+                try {
+                  const { data: issue } = await github.rest.issues.get({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issueNumber
+                  });
+                  linkedIssues = [{ number: issueNumber, labels: { nodes: issue.labels.map(l => ({ name: l.name })) } }];
+                } catch (e) {}
+              }
+
+              // 3. Enforcement Logic
+              const prLabels = pr.labels.map(l => l.name.toLowerCase());
+              const hasHelpWanted = prLabels.includes('help wanted') ||
+                                    linkedIssues.some(issue => issue.labels.nodes.some(l => l.name.toLowerCase() === 'help wanted'));
+
+              const hasMaintainerOnly = prLabels.includes('🔒 maintainer only') ||
+                                        linkedIssues.some(issue => issue.labels.nodes.some(l => l.name.toLowerCase() === '🔒 maintainer only'));
+
+              const hasLinkedIssue = linkedIssues.length > 0;
+
+              // Closure Policy: No help-wanted label = Close after 14 days
+              if (pr.state === 'open' && !hasHelpWanted && !hasMaintainerOnly) {
+                const prCreatedAt = new Date(pr.created_at);
+
+                // We give a 14-day grace period for non-help-wanted PRs to be manually reviewed/labeled by an EM
+                if (prCreatedAt > fourteenDaysAgo) {
+                  core.info(`PR #${pr.number} is new and lacks 'help wanted'. Giving 14-day grace period for EM review.`);
+                  continue;
+                }
+
+                core.info(`PR #${pr.number} is older than 14 days and lacks 'help wanted' association. Closing.`);
+                if (!dryRun) {
+                  await github.rest.issues.createComment({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: pr.number,
+                    body: "Hi there! Thank you for your interest in contributing to Gemini CLI. \n\nTo ensure we maintain high code quality and focus on our prioritized roadmap, we have updated our contribution policy (see [Discussion #17383](https://github.com/google-gemini/gemini-cli/discussions/17383)). \n\n**We only *guarantee* review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'.** All other community pull requests are subject to closure after 14 days if they do not align with our current focus areas. For this reason, we strongly recommend that contributors only submit pull requests against issues explicitly labeled as **'help-wanted'**. \n\nThis pull request is being closed as it has been open for 14 days without a 'help wanted' designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding and for being part of our community!"
+                  });
+                  await github.rest.pulls.update({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    pull_number: pr.number,
+                    state: 'closed'
+                  });
+                }
+                continue;
+              }
+
+              // Also check for linked issue even if it has help wanted (redundant but safe)
+              if (pr.state === 'open' && !hasLinkedIssue) {
+                 // Already covered by hasHelpWanted check above, but good for future-proofing
+                 continue;
+              }
+
+              // 4. Staleness Check (Scheduled only)
+              if (pr.state === 'open' && context.eventName !== 'pull_request') {
+                // Skip PRs that were created less than 30 days ago - they cannot be stale yet
+                const prCreatedAt = new Date(pr.created_at);
+                if (prCreatedAt > thirtyDaysAgo) continue;
+
+                let lastActivity = new Date(pr.created_at);
+                try {
+                  const reviews = await github.paginate(github.rest.pulls.listReviews, {
+                    owner: context.repo.owner, repo: context.repo.repo, pull_number: pr.number
+                  });
+                  for (const r of reviews) {
+                    if (await isMaintainer(r.user.login, r.author_association)) {
+                      const d = new Date(r.submitted_at || r.updated_at);
+                      if (d > lastActivity) lastActivity = d;
+                    }
+                  }
+                  const comments = await github.paginate(github.rest.issues.listComments, {
+                    owner: context.repo.owner, repo: context.repo.repo, issue_number: pr.number
+                  });
+                  for (const c of comments) {
+                    if (await isMaintainer(c.user.login, c.author_association)) {
+                      const d = new Date(c.updated_at);
+                      if (d > lastActivity) lastActivity = d;
+                    }
+                  }
+                } catch (e) {}
+
+                if (lastActivity < thirtyDaysAgo) {
+                  const labels = pr.labels.map(l => l.name.toLowerCase());
+                  const isProtected = labels.includes('help wanted') || labels.includes('🔒 maintainer only');
+                  if (isProtected) {
+                    core.info(`PR #${pr.number} is stale but has a protected label. Skipping closure.`);
+                    continue;
+                  }
+
+                  core.info(`PR #${pr.number} is stale (no maintainer activity for 30+ days). Closing.`);
+                  if (!dryRun) {
+                    await github.rest.issues.createComment({
+                      owner: context.repo.owner,
+                      repo: context.repo.repo,
+                      issue_number: pr.number,
+                      body: "Hi there! Thank you for your contribution. To keep our backlog manageable, we are closing pull requests that haven't seen maintainer activity for 30 days. If you're still working on this, please let us know!"
+                    });
+                    await github.rest.pulls.update({
+                      owner: context.repo.owner,
+                      repo: context.repo.repo,
+                      pull_number: pr.number,
+                      state: 'closed'
+                    });
+                  }
+                }
+              }
+            }

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

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

.github/workflows/links.yml

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

.github/workflows/memory-nightly.yml

@@ -1,35 +0,0 @@
-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
-        with:
-          persist-credentials: false
-
-      - 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/no-response.yml

@@ -0,0 +1,33 @@
+name: 'No Response'
+
+# Run as a daily cron at 1:45 AM
+on:
+  schedule:
+    - cron: '45 1 * * *'
+  workflow_dispatch:
+
+jobs:
+  no-response:
+    runs-on: 'ubuntu-latest'
+    if: |-
+      ${{ github.repository == 'google-gemini/gemini-cli' }}
+    permissions:
+      issues: 'write'
+      pull-requests: 'write'
+    concurrency:
+      group: '${{ github.workflow }}-no-response'
+      cancel-in-progress: true
+    steps:
+      - uses: 'actions/stale@5bef64f19d7facfb25b37b414482c7164d639639' # ratchet:actions/stale@v9
+        with:
+          repo-token: '${{ secrets.GITHUB_TOKEN }}'
+          days-before-stale: -1
+          days-before-close: 14
+          stale-issue-label: 'status/need-information'
+          close-issue-message: >-
+            This issue was marked as needing more information and has not received a response in 14 days.
+            Closing it for now. If you still face this problem, feel free to reopen with more details. Thank you!
+          stale-pr-label: 'status/need-information'
+          close-pr-message: >-
+            This pull request was marked as needing more information and has had no updates in 14 days.
+            Closing it for now. You are welcome to reopen with the required info. Thanks for contributing!

.github/workflows/perf-nightly.yml

@@ -1,35 +0,0 @@
-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
-        with:
-          persist-credentials: false
-
-      - 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'

.github/workflows/pr-contribution-guidelines-notifier.yml

@@ -0,0 +1,133 @@
+name: '🏷️ PR Contribution Guidelines Notifier'
+
+on:
+  pull_request:
+    types:
+      - 'opened'
+
+jobs:
+  notify-process-change:
+    runs-on: 'ubuntu-latest'
+    if: |-
+      github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli'
+    permissions:
+      pull-requests: 'write'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Check membership and post comment'
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
+          script: |-
+            const org = context.repo.owner;
+            const repo = context.repo.repo;
+            const username = context.payload.pull_request.user.login;
+            const pr_number = context.payload.pull_request.number;
+
+            // 1. Check if the PR author is a maintainer
+            // Check team membership (most reliable for private org members)
+            let isTeamMember = false;
+            const teams = ['gemini-cli-maintainers', 'gemini-cli-askmode-approvers', 'gemini-cli-docs'];
+            for (const team_slug of teams) {
+              try {
+                const members = await github.paginate(github.rest.teams.listMembersInOrg, {
+                  org: org,
+                  team_slug: team_slug
+                });
+                if (members.some(m => m.login.toLowerCase() === username.toLowerCase())) {
+                  isTeamMember = true;
+                  core.info(`${username} is a member of ${team_slug}. No notification needed.`);
+                  break;
+                }
+              } catch (e) {
+                core.warning(`Failed to fetch team members from ${team_slug}: ${e.message}`);
+              }
+            }
+
+            if (isTeamMember) return;
+
+            // Check author_association from webhook payload
+            const authorAssociation = context.payload.pull_request.author_association;
+            const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(authorAssociation);
+
+            if (isRepoMaintainer) {
+              core.info(`${username} is a maintainer (author_association: ${authorAssociation}). No notification needed.`);
+              return;
+            }
+
+            // Check if author is a Googler
+            const isGoogler = async (login) => {
+              try {
+                const orgs = ['googlers', 'google'];
+                for (const org of orgs) {
+                  try {
+                    await github.rest.orgs.checkMembershipForUser({
+                      org: org,
+                      username: login
+                    });
+                    return true;
+                  } catch (e) {
+                    if (e.status !== 404) throw e;
+                  }
+                }
+              } catch (e) {
+                core.warning(`Failed to check org membership for ${login}: ${e.message}`);
+              }
+              return false;
+            };
+
+            if (await isGoogler(username)) {
+              core.info(`${username} is a Googler. No notification needed.`);
+              return;
+            }
+
+            // 2. Check if the PR is already associated with an issue
+            const query = `
+              query($owner:String!, $repo:String!, $number:Int!) {
+                repository(owner:$owner, name:$repo) {
+                  pullRequest(number:$number) {
+                    closingIssuesReferences(first: 1) {
+                      totalCount
+                    }
+                  }
+                }
+              }
+            `;
+            const variables = { owner: org, repo: repo, number: pr_number };
+            const result = await github.graphql(query, variables);
+            const issueCount = result.repository.pullRequest.closingIssuesReferences.totalCount;
+
+            if (issueCount > 0) {
+              core.info(`PR #${pr_number} is already associated with an issue. No notification needed.`);
+              return;
+            }
+
+            // 3. Post the notification comment
+            core.info(`${username} is not a maintainer and PR #${pr_number} has no linked issue. Posting notification.`);
+
+            const comment = `
+            Hi @${username}, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this.
+
+            We're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: [Improving Our Contribution Process & Introducing New Guidelines](https://github.com/google-gemini/gemini-cli/discussions/16706).
+
+            Key Update: Starting **January 26, 2026**, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed.
+
+            Thank you for your understanding and for being a part of our community!
+            `.trim().replace(/^[ ]+/gm, '');
+
+            await github.rest.issues.createComment({
+              owner: org,
+              repo: repo,
+              issue_number: pr_number,
+              body: comment
+            });

.github/workflows/pr-size-labeler-batch-run.yml

@@ -1,107 +0,0 @@
-name: 'PR Size Labeler (Batch)'
-
-on:
-  workflow_dispatch:
-    inputs:
-      process_all:
-        description: 'Process all PRs (open and closed) or open only'
-        required: true
-        default: 'false'
-        type: 'choice'
-        options:
-          - 'true'
-          - 'false'
-      limit:
-        description: 'Max number of PRs to fetch and check'
-        required: true
-        default: '100'
-        type: 'string'
-
-permissions:
-  pull-requests: 'write'
-
-jobs:
-  batch-label:
-    runs-on: 'ubuntu-latest'
-    steps:
-      - name: 'Batch label PRs'
-        env:
-          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          GH_REPO: '${{ github.repository }}'
-        run: |
-          # Determine the state filter
-          STATE="open"
-          if [ "${{ github.event.inputs.process_all }}" = "true" ]; then
-            STATE="all"
-          fi
-
-          LIMIT="${{ github.event.inputs.limit }}"
-          echo "Batch labeling up to $LIMIT $STATE PRs..."
-
-          # 1. Ensure standard premium size labels exist in the repository (self-healing)
-          gh label create "size/XS" --color "7ee081" --description "XS: <10 lines changed" 2>/dev/null || true
-          gh label create "size/S"  --color "a6d49f" --description "S: 10-49 lines changed" 2>/dev/null || true
-          gh label create "size/M"  --color "f7d070" --description "M: 50-249 lines changed" 2>/dev/null || true
-          gh label create "size/L"  --color "f48c06" --description "L: 250-999 lines changed" 2>/dev/null || true
-          gh label create "size/XL" --color "dc2f02" --description "XL: >=1000 lines changed" 2>/dev/null || true
-
-          # 2. Query PR list with all required fields in ONE call to prevent N+1 queries
-          PR_LIST=$(gh pr list --state "$STATE" --limit "$LIMIT" --json number,additions,deletions,labels)
-          if [ -z "$PR_LIST" ] || [ "$PR_LIST" = "[]" ]; then
-            echo "ℹ️ No PRs found matching the criteria."
-            exit 0
-          fi
-
-          # Parse and iterate over PRs
-          UPDATED_COUNT=0
-          SKIPPED_COUNT=0
-
-          echo "$PR_LIST" | jq -c '.[]' | while read -r PR_JSON; do
-            PR_NUMBER=$(echo "$PR_JSON" | jq '.number')
-            ADDITIONS=$(echo "$PR_JSON" | jq '.additions')
-            DELETIONS=$(echo "$PR_JSON" | jq '.deletions')
-            TOTAL=$((ADDITIONS + DELETIONS))
-
-            # Calculate target size
-            if [ $TOTAL -lt 10 ]; then
-              SIZE="size/XS"
-            elif [ $TOTAL -lt 50 ]; then
-              SIZE="size/S"
-            elif [ $TOTAL -lt 250 ]; then
-              SIZE="size/M"
-            elif [ $TOTAL -lt 1000 ]; then
-              SIZE="size/L"
-            else
-              SIZE="size/XL"
-            fi
-
-            # Inspect existing labels to detect discrepancies
-            EXISTING_LABELS=$(echo "$PR_JSON" | jq -r '.labels[].name' 2>/dev/null || echo "")
-
-            LABELS_TO_REMOVE=()
-            for L in size/XS size/S size/M size/L size/XL; do
-              if echo "$EXISTING_LABELS" | grep -Fq "$L" && [ "$L" != "$SIZE" ]; then
-                LABELS_TO_REMOVE+=("--remove-label" "$L")
-              fi
-            done
-
-            LABEL_TO_ADD=()
-            if ! echo "$EXISTING_LABELS" | grep -Fq "$SIZE"; then
-              LABEL_TO_ADD+=("--add-label" "$SIZE")
-            fi
-
-            # Update labels if there's a difference
-            if [ ${#LABELS_TO_REMOVE[@]} -gt 0 ] || [ ${#LABEL_TO_ADD[@]} -gt 0 ]; then
-              echo "🔄 PR #$PR_NUMBER (+$ADDITIONS/-$DELETIONS = $TOTAL lines): updating size to $SIZE"
-              gh pr edit "$PR_NUMBER" "${LABELS_TO_REMOVE[@]}" "${LABEL_TO_ADD[@]}" 2>/dev/null || true
-              UPDATED_COUNT=$((UPDATED_COUNT + 1))
-            else
-              echo "✅ PR #$PR_NUMBER (+$ADDITIONS/-$DELETIONS = $TOTAL lines): already has correct label ($SIZE). Skipping."
-              SKIPPED_COUNT=$((SKIPPED_COUNT + 1))
-            fi
-          done
-
-          echo "============================================"
-          echo "🎉 Batch run completed!"
-          echo "Skipped (already correct): $SKIPPED_COUNT"
-          echo "Updated: $UPDATED_COUNT"

.github/workflows/pr-size-labeler.yml

@@ -1,120 +0,0 @@
-name: 'PR Size Labeler'
-
-on:
-  pull_request_target:
-    types: ['opened', 'synchronize', 'reopened']
-  workflow_dispatch:
-    inputs:
-      pr_number:
-        description: 'PR number to label manually (for workflow_dispatch)'
-        required: false
-        type: 'string'
-
-permissions:
-  pull-requests: 'write'
-  issues: 'write'
-
-jobs:
-  size-label:
-    runs-on: 'ubuntu-latest'
-    steps:
-      - name: 'Run size labeler'
-        env:
-          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
-          GH_REPO: '${{ github.repository }}'
-        run: |
-          # Determine the target PR number
-          if [ -n "${{ github.event.pull_request.number }}" ]; then
-            PR_NUMBER="${{ github.event.pull_request.number }}"
-          elif [ -n "${{ github.event.inputs.pr_number }}" ]; then
-            PR_NUMBER="${{ github.event.inputs.pr_number }}"
-          else
-            echo "❌ Error: No PR number provided."
-            exit 1
-          fi
-
-          echo "Checking PR #$PR_NUMBER..."
-
-          # 1. Ensure standard premium size labels exist in the repository (self-healing)
-          # size/XS: Light green (#7ee081)
-          # size/S: Yellow-green (#a6d49f)
-          # size/M: Amber/Yellow (#f7d070)
-          # size/L: Orange (#f48c06)
-          # size/XL: Red (#dc2f02)
-          gh label create "size/XS" --color "7ee081" --description "XS: <10 lines changed" 2>/dev/null || true
-          gh label create "size/S"  --color "a6d49f" --description "S: 10-49 lines changed" 2>/dev/null || true
-          gh label create "size/M"  --color "f7d070" --description "M: 50-249 lines changed" 2>/dev/null || true
-          gh label create "size/L"  --color "f48c06" --description "L: 250-999 lines changed" 2>/dev/null || true
-          gh label create "size/XL" --color "dc2f02" --description "XL: >=1000 lines changed" 2>/dev/null || true
-
-          # 2. Fetch PR details in a single efficient API call
-          PR_DATA=$(gh pr view "$PR_NUMBER" --json additions,deletions,changedFiles,labels)
-          if [ -z "$PR_DATA" ]; then
-            echo "❌ Error: Could not fetch PR details."
-            exit 1
-          fi
-
-          ADDITIONS=$(echo "$PR_DATA" | jq '.additions')
-          DELETIONS=$(echo "$PR_DATA" | jq '.deletions')
-          CHANGED_FILES=$(echo "$PR_DATA" | jq '.changedFiles')
-          TOTAL=$((ADDITIONS + DELETIONS))
-
-          echo "PR additions: $ADDITIONS, deletions: $DELETIONS, total changes: $TOTAL, files: $CHANGED_FILES"
-
-          # 3. Calculate new size label
-          if [ $TOTAL -lt 10 ]; then
-            SIZE="size/XS"
-          elif [ $TOTAL -lt 50 ]; then
-            SIZE="size/S"
-          elif [ $TOTAL -lt 250 ]; then
-            SIZE="size/M"
-          elif [ $TOTAL -lt 1000 ]; then
-            SIZE="size/L"
-          else
-            SIZE="size/XL"
-          fi
-
-          # 4. Check existing labels and update only if necessary
-          EXISTING_LABELS=$(echo "$PR_DATA" | jq -r '.labels[].name' 2>/dev/null || echo "")
-
-          LABELS_TO_REMOVE=()
-          for L in size/XS size/S size/M size/L size/XL; do
-            if echo "$EXISTING_LABELS" | grep -Fq "$L" && [ "$L" != "$SIZE" ]; then
-              LABELS_TO_REMOVE+=("--remove-label" "$L")
-            fi
-          done
-
-          LABEL_TO_ADD=()
-          if ! echo "$EXISTING_LABELS" | grep -Fq "$SIZE"; then
-            LABEL_TO_ADD+=("--add-label" "$SIZE")
-          fi
-
-          # Perform a single, highly atomic edit call if changes are needed
-          if [ ${#LABELS_TO_REMOVE[@]} -gt 0 ] || [ ${#LABEL_TO_ADD[@]} -gt 0 ]; then
-            echo "Updating labels: removing ${LABELS_TO_REMOVE[*]}, adding $SIZE"
-            gh pr edit "$PR_NUMBER" "${LABELS_TO_REMOVE[@]}" "${LABEL_TO_ADD[@]}"
-          else
-            echo "✅ PR #$PR_NUMBER already has the correct size label ($SIZE)."
-          fi
-
-          # 5. Premium, anti-spam comment logic (updates previous comment to keep thread clean)
-          COMMENT="📊 PR Size: **$SIZE**
-          - Lines changed: **$TOTAL**
-          - Additions: +$ADDITIONS
-          - Deletions: -$DELETIONS
-          - Files changed: $CHANGED_FILES"
-
-          # Find any existing size labeler comment by the github-actions bot
-          echo "Searching for existing size comment..."
-          COMMENT_ID=$(gh api "repos/${{ github.repository }}/issues/$PR_NUMBER/comments" \
-            --jq '.[] | select(.user.login == "github-actions[bot]" and (.body | startswith("📊 PR Size:"))) | .id' | head -n 1)
-
-          if [ -n "$COMMENT_ID" ]; then
-            echo "Updating existing comment (ID: $COMMENT_ID)..."
-            gh api "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -X PATCH -f body="$COMMENT" > /dev/null
-          else
-            echo "Creating new comment..."
-            gh pr comment "$PR_NUMBER" --body "$COMMENT" > /dev/null
-          fi
-
-          echo "🎉 PR size labeling completed successfully."

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

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

.github/workflows/release-manual.yml

@@ -46,15 +46,8 @@ on:
         default: 'prod'
 
 jobs:
-  build-mac:
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    uses: './.github/workflows/build-unsigned-mac-binaries.yml'
-    with:
-      ref: '${{ github.event.inputs.ref }}'
-
   release:
     if: "github.repository == 'google-gemini/gemini-cli'"
-    needs: ['build-mac']
     runs-on: 'ubuntu-latest'
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
@@ -65,13 +58,11 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Checkout Release Code'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
           path: 'release'
           fetch-depth: 0
@@ -92,11 +83,6 @@ jobs:
         working-directory: './release'
         run: 'npm ci'
 
-      - name: 'Download macOS Binaries'
-        uses: './.github/actions/download-mac-binaries'
-        with:
-          path: 'release/dist'
-
       - name: 'Prepare Release Info'
         id: 'release_info'
         working-directory: './release'

.github/workflows/release-nightly.yml

@@ -30,16 +30,9 @@ on:
         default: 'prod'
 
 jobs:
-  build-mac:
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    uses: './.github/workflows/build-unsigned-mac-binaries.yml'
-    with:
-      ref: '${{ github.event.inputs.ref }}'
-
   release:
     if: "github.repository == 'google-gemini/gemini-cli'"
-    needs: ['build-mac']
-    environment: "${{ github.event_name == 'schedule' && 'internal' || github.event.inputs.environment || 'prod' }}"
+    environment: "${{ github.event.inputs.environment || 'prod' }}"
     runs-on: 'ubuntu-latest'
     permissions:
       contents: 'write'
@@ -50,13 +43,11 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           fetch-depth: 0
 
       - name: 'Checkout Release Code'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
           path: 'release'
           fetch-depth: 0
@@ -71,11 +62,6 @@ jobs:
         working-directory: './release'
         run: 'npm ci'
 
-      - name: 'Download macOS Binaries'
-        uses: './.github/actions/download-mac-binaries'
-        with:
-          path: 'release/dist'
-
       - name: 'Print Inputs'
         shell: 'bash'
         env:
@@ -145,12 +131,12 @@ jobs:
           skip-branch-cleanup: true
           force-skip-tests: "${{ github.event_name != 'schedule' && github.event.inputs.force_skip_tests == 'true' }}"
           gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
-          npm-registry-publish-url: "${{ vars.NPM_REGISTRY_PUBLISH_URL || 'https://wombat-dressing-room.appspot.com' }}"
-          npm-registry-url: "${{ vars.NPM_REGISTRY_URL || 'https://wombat-dressing-room.appspot.com' }}"
-          npm-registry-scope: "${{ vars.NPM_REGISTRY_SCOPE || '@google' }}"
-          cli-package-name: "${{ vars.CLI_PACKAGE_NAME || '@google/gemini-cli' }}"
-          core-package-name: "${{ vars.CORE_PACKAGE_NAME || '@google/gemini-cli-core' }}"
-          a2a-package-name: "${{ vars.A2A_PACKAGE_NAME || '@google/gemini-cli-a2a-server' }}"
+          npm-registry-publish-url: '${{ vars.NPM_REGISTRY_PUBLISH_URL }}'
+          npm-registry-url: '${{ vars.NPM_REGISTRY_URL }}'
+          npm-registry-scope: '${{ vars.NPM_REGISTRY_SCOPE }}'
+          cli-package-name: '${{ vars.CLI_PACKAGE_NAME }}'
+          core-package-name: '${{ vars.CORE_PACKAGE_NAME }}'
+          a2a-package-name: '${{ vars.A2A_PACKAGE_NAME }}'
 
       - name: 'Create and Merge Pull Request'
         if: "github.event.inputs.environment != 'dev'"

.github/workflows/release-notes.yml

@@ -31,7 +31,6 @@ jobs:
       - name: 'Checkout repository'
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
         with:
-          persist-credentials: false
           # The user-level skills need to be available to the workflow
           fetch-depth: 0
           ref: 'main'
@@ -71,10 +70,7 @@ jobs:
       - name: 'Generate Changelog with Gemini'
         if: "steps.validate_version.outputs.CONTINUE == 'true'"
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
-        env:
-          GEMINI_CLI_TRUST_WORKSPACE: true
         with:
-          upload_artifacts: 'true'
           gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
           prompt: |
             Activate the 'docs-changelog' skill.

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

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

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

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

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

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

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

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

.github/workflows/release-promote.yml

@@ -55,7 +55,6 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           fetch-depth: 0
           fetch-tags: true
 
@@ -106,9 +105,7 @@ jobs:
           echo "NIGHTLY_JSON: ${NIGHTLY_JSON}"
           echo "STABLE_VERSION=${STABLE_VERSION}" >> "${GITHUB_OUTPUT}"
           # shellcheck disable=SC1083
-          PREVIOUS_PREVIEW_TAG=$(echo "${PREVIEW_JSON}" | jq -r .previousReleaseTag)
-          STABLE_SHA=$(git rev-parse "${PREVIOUS_PREVIEW_TAG}^{commit}")
-          echo "STABLE_SHA=${STABLE_SHA}" >> "${GITHUB_OUTPUT}"
+          echo "STABLE_SHA=$(git rev-parse "$(echo "${PREVIEW_JSON}" | jq -r .previousReleaseTag)"^{commit})" >> "${GITHUB_OUTPUT}"
           echo "PREVIOUS_STABLE_TAG=$(echo "${STABLE_JSON}" | jq -r .previousReleaseTag)" >> "${GITHUB_OUTPUT}"
           echo "PREVIEW_VERSION=$(echo "${PREVIEW_JSON}" | jq -r .releaseVersion)" >> "${GITHUB_OUTPUT}"
           # shellcheck disable=SC1083
@@ -174,13 +171,11 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Checkout correct SHA'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ matrix.sha }}'
           path: 'release'
           fetch-depth: 0
@@ -202,15 +197,9 @@ jobs:
           gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
           working-directory: './release'
 
-  build-mac:
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    uses: './.github/workflows/build-unsigned-mac-binaries.yml'
-    with:
-      ref: '${{ github.event.inputs.ref }}'
-
   publish-preview:
     name: 'Publish preview'
-    needs: ['calculate-versions', 'test', 'build-mac']
+    needs: ['calculate-versions', 'test']
     runs-on: 'ubuntu-latest'
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
@@ -221,13 +210,11 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Checkout correct SHA'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ needs.calculate-versions.outputs.PREVIEW_SHA }}'
           path: 'release'
           fetch-depth: 0
@@ -242,11 +229,6 @@ jobs:
         working-directory: './release'
         run: 'npm ci'
 
-      - name: 'Download macOS Binaries'
-        uses: './.github/actions/download-mac-binaries'
-        with:
-          path: 'release/dist'
-
       - name: 'Publish Release'
         uses: './.github/actions/publish-release'
         with:
@@ -284,7 +266,7 @@ jobs:
 
   publish-stable:
     name: 'Publish stable'
-    needs: ['calculate-versions', 'test', 'publish-preview', 'build-mac']
+    needs: ['calculate-versions', 'test', 'publish-preview']
     runs-on: 'ubuntu-latest'
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
@@ -295,13 +277,11 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Checkout correct SHA'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ needs.calculate-versions.outputs.STABLE_SHA }}'
           path: 'release'
           fetch-depth: 0
@@ -316,11 +296,6 @@ jobs:
         working-directory: './release'
         run: 'npm ci'
 
-      - name: 'Download macOS Binaries'
-        uses: './.github/actions/download-mac-binaries'
-        with:
-          path: 'release/dist'
-
       - name: 'Publish Release'
         uses: './.github/actions/publish-release'
         with:
@@ -369,7 +344,6 @@ jobs:
       - name: 'Checkout Ref'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
 
       - name: 'Setup Node.js'
@@ -405,7 +379,6 @@ jobs:
           BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
           DRY_RUN: '${{ github.event.inputs.dry_run }}'
           NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
-          GIT_PUSH_TOKEN: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
         run: |-
           git add package.json packages/*/package.json
           if [ -f package-lock.json ]; then
@@ -414,7 +387,7 @@ jobs:
           git commit -m "chore(release): bump version to ${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"
           if [[ "${DRY_RUN}" == "false" ]]; then
             echo "Pushing release branch to remote..."
-            git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
+            git push --set-upstream origin "${BRANCH_NAME}"
           else
             echo "Dry run enabled. Skipping push."
           fi

.github/workflows/release-rollback.yml

@@ -52,7 +52,6 @@ jobs:
       - name: 'Checkout repository'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
         with:
-          persist-credentials: false
           ref: '${{ github.event.inputs.ref }}'
           fetch-depth: 0
 
@@ -82,8 +81,7 @@ jobs:
           ORIGIN_TAG: '${{ steps.origin_tag.outputs.ORIGIN_TAG }}'
         shell: 'bash'
         run: |
-          ORIGIN_HASH=$(git rev-parse "${ORIGIN_TAG}")
-          echo "ORIGIN_HASH=${ORIGIN_HASH}" >> "$GITHUB_OUTPUT"
+          echo "ORIGIN_HASH=$(git rev-parse "${ORIGIN_TAG}")" >> "$GITHUB_OUTPUT"
 
       - name: 'Change tag'
         if: "${{ github.event.inputs.rollback_destination != '' }}"
@@ -194,7 +192,7 @@ jobs:
         run: |
           echo "ROLLBACK_TAG=$ROLLBACK_TAG_NAME" >> "$GITHUB_OUTPUT"
           git tag "$ROLLBACK_TAG_NAME" "${ORIGIN_HASH}"
-          git push "https://x-access-token:${GITHUB_TOKEN}@github.com/${{ github.repository }}.git" --tags
+          git push origin --tags
 
       - name: 'Verify Rollback Tag Added'
         if: "${{ github.event.inputs.dry-run == 'false' }}"

.github/workflows/release-sandbox.yml

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

.github/workflows/smoke-test.yml

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

.github/workflows/stale.yml

@@ -0,0 +1,44 @@
+name: 'Mark stale issues and pull requests'
+
+# Run as a daily cron at 1:30 AM
+on:
+  schedule:
+    - cron: '30 1 * * *'
+  workflow_dispatch:
+
+jobs:
+  stale:
+    strategy:
+      fail-fast: false
+      matrix:
+        runner:
+          - 'ubuntu-latest' # GitHub-hosted
+    runs-on: '${{ matrix.runner }}'
+    if: |-
+      ${{ github.repository == 'google-gemini/gemini-cli' }}
+    permissions:
+      issues: 'write'
+      pull-requests: 'write'
+    concurrency:
+      group: '${{ github.workflow }}-stale'
+      cancel-in-progress: true
+    steps:
+      - uses: 'actions/stale@5bef64f19d7facfb25b37b414482c7164d639639' # ratchet:actions/stale@v9
+        with:
+          repo-token: '${{ secrets.GITHUB_TOKEN }}'
+          stale-issue-message: >-
+            This issue has been automatically marked as stale due to 60 days of inactivity.
+            It will be closed in 14 days if no further activity occurs.
+          stale-pr-message: >-
+            This pull request has been automatically marked as stale due to 60 days of inactivity.
+            It will be closed in 14 days if no further activity occurs.
+          close-issue-message: >-
+            This issue has been closed due to 14 additional days of inactivity after being marked as stale.
+            If you believe this is still relevant, feel free to comment or reopen the issue. Thank you!
+          close-pr-message: >-
+            This pull request has been closed due to 14 additional days of inactivity after being marked as stale.
+            If this is still relevant, you are welcome to reopen or leave a comment. Thanks for contributing!
+          days-before-stale: 60
+          days-before-close: 14
+          exempt-issue-labels: 'pinned,security,🔒 maintainer only,help wanted,🗓️ Public Roadmap'
+          exempt-pr-labels: 'pinned,security,🔒 maintainer only,help wanted,🗓️ Public Roadmap'

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

@@ -34,8 +34,6 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
-        with:
-          persist-credentials: false
 
       - name: 'Optimize Windows Performance'
         if: "matrix.os == 'windows-latest'"
@@ -143,7 +141,6 @@ jobs:
         if: "github.event_name != 'pull_request'"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          GEMINI_CLI_TRUST_WORKSPACE: true
         run: |
           echo "Running integration tests with binary..."
           if [[ "${{ matrix.os }}" == 'windows-latest' ]]; then

.github/workflows/tools-python-ci.yml

@@ -1,45 +0,0 @@
-name: 'Testing: Tools (Python)'
-
-on:
-  push:
-    branches:
-      - 'main'
-      - 'release/**'
-    paths:
-      - 'tools/**'
-  pull_request:
-    branches:
-      - 'main'
-      - 'release/**'
-    paths:
-      - 'tools/**'
-
-defaults:
-  run:
-    shell: 'bash'
-
-jobs:
-  python-tests:
-    name: 'Python Tests'
-    runs-on: 'ubuntu-latest'
-    steps:
-      - name: 'Checkout'
-        uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
-
-      - name: 'Set up Python'
-        uses: 'actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55' # ratchet:actions/setup-python@v5
-        with:
-          python-version: '3.13'
-          cache: 'pip'
-          cache-dependency-path: 'tools/caretaker-agent/cloudrun/triage-worker/requirements.txt'
-
-      - name: 'Install dependencies'
-        run: |
-          python -m pip install --upgrade pip
-          if [ -f tools/caretaker-agent/cloudrun/triage-worker/requirements.txt ]; then
-            python -m pip install -r tools/caretaker-agent/cloudrun/triage-worker/requirements.txt
-          fi
-
-      - name: 'Run unittest suite'
-        run: |
-          PYTHONPATH=tools/caretaker-agent/cloudrun/triage-worker python -m unittest discover -s tools/caretaker-agent/cloudrun/triage-worker/tests -t tools/caretaker-agent/cloudrun/triage-worker

.github/workflows/verify-release.yml

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

.gitignore

@@ -48,7 +48,6 @@ 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*/
 
@@ -65,6 +64,3 @@ gemini-debug.log
 evals/logs/
 
 temp_agents/
-
-# conductor extension and planning directories
-conductor/

.prettierignore

@@ -22,5 +22,3 @@ Thumbs.db
 .pytest_cache
 **/SKILL.md
 packages/sdk/test-data/*.json
-*.mdx
-packages/vscode-ide-companion/NOTICES.txt

.vscode/launch.json

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

CONTRIBUTING.md

@@ -110,9 +110,7 @@ assign or unassign the issue as requested, provided the conditions are met
 (e.g., an issue must be unassigned to be assigned).
 
 Please note that you can have a maximum of 3 issues assigned to you at any given
-time and that only
-[issues labeled "help wanted"](https://github.com/google-gemini/gemini-cli/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22help%20wanted%22)
-may be self-assigned.
+time.
 
 ### Pull request guidelines
 
@@ -421,9 +419,9 @@ To debug the CLI's React-based UI, you can use React DevTools.
 
 On macOS, `gemini` uses Seatbelt (`sandbox-exec`) under a `permissive-open`
 profile (see `packages/cli/src/utils/sandbox-macos-permissive-open.sb`) that
-denies operations by default, confining writes to the project folder while
-allowing broad file reads and outbound network traffic ("open") by default. You
-can switch to a `strict-open` profile (see
+restricts writes to the project folder but otherwise allows all other operations
+and outbound network traffic ("open") by default. You can switch to a
+`strict-open` profile (see
 `packages/cli/src/utils/sandbox-macos-strict-open.sb`) that restricts both reads
 and writes to the working directory while allowing outbound network traffic by
 setting `SEATBELT_PROFILE=strict-open` in your environment or `.env` file.

Dockerfile

@@ -1,44 +1,3 @@
-# ---- Stage 1: Builder ----
-FROM docker.io/library/node:20-slim AS builder
-
-# Install git (needed by generate-git-commit-info.js script)
-RUN apt-get update && apt-get install -y --no-install-recommends git \
-  && apt-get clean && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /build
-
-# Copy only package.json files first for better layer caching
-# Dependencies only re-install when package files change, not source files
-COPY package*.json ./
-COPY packages/cli/package*.json ./packages/cli/
-COPY packages/core/package*.json ./packages/core/
-COPY packages/vscode-ide-companion/package*.json ./packages/vscode-ide-companion/
-COPY packages/vscode-ide-companion/scripts/ ./packages/vscode-ide-companion/scripts/
-COPY packages/devtools/package*.json ./packages/devtools/
-COPY packages/sdk/package*.json ./packages/sdk/
-COPY packages/test-utils/package*.json ./packages/test-utils/
-COPY packages/a2a-server/package*.json ./packages/a2a-server/
-
-# Use npm ci for consistent, reliable builds (respects package-lock.json)
-RUN HUSKY=0 npm ci --ignore-scripts
-
-# Now copy the rest of the source (after install for better caching)
-COPY packages/ ./packages/
-COPY tsconfig*.json ./
-COPY eslint.config.js ./
-COPY scripts/ ./scripts/
-COPY esbuild.config.js ./
-
-# Pass git commit hash as build arg instead of copying entire .git directory
-ARG GIT_COMMIT=unknown
-ENV GIT_COMMIT=$GIT_COMMIT
-
-# Build and pack artifacts
-RUN HUSKY=0 npm run build && \
-    npm pack -w packages/core --pack-destination packages/core/dist/ && \
-    npm pack -w packages/cli --pack-destination packages/cli/dist/
-
-# ---- Stage 2: Runtime ----
 FROM docker.io/library/node:20-slim
 
 ARG SANDBOX_NAME="gemini-cli-sandbox"
@@ -81,8 +40,8 @@ ENV PATH=$PATH:/usr/local/share/npm-global/bin
 USER node
 
 # install gemini-cli and clean up
-COPY --chown=node:node packages/cli/dist/google-gemini-cli-*.tgz /tmp/gemini-cli.tgz
-COPY --chown=node:node packages/core/dist/google-gemini-cli-core-*.tgz /tmp/gemini-core.tgz
+COPY packages/cli/dist/google-gemini-cli-*.tgz /tmp/gemini-cli.tgz
+COPY packages/core/dist/google-gemini-cli-core-*.tgz /tmp/gemini-core.tgz
 RUN npm install -g /tmp/gemini-core.tgz \
   && npm install -g /tmp/gemini-cli.tgz \
   && node -e "const fs=require('node:fs'); JSON.parse(fs.readFileSync('/usr/local/share/npm-global/lib/node_modules/@google/gemini-cli/package.json','utf8')); JSON.parse(fs.readFileSync('/usr/local/share/npm-global/lib/node_modules/@google/gemini-cli-core/package.json','utf8'));" \
@@ -91,4 +50,4 @@ RUN npm install -g /tmp/gemini-core.tgz \
   && rm -f /tmp/gemini-{cli,core}.tgz
 
 # default entrypoint when none specified
-ENTRYPOINT ["/usr/local/share/npm-global/bin/gemini"]
+CMD ["gemini"]

GEMINI.md

@@ -44,13 +44,6 @@ 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`)

README.md

@@ -371,8 +371,6 @@ for planned features and priorities.
 
 ## 📖 Resources
 
-- **[Free Course](https://learn.deeplearning.ai/courses/gemini-cli-code-and-create-with-an-open-source-agent/information)** -
-  Learn the basics.
 - **[Official Roadmap](./ROADMAP.md)** - See what's coming next.
 - **[Changelog](https://www.geminicli.com/docs/changelogs)** - See recent
   notable updates.
@@ -395,16 +393,6 @@ for removal instructions.
   [Terms & Privacy](https://www.geminicli.com/docs/resources/tos-privacy)
 - **Security**: [Security Policy](SECURITY.md)
 
-<p align="left">
- <a href="https://www.star-history.com/google-gemini/gemini-cli">
-  <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/badge?repo=google-gemini/gemini-cli&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/badge?repo=google-gemini/gemini-cli" />
-   <img alt="Star History Rank" src="https://api.star-history.com/badge?repo=google-gemini/gemini-cli" />
-  </picture>
- </a>
-</p>
-
 ---
 
 <p align="center">

docs/adk-replat/NOTES-adk-alignment.md

@@ -0,0 +1,529 @@
+# ADK-TS Alignment Pass
+
+Every interface in our outline must map cleanly to ADK-TS. This document
+verifies that mapping field-by-field, identifies gaps, and confirms
+HITL/plugin/transfer patterns work.
+
+Source: ADK-TS v0.4.0 at `/Users/adamfweidman/Desktop/adk-int/adk-js/core/src/`
+
+---
+
+## 1. AgentDescriptor ↔ ADK Agent Hierarchy
+
+### Field-by-field mapping
+
+| AgentDescriptor field        | ADK-TS source                                | Notes                                                                                                                                                    |
+| ---------------------------- | -------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `name`                       | `BaseAgent.name`                             | Direct. ADK validates it's a valid JS identifier.                                                                                                        |
+| `displayName`                | —                                            | ADK doesn't have this. No conflict.                                                                                                                      |
+| `description`                | `BaseAgent.description` (optional in ADK)    | Direct. Used for model routing in AgentTool.                                                                                                             |
+| `executor`                   | —                                            | New concept. ADK agents are always 'adk'. Adapter sets this.                                                                                             |
+| `inputSchema`                | `LlmAgent.inputSchema` (Zod or JSON Schema)  | Direct. ADK's AgentTool uses this for tool parameter generation.                                                                                         |
+| `outputSchema`               | `LlmAgent.outputSchema` (Zod or JSON Schema) | Direct. ADK uses for structured output + AgentTool response.                                                                                             |
+| `capabilities`               | —                                            | New concept. Adapter infers from agent type: LlmAgent gets `['elicitation', 'streaming', 'host_tool_execution']`, LoopAgent gets `['composition']`, etc. |
+| `ownTools`                   | `LlmAgent.tools: ToolUnion[]`                | Maps via ToolDescriptor adapter. ADK tools have `name`, `description`, `_getDeclaration()` which returns JSON Schema.                                    |
+| `requiredTools`              | —                                            | New concept. ADK agents don't declare required host tools. Adapter can infer from tool references.                                                       |
+| `subAgents`                  | `BaseAgent.subAgents: BaseAgent[]`           | Recursive. Each sub-agent becomes a nested AgentDescriptor.                                                                                              |
+| `constraints.maxTurns`       | `RunConfig.maxLlmCalls` (default 500)        | Maps, though semantics differ slightly (LLM calls vs turns).                                                                                             |
+| `constraints.maxTimeMinutes` | —                                            | ADK doesn't have time limits. No conflict — host enforces.                                                                                               |
+| `constraints.maxBudgetUsd`   | —                                            | ADK doesn't have budget. No conflict — host enforces.                                                                                                    |
+| `metadata`                   | —                                            | New concept. Adapter can populate from agent registration context.                                                                                       |
+
+### ADK-specific fields NOT in AgentDescriptor
+
+| ADK field                           | Where it lives | Our approach                                                                                               |
+| ----------------------------------- | -------------- | ---------------------------------------------------------------------------------------------------------- |
+| `instruction` / `globalInstruction` | LlmAgent       | Executor-internal. Not in descriptor (it's runtime config, not identity).                                  |
+| `model`                             | LlmAgent       | Goes in ExecutionOptions.model or executor-internal config.                                                |
+| `generateContentConfig`             | LlmAgent       | Executor-internal.                                                                                         |
+| `disallowTransferToParent/Peers`    | LlmAgent       | Could be `constraints` or `_meta`. Transfer policy is host-enforced.                                       |
+| `includeContents`                   | LlmAgent       | Executor-internal (context management).                                                                    |
+| `outputKey`                         | LlmAgent       | Executor-internal (state management).                                                                      |
+| `beforeModelCallback`, etc.         | LlmAgent       | Executor-internal. These are ADK's callback system — our LifecycleInterceptor is the interface equivalent. |
+
+### Verdict: CLEAN MAPPING
+
+AgentDescriptor captures everything needed to describe an ADK agent externally.
+ADK-specific runtime config (instruction, model, callbacks) stays inside the
+executor — exactly right for the descriptor/executor separation.
+
+**Key ADK pattern preserved:** AgentTool wraps an agent as a tool using
+`inputSchema` for parameters and `description` for the tool description. Our
+AgentDescriptor has both, so SubagentTool can do the same thing.
+
+---
+
+## 2. AgentSession ↔ ADK Runner
+
+### Method mapping
+
+| AgentSession method     | ADK-TS equivalent                                               | How adapter works                                                                                                                                                   |
+| ----------------------- | --------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `stream(data, options)` | `Runner.runAsync({ userId, sessionId, newMessage, runConfig })` | Adapter creates/loads session, maps data+options → runAsync params, wraps Event generator → AgentEvent generator. Each `stream()` call triggers a new `runAsync()`. |
+| `update(config)`        | No direct equivalent                                            | ADK doesn't support mid-stream config changes. Adapter queues updates for next `runAsync()` call.                                                                   |
+| `steer(data)`           | No direct equivalent                                            | ADK doesn't support mid-stream intervention. Adapter can queue for next invocation or ignore.                                                                       |
+| `abort()`               | No direct equivalent                                            | ADK uses `invocationContext.endInvocation = true`. Adapter sets this flag. Could also use AbortController.                                                          |
+
+### ExecutionRequest → Runner.runAsync mapping
+
+| ExecutionRequest field      | ADK mapping                                                      |
+| --------------------------- | ---------------------------------------------------------------- |
+| `descriptor`                | Used to find/create the BaseAgent instance                       |
+| `input`                     | → `newMessage: Content` (converted from ContentPart[] → Content) |
+| `sessionRef`                | → `sessionId` (string) or creates session from SessionSnapshot   |
+| `forkSession`               | Adapter clones session before running                            |
+| `options.tools`             | → merged into agent's `tools` config                             |
+| `options.model`             | → `LlmAgent.model` override                                      |
+| `options.hostToolExecution` | → `RunConfig.pauseOnToolCalls: true`                             |
+| `options.streaming`         | → `RunConfig.streamingMode`                                      |
+| `options.permissionMode`    | → SecurityPlugin config                                          |
+| `signal`                    | → wired to `invocationContext.endInvocation`                     |
+
+### HITL: How pauseOnToolCalls works end-to-end
+
+This is the critical path. Here's the full flow:
+
+```
+1. LLM returns tool call (FunctionCall in Event)
+2. ADK checks RunConfig.pauseOnToolCalls === true
+3. ADK sets invocationContext.endInvocation = true
+4. ADK yields the Event (with FunctionCall) and stops
+5. Runner.runAsync() generator completes
+
+   --- OUR INTERFACE BOUNDARY ---
+
+6. Adapter translates ADK Event → ToolRequestEvent
+7. Host receives ToolRequestEvent from session.stream() generator
+8. Host runs policy check (PolicyEvaluator.evaluate())
+9. Host fires hooks (LifecycleInterceptor.fire('before_tool', ...))
+10. If policy allows → Host executes tool → gets ToolResultData
+11. Host calls session.stream({ kind: 'tool_result', ... }) to get next stream
+
+   --- BACK INTO ADK ---
+
+12. Adapter receives tool result
+13. Adapter creates FunctionResponse Content
+14. Adapter calls Runner.runAsync() again with FunctionResponse as newMessage
+15. ADK loads session (has prior tool call event)
+16. ADK resumes agent with tool response
+17. Loop continues from step 1
+```
+
+**Why this works:** ADK's `pauseOnToolCalls` was designed exactly for this
+pattern — external tool execution by a host. The adapter translates between
+ADK's "end invocation + resume with FunctionResponse" pattern and our
+"ToolRequestEvent + send(tool_result)" pattern.
+
+**Key insight:** Each `session.stream()` call triggers a new `Runner.runAsync()`
+call. This means each ADK "invocation" maps to one `stream()` call. The session
+persists state across invocations. Mid-stream `update()` and `steer()` calls are
+queued for the next invocation since ADK doesn't support mid-turn changes.
+
+### HITL: ToolConfirmation flow
+
+ADK also has a separate ToolConfirmation pattern (via
+`context.requestConfirmation()`):
+
+```
+1. beforeToolCallback calls context.requestConfirmation({ hint: '...' })
+2. This sets eventActions.requestedToolConfirmations[functionCallId]
+3. ADK yields event with requestedToolConfirmations populated
+4. Runner completes (invocation ends)
+
+   --- OUR INTERFACE BOUNDARY ---
+
+5. Adapter sees requestedToolConfirmations in event
+6. Adapter translates → ElicitationRequest { kind: 'tool_confirmation', ... }
+7. Host renders confirmation UI
+8. User responds → ElicitationResponse { action: 'accept' | 'decline' }
+
+   --- BACK INTO ADK ---
+
+9. Adapter receives elicitation response
+10. If accepted: Adapter creates FunctionResponse with confirmed=true
+11. Calls Runner.runAsync() with FunctionResponse
+12. ADK's SecurityPlugin or callback reads confirmation from session
+13. Tool executes
+```
+
+**Maps to our ElicitationRequest:** ADK's `ToolConfirmation.hint` →
+`ElicitationRequest.message`. ADK's `ToolConfirmation.payload` →
+`ElicitationRequest.context`. The `kind: 'tool_confirmation'` is the
+discriminator.
+
+### HITL: Auth request flow
+
+```
+1. Tool or callback calls context.requestCredential(authConfig)
+2. Sets eventActions.requestedAuthConfigs[functionCallId]
+3. Event yields, invocation ends
+
+   --- OUR INTERFACE BOUNDARY ---
+
+4. Adapter sees requestedAuthConfigs
+5. Translates → ElicitationRequest { kind: 'auth_required', context: authConfig }
+6. User provides credentials
+7. ElicitationResponse { action: 'accept', content: { credential: ... } }
+
+   --- BACK INTO ADK ---
+
+8. Adapter stores credential via CredentialService
+9. Calls Runner.runAsync() again
+10. Tool calls context.getAuthResponse() → gets credential
+```
+
+**Maps to our ElicitationRequest:** ADK's auth pattern is just another
+elicitation kind. This validates our generic elicitation design — it handles
+tool confirmation, auth, and any future interaction type.
+
+---
+
+## 3. AgentEvent ↔ ADK Event
+
+### Event type mapping
+
+| Our AgentEvent        | ADK Event pattern                                                                 | Adapter translation                           |
+| --------------------- | --------------------------------------------------------------------------------- | --------------------------------------------- |
+| `InitializeEvent`     | First event from Runner.runAsync()                                                | Adapter emits on first stream() call          |
+| `SessionUpdateEvent`  | `eventActions.stateDelta`                                                         | Adapter emits when stateDelta is non-empty    |
+| `MessageEvent`        | `event.content` with text Parts                                                   | Filter text/thought parts from Content        |
+| `ToolRequestEvent`    | `getFunctionCalls(event)` returns FunctionCall[]                                  | Each FunctionCall → one ToolRequestEvent      |
+| `ToolUpdateEvent`     | `event.longRunningToolIds`                                                        | Adapter emits progress for long-running tools |
+| `ToolResponseEvent`   | `getFunctionResponses(event)` returns FunctionResponse[]                          | Each FunctionResponse → one ToolResponseEvent |
+| `ElicitationRequest`  | `eventActions.requestedToolConfirmations` or `requestedAuthConfigs`               | Map to generic elicitation                    |
+| `ElicitationResponse` | User input → FunctionResponse in next runAsync call                               | Reverse of above                              |
+| `UsageEvent`          | `event.usageMetadata` (GenerateContentResponseUsageMetadata)                      | Map token counts                              |
+| `ErrorEvent`          | `event.errorCode` + `event.errorMessage`                                          | Map error fields                              |
+| `stream_end`          | `isFinalResponse(event)`, `eventActions.transferToAgent`, `eventActions.escalate` | Derive `stream_end` reason from ADK signals   |
+| `CustomEvent`         | `event.customMetadata`                                                            | Pass through                                  |
+
+### ADK EventActions → Our events
+
+| EventActions field           | Our event                                                                 | Notes                                                                                                        |
+| ---------------------------- | ------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
+| `stateDelta`                 | SessionUpdate or embedded in other events                                 | Delta state is a core ADK pattern                                                                            |
+| `artifactDelta`              | `CustomEvent { kind: 'artifact_delta' }`                                  | Artifacts not in our core events                                                                             |
+| `transferToAgent`            | Tool call (`transfer_to_agent`) + `stream_end` `reason: 'completed'`      | Handoff is a tool call. Host intercepts the tool request, mediates the handoff, originating agent completes. |
+| `escalate`                   | `stream_end` `reason: 'completed'` with `data: { escalateReason: '...' }` | LoopAgent exit signal. ADK's escalate = "I'm done, pass control back up"                                     |
+| `requestedToolConfirmations` | `ElicitationRequest { kind: 'tool_confirmation' }`                        | Per function call ID                                                                                         |
+| `requestedAuthConfigs`       | `ElicitationRequest { kind: 'auth_required' }`                            | Per function call ID                                                                                         |
+| `skipSummarization`          | `_meta: { skipSummarization: true }`                                      | ADK-specific, goes in metadata                                                                               |
+
+### AgentEventBase mapping
+
+| AgentEventBase field | ADK Event field                          | Notes                                             |
+| -------------------- | ---------------------------------------- | ------------------------------------------------- |
+| `id`                 | `event.id`                               | Direct                                            |
+| `timestamp`          | `event.timestamp` (number)               | Convert to ISO 8601 string                        |
+| `type`               | Derived from content analysis            | ADK doesn't have event types — adapter classifies |
+| `agentId`            | `event.author` (agent name) or context   | **New field** — which agent emitted this event    |
+| `threadId`           | `event.branch` (e.g., "agent_1.agent_2") | Direct mapping                                    |
+| `source`             | `event.author` ("user" or agent name)    | Direct                                            |
+| `_meta`              | `event.customMetadata`                   | Direct                                            |
+
+### Verdict: CLEAN MAPPING
+
+Every ADK event pattern maps to our event types. The adapter classifies ADK's
+untyped events into our typed event taxonomy. Key insight: ADK events are richer
+(they carry EventActions, function calls, auth requests all in one event), so
+the adapter may fan out one ADK Event into multiple AgentEvents (e.g., one
+Message + one ToolRequest + one ElicitationRequest). The new `agentId` field
+maps directly from ADK's `event.author`.
+
+---
+
+## 4. ToolContract ↔ ADK Tool System
+
+### ToolDescriptor ↔ BaseTool
+
+| ToolDescriptor field      | ADK source                                                    | Notes                             |
+| ------------------------- | ------------------------------------------------------------- | --------------------------------- |
+| `name`                    | `BaseTool.name`                                               | Direct                            |
+| `displayName`             | —                                                             | ADK doesn't have this             |
+| `description`             | `BaseTool.description`                                        | Direct                            |
+| `parametersSchema`        | `BaseTool._getDeclaration()` → FunctionDeclaration.parameters | JSON Schema from declaration      |
+| `annotations.readOnly`    | Inferred from tool type                                       | FunctionTool with no side effects |
+| `annotations.longRunning` | `BaseTool.isLongRunning`                                      | Direct                            |
+
+### ToolCallRequest ↔ FunctionCall
+
+| ToolCallRequest | ADK FunctionCall    | Notes  |
+| --------------- | ------------------- | ------ |
+| `requestId`     | `functionCall.id`   | Direct |
+| `name`          | `functionCall.name` | Direct |
+| `args`          | `functionCall.args` | Direct |
+
+### ToolResultData ↔ FunctionResponse + tool return
+
+| ToolResultData   | ADK                            | Notes                                            |
+| ---------------- | ------------------------------ | ------------------------------------------------ |
+| `llmContent`     | `FunctionResponse.response`    | Adapter wraps into ContentPart[]                 |
+| `displayContent` | —                              | ADK doesn't separate display from model content  |
+| `isError`        | Error thrown from `runAsync()` | Adapter catches and sets flag                    |
+| `tailCalls`      | —                              | ADK doesn't have tail calls (gemini-cli concept) |
+
+### AgentTool pattern
+
+ADK's `AgentTool` wraps a `BaseAgent` as a `BaseTool`:
+
+- Uses `agent.inputSchema` for tool parameters
+- Uses `agent.description` for tool description
+- Creates internal Runner with isolated session
+- Returns agent output as tool result
+- Merges state deltas back to parent
+
+**Our equivalent:** `SubagentTool` wraps `AgentDescriptor` as a tool:
+
+- Uses `descriptor.inputSchema` for tool parameters
+- Uses `descriptor.description` for tool description
+- Creates executor via `SessionFactory.create(descriptor, context)`
+- Returns execution result as tool result
+
+**Mapping is 1:1.** The only difference is ADK does it with concrete agent
+instances; we do it with descriptors + factory.
+
+---
+
+## 5. LifecycleInterceptor ↔ ADK Plugin System
+
+### Hook point mapping
+
+| Our hook point string | ADK Plugin callback     | Mapping                                    |
+| --------------------- | ----------------------- | ------------------------------------------ |
+| `'before_agent'`      | `beforeAgentCallback`   | `payload: { agent, context }`              |
+| `'after_agent'`       | `afterAgentCallback`    | `payload: { agent, context }`              |
+| `'before_model'`      | `beforeModelCallback`   | `payload: { context, llmRequest }`         |
+| `'after_model'`       | `afterModelCallback`    | `payload: { context, llmResponse }`        |
+| `'before_tool'`       | `beforeToolCallback`    | `payload: { tool, args, context }`         |
+| `'after_tool'`        | `afterToolCallback`     | `payload: { tool, args, context, result }` |
+| `'on_event'`          | `onEventCallback`       | `payload: { event }`                       |
+| `'on_user_message'`   | `onUserMessageCallback` | `payload: { userMessage }`                 |
+| `'before_run'`        | `beforeRunCallback`     | `payload: { context }`                     |
+| `'after_run'`         | `afterRunCallback`      | `payload: { context }`                     |
+| `'on_model_error'`    | `onModelErrorCallback`  | `payload: { request, error }`              |
+| `'on_tool_error'`     | `onToolErrorCallback`   | `payload: { tool, args, error }`           |
+
+### HookResult ↔ ADK callback return
+
+| HookResult field    | ADK pattern                                     | Notes                               |
+| ------------------- | ----------------------------------------------- | ----------------------------------- |
+| `action: 'proceed'` | Return `undefined`                              | Plugin returns nothing → continue   |
+| `action: 'block'`   | Return `Content` (for agent/model) or throw     | Non-undefined return short-circuits |
+| `modifications`     | Return modified `LlmRequest`/`LlmResponse`/args | Plugin returns modified version     |
+
+### ADK's early-exit pattern
+
+ADK plugins use "first non-undefined return wins":
+
+- `beforeModelCallback` returns `LlmResponse` → skips LLM call entirely (cache
+  hit)
+- `beforeToolCallback` returns modified `args` → tool runs with new args
+- `beforeAgentCallback` returns `Content` → skips agent run entirely
+
+Our `HookResult.modifications` carries the same data. The `action: 'block'` +
+return value pattern maps cleanly.
+
+### gemini-cli hooks NOT in ADK
+
+| gemini-cli hook       | ADK equivalent                       | Notes                                                         |
+| --------------------- | ------------------------------------ | ------------------------------------------------------------- |
+| `BeforeToolSelection` | —                                    | ADK doesn't let you modify which tools are available mid-turn |
+| `Notification`        | —                                    | ADK doesn't have notification hooks                           |
+| `SessionStart`        | `onUserMessageCallback` (first call) | Close enough                                                  |
+| `SessionEnd`          | `afterRunCallback`                   | Close enough                                                  |
+| `PreCompress`         | —                                    | ADK doesn't have context compression hooks                    |
+
+These gaps are fine — they're gemini-cli-specific hook points. Our generic
+`fire(hookPoint, payload)` handles them because the hook point is an open
+string. ADK executors simply don't fire these hook points, and
+`supportedHookPoints()` reflects that.
+
+---
+
+## 6. PolicyEvaluator ↔ ADK SecurityPlugin
+
+### ADK SecurityPlugin
+
+```typescript
+class SecurityPlugin extends BasePlugin {
+  policyEngine: BasePolicyEngine;
+
+  // In beforeToolCallback:
+  async beforeToolCallback({ tool, args, context }) {
+    const outcome = await this.policyEngine.evaluate(tool.name, args);
+    switch (outcome) {
+      case PolicyOutcome.DENY:
+        throw error;
+      case PolicyOutcome.CONFIRM:
+        context.requestConfirmation({ hint });
+      case PolicyOutcome.ALLOW:
+        return undefined; // proceed
+    }
+  }
+}
+```
+
+### Mapping
+
+| Our PolicyEvaluator       | ADK SecurityPlugin                                        | Notes                                      |
+| ------------------------- | --------------------------------------------------------- | ------------------------------------------ |
+| `evaluate(request)`       | `policyEngine.evaluate(toolName, args)`                   | ADK is simpler — tool name + args only     |
+| `PolicyDecision.allow`    | `PolicyOutcome.ALLOW`                                     | Direct                                     |
+| `PolicyDecision.deny`     | `PolicyOutcome.DENY`                                      | Direct                                     |
+| `PolicyDecision.ask_user` | `PolicyOutcome.CONFIRM` → `context.requestConfirmation()` | ADK chains to ToolConfirmation             |
+| `getExcluded()`           | —                                                         | ADK doesn't pre-filter tools               |
+| `request.principal`       | —                                                         | ADK doesn't track who's calling            |
+| `request.principalPath`   | Could use `context.agentName` + branch                    | For hierarchical policy                    |
+| `request.context`         | —                                                         | Our extension point for host-specific data |
+
+### How ADK policy maps when host controls execution
+
+With `pauseOnToolCalls: true`, the flow is:
+
+1. ADK yields tool call → adapter converts to ToolRequestEvent
+2. **Host** runs PolicyEvaluator.evaluate() — NOT ADK's SecurityPlugin
+3. Host decides allow/deny/ask_user
+4. If allowed, host executes tool and sends result via `session.stream()`
+
+This means **ADK's SecurityPlugin is bypassed when the host controls tool
+execution** — which is correct! The host's PolicyEvaluator is the authority.
+ADK's SecurityPlugin only matters when ADK executes tools internally
+(`pauseOnToolCalls: false`).
+
+---
+
+## 7. SessionContract ↔ ADK Session
+
+### Session mapping
+
+| Our SessionHandle | ADK Session                              | Notes                                     |
+| ----------------- | ---------------------------------------- | ----------------------------------------- |
+| `id`              | `Session.id`                             | Direct                                    |
+| `agentName`       | `Session.appName`                        | ADK uses appName, not agent name          |
+| `events`          | `Session.events: Event[]`                | Direct (but ADK Events → our AgentEvents) |
+| `state`           | `Session.state: Record<string, unknown>` | Direct                                    |
+| `lastUpdateTime`  | `Session.lastUpdateTime`                 | Direct                                    |
+
+### SessionProvider ↔ BaseSessionService
+
+| Our SessionProvider           | ADK BaseSessionService                          | Notes                      |
+| ----------------------------- | ----------------------------------------------- | -------------------------- |
+| `create(agentName, metadata)` | `createSession({ appName, userId })`            | ADK requires userId        |
+| `load(sessionId)`             | `getSession({ appName, userId, sessionId })`    | ADK requires all three IDs |
+| `list(agentName)`             | `listSessions({ appName, userId })`             | ADK scopes by userId       |
+| `delete(sessionId)`           | `deleteSession({ appName, userId, sessionId })` | Same pattern               |
+
+### Gap: ADK requires userId
+
+ADK sessions are scoped by `(appName, userId, sessionId)`. Our interface uses
+just `sessionId`. The adapter can embed userId in the session metadata or derive
+it from HostContext.
+
+### State prefixes (ADK-specific)
+
+ADK uses prefixed state keys:
+
+- `app:` — app-scoped, persisted
+- `user:` — user-scoped, persisted
+- `temp:` — temporary, stripped before persistence
+
+Our `SessionHandle.state` is a flat `Record<string, unknown>`. The adapter
+preserves prefixes as-is — they're just string keys. No conflict.
+
+---
+
+## 8. ContentPart ↔ ADK Content/Part
+
+### ADK uses Google GenAI types
+
+ADK's `Content` and `Part` come from `@google/genai`:
+
+```typescript
+interface Content {
+  role?: string;  // 'user' | 'model'
+  parts: Part[];
+}
+
+type Part = TextPart | InlineDataPart | FunctionCallPart | FunctionResponsePart | ...
+```
+
+### Mapping
+
+| Our ContentPart                                     | ADK/GenAI Part                                 | Notes                                                  |
+| --------------------------------------------------- | ---------------------------------------------- | ------------------------------------------------------ |
+| `{ type: 'text', text }`                            | `{ text: string }`                             | Direct                                                 |
+| `{ type: 'thought', thought }`                      | `{ thought: true, text: string }`              | ADK uses `thought` boolean flag on TextPart            |
+| `{ type: 'media', mimeType, data }`                 | `{ inlineData: { mimeType, data } }`           | Restructure                                            |
+| `{ type: 'reference', text, uri }`                  | `{ fileData: { fileUri, mimeType } }`          | Map fileData → reference                               |
+| `{ type: 'refusal', text }`                         | —                                              | Not in ADK/GenAI. Adapter would map from finishReason. |
+| `{ type: 'function_call', name, args, id }`         | `{ functionCall: { name, args, id } }`         | Unwrap                                                 |
+| `{ type: 'function_response', name, response, id }` | `{ functionResponse: { name, response, id } }` | Unwrap                                                 |
+
+### Verdict: CLEAN MAPPING
+
+The adapter converts between our flat discriminated union and ADK's nested Part
+structure. No information loss in either direction.
+
+---
+
+## 9. Composition ↔ ADK Agent Patterns
+
+| Our CompositionConfig.pattern | ADK Agent type                         | Notes                                            |
+| ----------------------------- | -------------------------------------- | ------------------------------------------------ |
+| `'hierarchical'`              | Any agent with `subAgents`             | Default — parent calls sub-agents as tools       |
+| `'sequential'`                | `SequentialAgent`                      | Runs children in order                           |
+| `'parallel'`                  | `ParallelAgent`                        | Runs children concurrently, branch isolation     |
+| `'loop'`                      | `LoopAgent`                            | Repeats children until escalate or maxIterations |
+| `'transfer'`                  | LlmAgent with `transfer_to_agent` tool | Peer-to-peer handoff                             |
+
+### Branch isolation
+
+ADK's `ParallelAgent` gives each child an isolated `branch` context:
+
+- Children don't see peer events
+- Each gets unique branch path: `"parent.child_0"`, `"parent.child_1"`
+- Results merged after all complete
+
+Maps to our `threadId` — each parallel branch gets a unique threadId. Events
+from different branches are interleaved by the host.
+
+---
+
+## 10. Summary: Gaps and Resolutions
+
+### No gaps blocking ADK integration:
+
+| Concern                 | Status    | Resolution                                                                |
+| ----------------------- | --------- | ------------------------------------------------------------------------- |
+| pauseOnToolCalls HITL   | **Works** | Adapter maps to stream() cycle (§2)                                       |
+| ToolConfirmation        | **Works** | Maps to ElicitationRequest (§2)                                           |
+| Auth requests           | **Works** | Maps to ElicitationRequest (§2)                                           |
+| Plugin hooks (12 types) | **Works** | Maps to LifecycleInterceptor.fire() (§5)                                  |
+| Agent transfers         | **Works** | Tool call (`transfer_to_agent`) + `stream_end` `reason: 'completed'` (§3) |
+| State delta pattern     | **Works** | SessionUpdateEvent or \_meta (§3)                                         |
+| Branch isolation        | **Works** | threadId mapping (§9)                                                     |
+| AgentTool pattern       | **Works** | SubagentTool with descriptor + factory (§4)                               |
+| Session management      | **Works** | Adapter maps userId into session (§7)                                     |
+
+### Minor adapter complexity:
+
+1. **Event fan-out:** One ADK Event may become multiple AgentEvents (message +
+   tool call + elicitation). Adapter logic needed but straightforward.
+2. **userId scoping:** ADK sessions require userId; our interface doesn't.
+   Adapter derives from HostContext.
+3. **Timestamp format:** ADK uses `number` (epoch ms); we use ISO 8601 string.
+   Simple conversion.
+4. **Content structure:** ADK uses nested Part types; we use flat discriminated
+   union. Adapter converts bidirectionally.
+
+### ADK features our interface supports that gemini-cli doesn't have yet:
+
+- `LoopAgent` / `ParallelAgent` / `SequentialAgent` composition → our
+  CompositionConfig
+- `eventActions.stateDelta` → our SessionUpdateEvent
+- `eventActions.transferToAgent` → tool call (`transfer_to_agent`) +
+  `stream_end` `reason: 'completed'`
+- `eventActions.escalate` → `stream_end` `reason: 'completed'` with
+  `data: { escalateReason }`
+- Long-running tools → our ToolUpdateEvent
+- Auth credential flow → our ElicitationRequest with kind: 'auth_required'

docs/adk-replat/NOTES-adk-ts-architecture.md

@@ -0,0 +1,274 @@
+# ADK-TS (Agent Development Kit - TypeScript) Architecture Notes
+
+## Package: `@google/adk` v0.4.0
+
+**Location:** `/Users/adamfweidman/Desktop/adk-int/adk-js/core/`
+
+## Agent Hierarchy
+
+```
+BaseAgent (abstract)
+├── LlmAgent         - Model-driven agent with tools (the main one)
+├── LoopAgent         - Runs sub-agents in a loop (maxIterations, escalate to exit)
+├── ParallelAgent     - Runs sub-agents concurrently (isolated branches)
+└── SequentialAgent   - Runs sub-agents sequentially
+```
+
+### BaseAgent Config
+
+- `name: string` - Unique identifier (must be valid JS identifier)
+- `description?: string` - One-line capability for model routing
+- `parentAgent?: BaseAgent` - Parent in agent tree
+- `subAgents?: BaseAgent[]` - Child agents
+- `beforeAgentCallback / afterAgentCallback` - Pre/post execution hooks
+
+### LlmAgent Config (extends BaseAgent)
+
+- `model?: string | BaseLlm` - LLM to use
+- `instruction?: string | InstructionProvider` - Agent-specific instructions
+- `globalInstruction?: string | InstructionProvider` - Tree-wide (root only)
+- `tools?: ToolUnion[]` - Available tools
+- `generateContentConfig?: GenerateContentConfig` - LLM params
+- `disallowTransferToParent / disallowTransferToPeers` - Transfer controls
+- `includeContents?: 'default' | 'none'` - Context history inclusion
+- `inputSchema / outputSchema` - Validation schemas
+- `outputKey?: string` - Session state key for output storage
+- `beforeModelCallback / afterModelCallback` - LLM hooks
+- `beforeToolCallback / afterToolCallback` - Tool hooks
+- `requestProcessors / responseProcessors` - LLM request/response processors
+- `codeExecutor?: BaseCodeExecutor`
+
+## Event System
+
+### Event Interface
+
+```typescript
+interface Event extends LlmResponse {
+  id: string;
+  invocationId: string;
+  author?: string; // "user" or agent name
+  actions: EventActions; // State/artifact/auth/transfer operations
+  longRunningToolIds?: string[];
+  branch?: string; // Hierarchical agent path
+  timestamp: number;
+  content?: Content;
+  partial?: boolean; // Streaming indicator
+}
+```
+
+### EventActions
+
+```typescript
+interface EventActions {
+  skipSummarization?: boolean;
+  stateDelta: Record<string, unknown>;
+  artifactDelta: Record<string, number>;
+  transferToAgent?: string;
+  escalate?: boolean;
+  requestedAuthConfigs: Record<string, AuthConfig>;
+  requestedToolConfirmations: Record<string, ToolConfirmation>;
+}
+```
+
+### Structured Events (utility layer)
+
+Converts raw Event to discriminated union:
+
+```
+EventType: THOUGHT | CONTENT | TOOL_CALL | TOOL_RESULT | CALL_CODE |
+           CODE_RESULT | ERROR | ACTIVITY | TOOL_CONFIRMATION | FINISHED
+```
+
+## Tool System
+
+### BaseTool (abstract)
+
+- `name, description, isLongRunning`
+- `_getDeclaration(): FunctionDeclaration` - OpenAPI schema for LLM
+- `runAsync(request): Promise<unknown>` - Execute tool
+- `processLlmRequest(request): Promise<void>` - Preprocessing
+
+### Concrete Tool Types
+
+1. **FunctionTool** - Generic typed tools (Zod schema support)
+2. **AgentTool** - Wrap agents as tools (for hierarchical composition)
+3. **MCPTool** - Model Context Protocol server tools
+4. **GoogleSearchTool** - Built-in web search
+5. **ExitLoopTool** - Signal loop exit
+6. **LongRunningFunctionTool** - Async long-running operations
+
+### BaseToolset
+
+- Filter tools by predicate or string list
+- `getTools(context)`, `close()`, `isToolSelected()`
+- **MCPToolset** - Toolset for MCP server connections
+
+## Session Management
+
+### Session Interface
+
+```typescript
+interface Session {
+  id: string;
+  appName: string;
+  userId: string;
+  state: Record<string, unknown>; // Mutable key-value store
+  events: Event[]; // Complete conversation history
+  lastUpdateTime: number;
+}
+```
+
+### Session Services
+
+- `BaseSessionService` (abstract) - createSession, getSession, listSessions,
+  deleteSession, appendEvent
+- `InMemorySessionService` - In-process storage
+- `DatabaseSessionService` - Mikro-ORM backed (SQL)
+
+### State Management
+
+- `State` class wraps base state + delta
+- `get()` returns from delta if present, else base
+- `set()` updates delta only
+- `hasDelta()` checks if changes made
+
+## Human-in-the-Loop (HITL)
+
+### Tool Confirmation
+
+```typescript
+class ToolConfirmation {
+  hint?: string; // Guidance for user
+  confirmed: boolean; // User approval
+  payload?: unknown; // Additional context
+}
+```
+
+### Security Plugin
+
+- `beforeToolCallback` - Evaluates policy before tool execution
+- `BasePolicyEngine` interface with `evaluate()` method
+- `PolicyOutcome`: DENY | CONFIRM | ALLOW
+
+### Auth Requests
+
+- `context.requestCredential(authConfig)` - Request auth from user
+- `context.getAuthResponse(authConfig)` - Check for auth response
+- Sets `eventActions.requestedAuthConfigs[functionCallId]`
+
+## Multi-Agent Patterns
+
+### Agent Transfer
+
+- LlmAgent injects `transfer_to_agent(agentName)` tool
+- Sets `eventActions.transferToAgent = targetAgentName`
+- Runner resolves target and continues
+- Can transfer to: sub-agents, parent (if not disabled), peers (if not disabled)
+
+### Parallel Agent
+
+- Runs all subAgents concurrently
+- Isolates each via `branch` context
+- Sub-agents don't see peer history
+- Merges event streams with fair ordering
+
+### Loop Agent
+
+- Repeatedly runs subAgents
+- `maxIterations` caps loop count
+- Exits on `event.actions.escalate === true`
+
+## Plugin System
+
+### BasePlugin Lifecycle Hooks (14 hooks!)
+
+- `onUserMessageCallback` - Preprocess user messages
+- `beforeRunCallback` - Before agent run (can short-circuit)
+- `onEventCallback` - Per-event (can modify events)
+- `afterRunCallback` - Final cleanup
+- `beforeAgentCallback / afterAgentCallback` - Agent lifecycle
+- `beforeModelCallback / afterModelCallback` - LLM lifecycle
+- `onModelErrorCallback` - Model error handling
+- `beforeToolCallback / afterToolCallback` - Tool lifecycle
+- `onToolErrorCallback` - Tool error handling
+
+### Built-in Plugins
+
+- **LoggingPlugin** - Debug logging
+- **SecurityPlugin** - Policy enforcement + tool confirmation
+- **PluginManager** - Plugin orchestration
+
+## Runner
+
+### Runner Config
+
+```typescript
+interface RunnerConfig {
+  appName: string;
+  agent: BaseAgent; // Root agent
+  plugins?: BasePlugin[];
+  artifactService?: BaseArtifactService;
+  sessionService: BaseSessionService; // Required
+  memoryService?: BaseMemoryService;
+  credentialService?: BaseCredentialService;
+}
+```
+
+### RunConfig (per-run options)
+
+```typescript
+interface RunConfig {
+  speechConfig?: SpeechConfig;
+  responseModalities?: Modality[];
+  maxLlmCalls?: number; // Default 500
+  pauseOnToolCalls?: boolean; // Client-side tool execution
+  streamingMode?: StreamingMode; // NONE | SSE | BIDI
+  // ... audio/live configs
+}
+```
+
+### Execution Pipeline
+
+1. Load or create session
+2. Create InvocationContext
+3. Run pluginManager.runOnUserMessageCallback()
+4. Append user message to session
+5. Run agent.runAsync(invocationContext) → yields events
+6. For each non-partial event: append to session
+7. Run pluginManager.runOnEventCallback()
+8. Run pluginManager.runAfterRunCallback()
+
+## Model Layer
+
+### BaseLlm (abstract)
+
+- `generateContentAsync(llmRequest, stream?): AsyncGenerator<LlmResponse>`
+- `connect(llmRequest): Promise<BaseLlmConnection>` - For live/streaming
+
+### Implementations
+
+- `Gemini` - Google Gemini API
+- `ApigeeLlm` - Apigee-wrapped models
+- `LLMRegistry` - Static registry for model lookup
+
+## Service Adapters (all abstract base + implementations)
+
+| Service               | Implementations                |
+| --------------------- | ------------------------------ |
+| BaseSessionService    | InMemory, Database (Mikro-ORM) |
+| BaseArtifactService   | InMemory, File, GCS            |
+| BaseMemoryService     | InMemory                       |
+| BaseCredentialService | InMemory                       |
+| BaseCodeExecutor      | BuiltIn                        |
+
+## Design Patterns
+
+1. **Symbol-based type guards** - Every class uses `Symbol.for()` + `isXxx()`
+2. **Abstract base classes** - Service interfaces via abstract classes
+3. **Async generators** - All agent execution yields events
+4. **Context objects** - Rich context passed to callbacks/tools
+5. **Delta state** - Session state + event action deltas
+6. **Plugin middleware** - 14 hooks at multiple execution points
+7. **Tree-based hierarchy** - Parent-child agents with root traversal
+8. **Branch isolation** - Parallel agents use branch paths
+9. **Callback chains** - Multiple callbacks per stage with early termination

docs/adk-replat/NOTES-cross-sdk-comparison.md

@@ -0,0 +1,587 @@
+# Cross-SDK Comparison: Events, Agents, and Interface Superset
+
+## 1. AgentEvents: Our Outline vs Michael's
+
+Our outline and Michael's `Gemini CLI Agents.txt` are **nearly identical** in
+event taxonomy. The only difference is we added a `stream_end` event type:
+
+| #   | Michael's Events       | Our Outline           | Delta                                                                           |
+| --- | ---------------------- | --------------------- | ------------------------------------------------------------------------------- |
+| 1   | `initialize`           | `InitializeEvent`     | Same                                                                            |
+| 2   | `session_update`       | `SessionUpdateEvent`  | Same                                                                            |
+| 3   | `message`              | `MessageEvent`        | Same — streaming handled by AsyncGenerator                                      |
+| 4   | `tool_request`         | `ToolRequestEvent`    | Same                                                                            |
+| 5   | `tool_update`          | `ToolUpdateEvent`     | Same                                                                            |
+| 6   | `tool_response`        | `ToolResponseEvent`   | Same                                                                            |
+| 7   | `elicitation_request`  | `ElicitationRequest`  | Same                                                                            |
+| 8   | `elicitation_response` | `ElicitationResponse` | Same                                                                            |
+| 9   | `usage`                | `UsageEvent`          | Same                                                                            |
+| 10  | `error`                | `ErrorEvent`          | Same                                                                            |
+| 11  | `custom`               | `CustomEvent`         | Same                                                                            |
+| 12  | —                      | **StreamEnd**         | **Added**: completed, failed, aborted, max_turns, max_budget, max_time, refusal |
+
+### Minor structural differences:
+
+| Aspect                 | Michael                                             | Our Outline                                                               |
+| ---------------------- | --------------------------------------------------- | ------------------------------------------------------------------------- |
+| **Base type**          | `AgentEventCommon` with `type: string` (fully open) | `AgentEventBase` with `type: AgentEventType` (`'known' \| (string & {})`) |
+| **Agent ID**           | —                                                   | `agentId` on event base (which agent emitted this event)                  |
+| **Event map**          | Generic `interface AgentEvents` + mapped type       | Same — adopted Michael's pattern for declaration merging extensibility    |
+| **ContentPart.\_meta** | Required (`_meta: Record<string, unknown>`)         | Optional (`_meta?: Record<string, unknown>`)                              |
+| **ErrorData.status**   | Google RPC codes (`'RESOURCE_EXHAUSTED' \| '...'`)  | Open string (per our generic philosophy)                                  |
+| **Message.role**       | `'user' \| 'agent' \| 'developer'`                  | Same                                                                      |
+| **Stream end**         | Only `initialize`                                   | `stream_end` with `reason` field + open `data` bag                        |
+| **Handoff**            | Not covered                                         | Tool call (`transfer_to_agent`) — no dedicated event                      |
+| **Pausing**            | Implicit (elicitation/tool events)                  | Same — no explicit pause/resume events                                    |
+
+### Design decisions adopted from Michael
+
+1. **`interface AgentEvents` + mapped type** — Michael's pattern enables
+   declaration merging, letting any module add new event types without modifying
+   the base definition. Strictly better than an explicit union type.
+2. **`_meta` on ContentPart** — More extensible. We adopted it (as optional).
+3. **Implicit pausing** — No separate pause/resume events. When the agent emits
+   an `elicitation_request` or `tool_request`, the stream naturally pauses. The
+   host calls `stream()` to resume.
+
+---
+
+## 2. Claude Agent SDK — Key Interfaces
+
+Source: `@anthropic-ai/claude-agent-sdk`
+
+### Agent Execution Model
+
+```typescript
+// Entry point — not an interface, a function
+function query({
+  prompt: string | AsyncIterable<SDKUserMessage>,
+  options?: Options
+}): Query  // extends AsyncGenerator<SDKMessage, void>
+```
+
+### Message Types (Event Stream)
+
+```typescript
+type SDKMessage =
+  | SystemMessage // subtype: "init" | "compact_boundary"
+  | AssistantMessage // Claude's response with tool calls
+  | UserMessage // Tool results fed back
+  | StreamEvent // Raw API stream events (opt-in)
+  | ResultMessage // Final: success | error_max_turns | error_max_budget_usd | error_during_execution
+  | CompactBoundaryMessage; // Context compaction marker
+```
+
+### Tool Approval (HITL)
+
+```typescript
+canUseTool: async (toolName: string, input: Record<string, any>) =>
+  Promise<
+    | { behavior: 'allow'; updatedInput: Record<string, any> }
+    | { behavior: 'deny'; message: string }
+  >;
+```
+
+### Subagent Definition
+
+```typescript
+interface AgentDefinition {
+  description: string; // When to invoke
+  prompt: string; // System prompt
+  tools?: string[]; // Available tools (defaults to all)
+  model?: 'sonnet' | 'opus' | 'haiku' | 'inherit';
+}
+```
+
+### Session Management
+
+```typescript
+interface Options {
+  continue?: boolean;         // Resume most recent session
+  resume?: string;            // Resume by session ID
+  forkSession?: boolean;      // Branch from resume point
+  persistSession?: boolean;   // Default: true
+  maxTurns?: number;
+  maxBudgetUsd?: number;      // Spend limit
+  permissionMode?: 'default' | 'acceptEdits' | 'plan' | 'dontAsk' | 'bypassPermissions';
+  structuredOutput?: { type: "json_schema", ... };
+}
+```
+
+### Result (Termination)
+
+```typescript
+interface SDKResultMessage {
+  type: 'result';
+  subtype:
+    | 'success'
+    | 'error_max_turns'
+    | 'error_max_budget_usd'
+    | 'error_during_execution'
+    | 'error_max_structured_output_retries';
+  result?: string;
+  total_cost_usd: number;
+  usage: { input_tokens: number; output_tokens: number };
+  num_turns: number;
+  session_id: string;
+  stop_reason: string | null; // "end_turn", "max_tokens", "refusal"
+}
+```
+
+### V2 Preview (Simpler API)
+
+```typescript
+await using session = unstable_v2_createSession({ model: "..." });
+await session.send("Hello!");
+for await (const msg of session.stream()) { ... }
+await session.send("Follow-up");
+for await (const msg of session.stream()) { ... }
+```
+
+---
+
+## 3. OpenAI Codex SDK / Responses API — Key Interfaces
+
+### Codex SDK (TypeScript)
+
+```typescript
+// Client
+const codex = new Codex({ env?, config? });
+const thread = codex.startThread({ workingDirectory?, skipGitRepoCheck? });
+const thread = codex.resumeThread(threadId);
+
+// Execution
+const turn = await thread.run(prompt: string | InputEntry[], options?);
+const { events } = await thread.runStreamed(prompt);
+
+// Streaming
+for await (const event of events) {
+  switch (event.type) {
+    case "item.completed": // event.item
+    case "turn.completed": // event.usage
+  }
+}
+```
+
+### Responses API Streaming Events (53 types)
+
+Organized hierarchically:
+
+**Response Lifecycle (7):**
+
+- `response.queued`, `response.created`, `response.in_progress`
+- `response.completed`, `response.incomplete`, `response.failed`
+- `error`
+
+**Content Streaming (8):**
+
+- `response.output_item.added`, `response.output_item.done`
+- `response.content_part.added`, `response.content_part.done`
+- `response.output_text.delta`, `response.output_text.done`
+- `response.refusal.delta`, `response.refusal.done`
+
+**Reasoning (6):**
+
+- `response.reasoning_text.delta`, `response.reasoning_text.done`
+- `response.reasoning_summary_part.added`,
+  `response.reasoning_summary_part.done`
+- `response.reasoning_summary_text.delta`,
+  `response.reasoning_summary_text.done`
+
+**Function Calls (2):**
+
+- `response.function_call_arguments.delta`,
+  `response.function_call_arguments.done`
+
+**MCP (8):**
+
+- `response.mcp_call_arguments.delta`, `response.mcp_call_arguments.done`
+- `response.mcp_call.in_progress`, `response.mcp_call.completed`,
+  `response.mcp_call.failed`
+- `response.mcp_list_tools.in_progress`, `response.mcp_list_tools.completed`,
+  `response.mcp_list_tools.failed`
+
+**Built-in Tools (15):**
+
+- File search: `in_progress`, `searching`, `completed`
+- Web search: `in_progress`, `searching`, `completed`
+- Code interpreter: `in_progress`, `interpreting`, `code.delta`, `code.done`,
+  `completed`
+- Image gen: `in_progress`, `generating`, `partial_image`, `completed`
+
+**Audio (4):**
+
+- `response.audio.delta`, `response.audio.done`
+- `response.audio.transcript.delta`, `response.audio.transcript.done`
+
+**Annotations (1):**
+
+- `response.output_text.annotation.added`
+
+### OpenAI Agents SDK (higher-level)
+
+```python
+# Python-first, but patterns apply
+class RunItemStreamEvent:
+    name: Literal[
+        "message_output_created",
+        "handoff_requested",
+        "handoff_occurred",
+        "tool_called",
+        "tool_output",
+        "tool_search_called",
+        "tool_search_output_created",
+        "reasoning_item_created",
+        "mcp_approval_requested",
+        "mcp_approval_response",
+        "mcp_list_tools",
+    ]
+
+class AgentUpdatedStreamEvent:
+    # Fires when current agent changes (handoff)
+    new_agent: Agent
+```
+
+---
+
+## 4. Superset Analysis — What Changes Our Interfaces?
+
+### Concepts Present in ALL Systems
+
+| Concept               | gemini-cli | ADK-TS | Claude SDK    | Codex/OpenAI   | Our Interfaces          |
+| --------------------- | ---------- | ------ | ------------- | -------------- | ----------------------- |
+| Text streaming        | ✅         | ✅     | ✅            | ✅             | ✅ MessageEvent         |
+| Tool request/response | ✅         | ✅     | ✅            | ✅             | ✅ ToolRequest/Response |
+| Thinking/reasoning    | ✅         | ✅     | ✅ (thinking) | ✅ (reasoning) | ✅ ContentPart.thought  |
+| Error events          | ✅         | ✅     | ✅            | ✅             | ✅ ErrorEvent           |
+| Token usage           | ✅         | ✅     | ✅            | ✅             | ✅ UsageEvent           |
+| Tool progress         | ✅         | ✅     | —             | ✅             | ✅ ToolUpdateEvent      |
+| Session resume        | ✅         | ✅     | ✅            | ✅             | ✅ sessionRef           |
+| Subagents             | ✅         | ✅     | ✅            | —              | ✅ threadId             |
+| Abort/cancel          | ✅         | ✅     | ✅            | ✅             | ✅ abort()              |
+| Metadata escape hatch | —          | ✅     | —             | —              | ✅ \_meta               |
+
+### NEW Concepts From Claude/Codex That We Should Incorporate
+
+#### 4.1 Structured Stream End Reasons (HIGH PRIORITY)
+
+**What:** Claude SDK has typed termination:
+`success | error_max_turns | error_max_budget_usd | error_during_execution`.
+OpenAI has `completed | incomplete | failed`.
+
+**Why it matters:** We need a `stream_end` event that captures why the stream
+ended — the one signal not covered by other event types.
+
+**Final design — `stream_end` with `reason` + open `data` bag:**
+
+```typescript
+type StreamEndReason =
+  | 'completed'
+  | 'failed'
+  | 'aborted'
+  | 'max_turns'
+  | 'max_budget'
+  | 'max_time'
+  | 'refusal'
+  | (string & {});
+
+interface StreamEnd {
+  reason: StreamEndReason;
+  data?: Record<string, unknown>; // { result?, cost?, usage?, numTurns?, error?, ... }
+}
+```
+
+**Design rationale:**
+
+- Start is covered by `initialize`. Pausing is implicit (elicitation/tool
+  request events). Handoff is a tool call (`transfer_to_agent`).
+- End-of-stream details go in `data` as an open bag, not fixed fields.
+
+#### 4.2 Budget Constraints (MEDIUM PRIORITY)
+
+**What:** Claude SDK has `maxBudgetUsd`. Neither gemini-cli nor ADK has this
+today.
+
+**Why it matters:** Cost control is critical for production deployments.
+
+**Proposed change to AgentConstraints:**
+
+```typescript
+interface AgentConstraints {
+  maxTurns?: number;
+  maxTimeMinutes?: number;
+  maxLlmCalls?: number;
+  maxBudgetUsd?: number; // NEW: from Claude SDK
+}
+```
+
+#### 4.3 Session Forking (MEDIUM PRIORITY)
+
+**What:** Claude SDK supports `forkSession: boolean` — branch from a resume
+point to explore alternatives.
+
+**Why it matters:** Enables "what if" exploration without destroying history.
+Useful for plan mode.
+
+**Proposed change to ExecutionRequest:**
+
+```typescript
+interface ExecutionRequest {
+  // ... existing fields ...
+  sessionRef?: string | SessionSnapshot;
+  forkSession?: boolean; // NEW: branch from sessionRef instead of continuing
+}
+```
+
+#### 4.4 Permission Modes on Execution (MEDIUM PRIORITY)
+
+**What:** Claude has 5 permission modes:
+`default | acceptEdits | plan | dontAsk | bypassPermissions`. gemini-cli has 4
+approval modes: `default | autoEdit | yolo | plan`.
+
+**Why it matters:** Both systems have this concept. It should be in
+ExecutionOptions, not hard-coded.
+
+**Proposed change to ExecutionOptions:**
+
+```typescript
+interface ExecutionOptions {
+  // ... existing fields ...
+  permissionMode?: string; // Open string. Conventions: 'default' | 'auto_edit' | 'autonomous' | 'plan' | string
+}
+```
+
+#### 4.5 Agent Handoff (MEDIUM PRIORITY)
+
+**What:** OpenAI Agents SDK has explicit `handoff_requested` /
+`handoff_occurred` events plus `AgentUpdatedStreamEvent`. ADK has
+`transfer_to_agent` tool + `eventActions.transferToAgent`. Claude SDK has
+subagent invocation via Agent tool.
+
+**Why it matters:** When agent A delegates to agent B, the host/UI needs to
+know.
+
+**Design decision: Handoff is a tool call, not a separate event type.**
+
+The agent calls `transfer_to_agent` as a tool (ToolRequest event). The host
+intercepts this tool call (since host controls tool execution), looks up the
+target agent, creates a new executor via the factory, and mediates the handoff.
+The originating agent's stream ends with `stream_end` reason `'completed'`.
+
+```typescript
+// 1. Agent emits tool request:
+{ type: 'tool_request', name: 'transfer_to_agent', args: { target: 'coder', reason: '...' } }
+
+// 2. Host mediates handoff, originating agent completes:
+{ type: 'stream_end', reason: 'completed', agentId: 'planner', data: { handoffTarget: 'coder' } }
+```
+
+This avoids duplicating routing logic between stream_end events and tool calls.
+Matches ADK's `transfer_to_agent` tool pattern.
+
+#### 4.6 Refusal as Distinct Signal (LOW PRIORITY)
+
+**What:** OpenAI has explicit `response.refusal.delta/done` events. Claude has
+`stop_reason: "refusal"`.
+
+**Why it matters:** Model refusals are operationally important (safety, policy).
+
+**Proposed:** No new event type. Handle via `MessageEvent` with a `refusal`
+content part type, or via `ErrorEvent` with specific error code. ContentPart can
+be extended:
+
+```typescript
+| { type: 'refusal'; text: string }
+```
+
+#### 4.7 Content Annotations (LOW PRIORITY)
+
+**What:** OpenAI has `response.output_text.annotation.added` for citations, file
+paths.
+
+**Why it matters:** Citations and source attribution are increasingly important.
+
+**Proposed:** Michael's `reference` ContentPart already covers this. No change
+needed — `reference` with `uri` and `text` handles citations.
+
+#### 4.8 Context Compaction Events (LOW PRIORITY)
+
+**What:** Claude SDK has `CompactBoundaryMessage` marking when context was
+compressed.
+
+**Why it matters:** For long sessions, knowing when context was compressed helps
+with debugging and UI.
+
+**Proposed:** `CustomEvent` with `kind: 'compact_boundary'`. No new event type
+needed.
+
+#### 4.9 Structured Output Schema (ALREADY COVERED)
+
+**What:** Both Claude (`structuredOutput`) and OpenAI support JSON Schema output
+constraints.
+
+**Status:** Already covered by `AgentDescriptor.outputSchema: JsonSchema`. No
+change needed.
+
+### Concepts We DON'T Need to Adopt
+
+| Concept                                                                   | Why Skip                                                                                                               |
+| ------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |
+| OpenAI's 53 granular streaming events                                     | Too coupled to Responses API internals. Our `ToolUpdateEvent` + `MessageEvent` via AsyncGenerator abstracts over this. |
+| OpenAI's per-tool-type events (file_search, web_search, code_interpreter) | Tool-specific progress belongs in `ToolUpdateEvent.data`, not in the event taxonomy.                                   |
+| Audio/Image streaming events                                              | Handle via `ToolUpdateEvent` with media ContentParts. When needed, add as ContentPart types, not event types.          |
+| Claude's raw `StreamEvent` wrapper                                        | Implementation detail of the Claude API client. Our adapters consume these internally.                                 |
+| MCP-specific events (mcp_call, mcp_list_tools)                            | MCP tools are just tools. Use generic `ToolRequestEvent/ToolResponseEvent`. MCP approval is an `ElicitationRequest`.   |
+
+---
+
+## 5. Updated Event Type Comparison (Full Superset)
+
+| #   | Event Type           | Michael | Our Outline | Claude SDK                    | OpenAI                            | Verdict                                        |
+| --- | -------------------- | ------- | ----------- | ----------------------------- | --------------------------------- | ---------------------------------------------- |
+| 1   | Initialize           | ✅      | ✅          | SystemMessage(init)           | —                                 | **Keep**                                       |
+| 2   | Session Update       | ✅      | ✅          | —                             | —                                 | **Keep**                                       |
+| 3   | Message              | ✅      | ✅          | AssistantMessage              | output_text.delta/done            | **Keep**                                       |
+| 4   | Tool Request         | ✅      | ✅          | AssistantMessage.tool_use     | function_call_arguments           | **Keep**                                       |
+| 5   | Tool Update          | ✅      | ✅          | —                             | per-tool progress events          | **Keep**                                       |
+| 6   | Tool Response        | ✅      | ✅          | UserMessage                   | —                                 | **Keep**                                       |
+| 7   | Elicitation Request  | ✅      | ✅          | canUseTool callback           | mcp_approval_requested            | **Keep**                                       |
+| 8   | Elicitation Response | ✅      | ✅          | canUseTool return             | mcp_approval_response             | **Keep**                                       |
+| 9   | Usage                | ✅      | ✅          | ResultMessage.usage           | response.completed                | **Keep**                                       |
+| 10  | Error                | ✅      | ✅          | ResultMessage(error\_\*)      | response.failed                   | **Keep**                                       |
+| 11  | Custom               | ✅      | ✅          | —                             | —                                 | **Keep**                                       |
+| 12  | StreamEnd            | —       | ✅          | ResultMessage + SystemMessage | response.created/completed/failed | **Keep — `stream_end` with `reason` + `data`** |
+
+**Result: Our 12 event types are the right abstraction level.** Claude and
+OpenAI validate every category. The granularity differences (OpenAI's 53 vs
+our 12) are implementation details that adapters handle internally. `stream_end`
+uses a single `reason` field with an open `data` bag. Handoff is a tool call.
+Pausing is implicit.
+
+---
+
+## 6. Updated ContentPart Types (Superset)
+
+```typescript
+type ContentPart = (
+  | { type: 'text'; text: string }
+  | { type: 'thought'; thought: string; thoughtSignature?: string }
+  | { type: 'media'; data?: string; uri?: string; mimeType?: string }
+  | {
+      type: 'reference';
+      text: string;
+      data?: string;
+      uri?: string;
+      mimeType?: string;
+    }
+  | { type: 'refusal'; text: string } // NEW: from OpenAI
+) &
+  // Future: type: string for unknown types from new SDKs
+  { _meta?: Record<string, unknown> };
+```
+
+Adding `refusal` as a ContentPart type (rather than a new event) keeps the event
+taxonomy stable while supporting model refusals from both Claude and OpenAI.
+
+---
+
+## 7. Key Architectural Patterns Across SDKs
+
+### Pattern: Execution Entry Points
+
+| SDK         | Entry Point                                                               | Multi-turn Pattern                              |
+| ----------- | ------------------------------------------------------------------------- | ----------------------------------------------- |
+| Michael     | `agent.send(trajectory, data)` / `session.send()` + `session.update()`    | Same method / three-method session              |
+| Our Outline | `session.stream(data)` + `session.update(config)` + `session.steer(data)` | Four-method session (stream/update/steer/abort) |
+| Claude SDK  | `query({ prompt, options })`                                              | New `query()` call with `resume: sessionId`     |
+| Claude V2   | `session.send()` + `session.stream()`                                     | Separate send/stream                            |
+| Codex SDK   | `thread.run(prompt)` / `thread.runStreamed(prompt)`                       | Same thread object                              |
+
+**Observation:** Claude V2 and Codex both use a stateful session/thread object
+with send+stream. Michael uses a single `send()` method. Our `stream()` method
+is the unified version — the first call starts, subsequent calls continue (like
+ADK's `runAsync()`).
+
+### Pattern: Tool Approval
+
+| SDK         | Pattern                                                  | Sync/Async               |
+| ----------- | -------------------------------------------------------- | ------------------------ |
+| gemini-cli  | PolicyEngine + ConfirmationBus                           | Async (message bus)      |
+| ADK-TS      | SecurityPlugin.policyCheck()                             | Async (plugin callback)  |
+| Claude SDK  | `canUseTool()` callback                                  | Async (callback)         |
+| OpenAI      | `mcp_approval_requested` event                           | Event-based              |
+| Our Outline | `ElicitationRequest` event + `PolicyEvaluator` interface | Both (event + interface) |
+
+**Observation:** Our approach covers both patterns — the `ElicitationRequest`
+event for event-based approval (like OpenAI), and the `PolicyEvaluator`
+interface for synchronous policy checks (like gemini-cli/ADK/Claude). This is
+the right superset.
+
+### Pattern: Subagent Definition
+
+| SDK           | Pattern                          | Key Fields                                                                                 |
+| ------------- | -------------------------------- | ------------------------------------------------------------------------------------------ |
+| gemini-cli    | `AgentDefinition` (local/remote) | name, description, kind, tools, model                                                      |
+| ADK-TS        | `BaseAgentConfig`                | name, description, subAgents, tools                                                        |
+| Claude SDK    | `AgentDefinition`                | description, prompt, tools, model                                                          |
+| OpenAI Agents | `Agent` class                    | name, instructions, tools, handoffs, model                                                 |
+| Our Outline   | `AgentDescriptor`                | name, description, executor, inputSchema, capabilities, ownTools, requiredTools, subAgents |
+
+**Observation:** Our `AgentDescriptor` is the most complete. Claude's `prompt`
+field and OpenAI's `instructions` are executor-level concerns (system prompt),
+not descriptor-level. The descriptor declares identity; the executor uses the
+prompt. This separation is correct.
+
+One gap: **handoffs**. OpenAI Agents has an explicit `handoffs` field listing
+which agents can be delegated to. Our `subAgents` field serves the same purpose
+but the naming implies hierarchy rather than peer delegation. Consider whether
+`subAgents` should be renamed to `delegateAgents` or kept as-is with
+documentation clarifying it covers both hierarchical and peer delegation.
+
+---
+
+## 8. Concrete Changes to outline.md
+
+Based on this analysis, the following changes should be made:
+
+### Applied (validated by multiple SDKs):
+
+1. ✅ **`type: AgentEventType`** with known values + `(string & {})`
+   (autocomplete + extensibility)
+2. ✅ **`interface AgentEvents` + mapped type** (adopted from Michael for
+   declaration merging)
+3. ✅ **`agentId` on event base** (which agent emitted this event)
+4. ✅ **`_meta` on ContentPart** (aligned with Michael)
+5. ✅ **`stream_end` event** — signals why the stream ended, with `reason`
+   field + open `data` bag
+6. ✅ **Handoff as tool call** — `transfer_to_agent` tool, not a separate event
+7. ✅ **`maxBudgetUsd` in AgentConstraints** (Claude SDK, increasingly standard)
+8. ✅ **`refusal` ContentPart type** (both Claude and OpenAI surface refusals)
+9. ✅ **`forkSession` in ExecutionRequest** (Claude SDK, valuable for
+   exploration)
+10. ✅ **`permissionMode` in ExecutionOptions** (both gemini-cli and Claude SDK)
+11. ✅ **`cost` field on Usage** (Claude SDK tracks total_cost_usd)
+
+### Correctly abstracted (no change needed):
+
+- Event taxonomy (12 types) — validated as right abstraction level
+- `AgentDescriptor` shape — most complete across all SDKs
+- `AgentSession.stream/update/steer/abort` — covers all SDK patterns
+- ToolUpdate — correctly abstracts over OpenAI's 15+ tool-specific progress
+  events
+- `ElicitationRequest/Response` — covers both callback and event patterns
+- `ContentPart` types — text/thought/media/reference/refusal
+
+---
+
+## Sources
+
+- [Claude Agent SDK TypeScript Reference](https://platform.claude.com/docs/en/agent-sdk/typescript)
+- [Claude Agent SDK Streaming](https://platform.claude.com/docs/en/agent-sdk/streaming-output)
+- [Claude Agent SDK Sessions](https://platform.claude.com/docs/en/agent-sdk/sessions)
+- [Claude Agent SDK Subagents](https://platform.claude.com/docs/en/agent-sdk/subagents)
+- [OpenAI Codex SDK TypeScript](https://github.com/openai/codex/tree/main/sdk/typescript)
+- [OpenAI Codex SDK Docs](https://developers.openai.com/codex/sdk/)
+- [OpenAI Responses API Streaming Events](https://developers.openai.com/api/reference/resources/responses/streaming-events/)
+- [OpenAI Agents SDK Streaming](https://openai.github.io/openai-agents-python/streaming/)
+- [Responses API Streaming Guide (Community)](https://community.openai.com/t/responses-api-streaming-the-simple-guide-to-events/1363122)

docs/adk-replat/NOTES-gemini-cli-architecture.md

@@ -0,0 +1,259 @@
+# Gemini CLI Architecture Notes
+
+## Project Structure
+
+**Monorepo packages:**
+
+- `packages/core/` - Main execution engine (the big one)
+- `packages/cli/` - CLI frontend
+- `packages/sdk/` - SDK for extensions
+- `packages/a2a-server/` - Agent-to-agent server
+- `packages/devtools/` - Dev utilities
+- `packages/vscode-ide-companion/` - VS Code extension
+
+## Core Execution Loop
+
+### GeminiClient (`core/src/core/client.ts` ~38KB)
+
+- **Primary orchestrator** for user interactions
+- Manages session lifecycle, message routing, model selection
+- Coordinates hooks, context management, error recovery
+- Enforces `MAX_TURNS = 100` per session
+- Tracks `currentSequenceModel` for multi-turn stickiness
+- Handles history compression when context grows
+
+### GeminiChat (`core/src/core/geminiChat.ts` ~34KB)
+
+- Bidirectional LLM communication
+- Maintains `history[]` alternating user/model turns
+- Retry logic: max 2 attempts, 500ms delay for invalid responses
+- Fires `BeforeModel` and `AfterModel` hooks
+- Integrates ChatRecordingService for persistence
+
+### Scheduler (`core/src/scheduler/scheduler.ts` ~23KB)
+
+- **Three-phase event-driven**: Ingestion → Processing → Completion
+- Tool call state machine:
+  `Validating → AwaitingApproval → Scheduled → Executing → Terminal`
+- Terminal states: `Success`, `Error`, `Cancelled`
+- Parallel execution for read-only and agent-type tools
+- Yields to event loop for user approval
+- Publishes state changes via MessageBus
+
+### CoreToolScheduler (`core/src/core/coreToolScheduler.ts` ~38KB)
+
+- Sequential, queue-based tool processing
+- Validates policy via PolicyEngine
+- Confirmation handling via ToolModificationHandler (editor integration)
+- Uses MessageBus for async confirmation responses
+
+## Tool System
+
+### DeclarativeTool Pattern
+
+- **Separation of concerns**: build() → validate → createInvocation() →
+  execute()
+- `ToolBuilder` defines metadata (name, displayName, description, kind) + schema
+  via `getSchema()`
+- `ToolInvocation` has: `getDescription()`, `toolLocations()`,
+  `shouldConfirmExecute()`, `execute()`
+- `ToolResult` contains: `llmContent` (for LLM), `returnDisplay` (for UI), error
+  details, tail calls
+
+### BaseToolInvocation
+
+- Abstract base with MessageBus integration for policy/confirmation
+- Three decision paths: ALLOW, DENY, ASK_USER via `getMessageBusDecision()`
+
+### ToolRegistry (`core/src/tools/tool-registry.ts`)
+
+- Registers tools via `registerTool()`
+- MCP tools with fully qualified names: `mcp_serverName_toolName`
+- Priority sorting: built-in → discovered → MCP (by server name)
+- Filters by active status based on configuration
+
+### Confirmation System
+
+- `ToolCallConfirmationDetails` union: edit, execute, MCP, info, ask_user,
+  exit_plan_mode
+- `ToolConfirmationOutcome` enum: ProceedOnce, ProceedAlways, etc.
+- Async confirmation via MessageBus pub/sub
+
+## Hooks System
+
+### Hook Types (11 hook points)
+
+| Hook                  | Trigger                 | Key Capability                    |
+| --------------------- | ----------------------- | --------------------------------- |
+| `BeforeTool`          | Before tool execution   | Modify tool_input                 |
+| `AfterTool`           | After tool completion   | Context injection, tail calls     |
+| `BeforeAgent`         | Before agent prompt     | Additional context                |
+| `AfterAgent`          | After agent response    | Clear context flag                |
+| `BeforeModel`         | Before LLM request      | Modify request or inject response |
+| `AfterModel`          | After LLM response      | Modify response                   |
+| `BeforeToolSelection` | Before tool selection   | Modify toolConfig                 |
+| `Notification`        | When notifications fire | Suppress/modify message           |
+| `SessionStart`        | Session begins          | Additional context                |
+| `SessionEnd`          | Session terminates      | Cleanup                           |
+| `PreCompress`         | Before compression      | Suppress/modify                   |
+
+### Hook Output Fields (common to all hooks)
+
+- `continue` - Whether execution proceeds
+- `stopReason` - Reason to halt
+- `suppressOutput` - Hide from user
+- `systemMessage` - Add to system context
+- `decision` - ask/block/deny/approve/allow
+
+### Hook System Components
+
+- `HookSystem` - Main coordinator
+- `HookRegistry` - Stores/manages configurations
+- `HookRunner` - Executes registered hooks
+- `HookAggregator` - Combines multiple hook results
+- `HookPlanner` - Determines execution order
+- `HookEventHandler` - Orchestrates event firing
+- `HookTranslator` - Converts between formats
+
+## Policy Engine
+
+### Rule Structure
+
+```
+PolicyRule {
+  toolName: string;        // wildcards supported
+  decision: PolicyDecision; // ALLOW | DENY | ASK_USER
+  priority: number;
+  argsPattern?: RegExp;    // conditional on args
+  mcpName?: string;
+  source: string;
+}
+```
+
+### Tier Hierarchy (lowest → highest priority)
+
+1. Default (1) - Core built-in policies
+2. Extension (2) - Extension contributions
+3. Workspace (3) - Project-scoped (.gemini/)
+4. User (4) - User-provided (~/.gemini/)
+5. Admin (5) - System-level policies
+
+### Dynamic Rule Priorities (within User Tier)
+
+- 4.9 - MCP_EXCLUDED (persistent server blocks)
+- 4.4 - EXCLUDE_TOOLS_FLAG (CLI exclusions)
+- 4.3 - ALLOWED_TOOLS_FLAG (CLI allows)
+- 4.2 - TRUSTED_MCP_SERVER
+- 4.1 - ALLOWED_MCP_SERVER
+- 3.95 - ALWAYS_ALLOW (interactive selections)
+
+### Security Constraint
+
+- Extensions CANNOT contribute ALLOW rules or YOLO mode
+
+## Agent System
+
+### Agent Registry (`core/src/agents/registry.ts`)
+
+Discovery sources:
+
+1. Built-in: CodebaseInvestigator, CliHelp, Generalist, Browser
+2. User-level: `~/.gemini/agents/`
+3. Project-level: `.gemini/agents/` (requires folder trust)
+4. Extension-based: From active extensions
+
+### LocalAgentExecutor (`core/src/agents/local-executor.ts`)
+
+- Prompt processing: input augmentation → template expansion → system prompt
+  construction
+- Uses GeminiChat for accumulating conversation
+- ChatCompressionService for history management
+- Turn loop: invoke model → extract function calls → check auth → append results
+- Termination: complete_task tool, max turns, timeout
+
+### SubagentTool (`core/src/agents/subagent-tool.ts`)
+
+- Extends BaseDeclarativeTool - agents invoked like standard tools
+- Read-only status checking, user hint propagation
+- Execution: validate → optional confirmation → parameter enrichment →
+  SubagentToolWrapper
+
+### Remote Agents
+
+- A2A client manager for agent-to-agent protocol
+- Remote invocation for external agents
+- Agent acknowledgement system (security for project agents)
+
+## Model System
+
+### ModelConfigService
+
+- **Hierarchical alias system**: children override parents
+- Resolution: alias chain → level assignment → apply overrides
+- Deep merging with array override capability
+- Fallback to `chat-base` alias for unknown models
+
+### ModelRouterService
+
+Sequential strategy pattern:
+
+1. Fallback & Override
+2. Approval Mode Strategy
+3. Gemma Classifier (if enabled)
+4. Generic Classifier
+5. Numerical Classifier
+6. Default Strategy
+
+### ModelAvailabilityService
+
+Health states:
+
+- **Terminal** - permanently unavailable
+- **Sticky Retry** - failed once, can retry once per turn
+- **Healthy** - no issues
+
+## Services
+
+| Service                     | Purpose                                 |
+| --------------------------- | --------------------------------------- |
+| ChatRecordingService        | Session persistence (JSON files)        |
+| ChatCompressionService      | History summarization for token budgets |
+| ModelConfigService          | Hierarchical model config with aliases  |
+| ModelAvailabilityService    | Model health tracking                   |
+| ModelRouterService          | Model selection via strategies          |
+| FolderTrustDiscoveryService | Workspace security scanning             |
+| KeychainService             | Credential storage                      |
+| LoopDetectionService        | Detect repetitive agent loops           |
+
+## UI + Core Separation
+
+### IDE Client (`core/src/ide/ide-client.ts`)
+
+- Singleton managing CLI ↔ IDE communication via MCP
+- **Outbound** (CLI → IDE): `openDiff`, `closeDiff`
+- **Inbound** (IDE → CLI): `ide/contextUpdate`, `ide/diffAccepted`,
+  `ide/diffRejected`
+
+### Event Contract
+
+```typescript
+interface IdeContextNotification {
+  method: 'ide/contextUpdate';
+  params: { workspaceState: { openFiles: string[]; isTrusted: boolean } };
+}
+```
+
+### Confirmation Bus
+
+- `TOOL_CONFIRMATION_REQUEST` / `TOOL_CONFIRMATION_RESPONSE`
+- Detail types: edit, execute, MCP, info, ask_user, exit_plan_mode
+- Async pub/sub via MessageBus
+
+## Configuration (`core/src/config/config.ts` ~95KB!)
+
+- Tool config: core tools, allowed/excluded, MCP servers
+- File filtering: git ignore, fuzzy search, max counts, timeouts
+- Approval modes: policy engine config
+- Experiments: feature flags (GEMINI_3_1_PRO_LAUNCHED, ENABLE_ADMIN_CONTROLS,
+  etc.)
+- FolderTrust: discovery scans for commands, skills, settings, MCP, hooks

docs/adk-replat/NOTES-key-systems-deep-dive.md

@@ -0,0 +1,296 @@
+# Deep Dive: Key Gemini-CLI Systems
+
+## Hooks System (Complete)
+
+### 11 Hook Points
+
+| Hook                | Input                                  | Key Output Capabilities                       |
+| ------------------- | -------------------------------------- | --------------------------------------------- |
+| BeforeTool          | toolName, toolInput, mcpContext        | Modify tool_input, block/allow, systemMessage |
+| AfterTool           | toolName, toolInput, toolResponse      | additionalContext, tailToolCallRequest        |
+| BeforeAgent         | prompt                                 | Additional context                            |
+| AfterAgent          | prompt, response, stopHookActive       | Clear context                                 |
+| BeforeModel         | llmRequest (GenerateContentParameters) | Modify llm_request OR inject llm_response     |
+| AfterModel          | llmRequest, llmResponse                | Modify llm_response                           |
+| BeforeToolSelection | llmRequest                             | Modify toolConfig (function list, mode)       |
+| Notification        | type, message, details                 | Suppress/modify                               |
+| SessionStart        | source (Startup/Resume/Clear)          | Additional context                            |
+| SessionEnd          | reason (Exit/Clear/Logout/etc)         | Cleanup                                       |
+| PreCompress         | trigger (Manual/Auto)                  | Suppress/modify                               |
+
+### Hook Configuration Types
+
+- **Runtime hooks** (HookType.Runtime): JS/TS functions, registered
+  programmatically
+- **Command hooks** (HookType.Command): External shell commands with JSON I/O
+
+### Exit Code Semantics (Command Hooks)
+
+- 0 = Success (allowed with system message)
+- 1 = Non-blocking error (warning, continues)
+- 2+ = Blocking failure (denied, stderr as reason)
+
+### Hook Decision Values
+
+`'ask' | 'block' | 'deny' | 'approve' | 'allow' | undefined`
+
+### Execution Strategies
+
+- **Parallel** (default): Promise.all(), independent
+- **Sequential** (opt-in per hook): Chained, output→input cascading
+
+### Aggregation
+
+- Blocking decisions: OR logic (any block → all block)
+- Field replacement: later overrides earlier
+- Tool selection: union of allowed functions, mode precedence NONE > ANY > AUTO
+
+### Trust Model
+
+- Project hooks require folder trust verification
+- TrustedHooksManager at `~/.gemini/trusted-hooks.json`
+- Environment sanitized for command hooks (sensitive vars removed)
+- `GEMINI_PROJECT_DIR` injected
+
+### Key Insight for Abstraction
+
+Hooks fire inside gemini-cli's execution loop. When ADK controls the model:
+
+- BeforeModel/AfterModel still fire because AdkGeminiModel wraps GeminiChat
+- BeforeTool/AfterTool still fire because AdkToolAdapter wraps DeclarativeTool
+- This is dewitt's solution: adapters preserve hook injection points
+
+**For OpenRouter or opaque agents, hooks CANNOT fire unless the agent delegates
+model/tool calls back to gemini-cli.**
+
+---
+
+## Policy Engine (Complete)
+
+### TOML Rule Format
+
+```toml
+[[rules]]
+decision = "allow" | "deny" | "ask_user"
+priority = 0-999
+toolName = "tool_name"       # wildcards: *, mcp_*, mcp_server_*
+mcpName = "server_name"      # MCP server filter
+argsPattern = "regex"        # matches JSON-stringified args
+commandPrefix = "cmd"        # shell command prefix match
+commandRegex = "regex"       # shell command regex (mutually exclusive with prefix)
+modes = ["default", "autoEdit", "yolo", "plan"]
+annotations = ["read-only", "experimental"]
+allowRedirection = true      # for shell commands
+allowMessage = "..."         # user-facing message on allow
+denyMessage = "..."          # user-facing message on deny
+```
+
+### 5-Tier Priority System
+
+- Tier 5 (Admin): 5.000-5.999
+- Tier 4 (User): 4.000-4.999
+- Tier 3 (Workspace): 3.000-3.999
+- Tier 2 (Extension): 2.000-2.999
+- Tier 1 (Default): 1.000-1.999
+
+Formula: `tier + (priority / 1000)`
+
+### 4 Approval Modes
+
+1. **default** — ASK_USER decisions prompt user
+2. **autoEdit** — File writes auto-approved with safety checking (conseca)
+3. **yolo** — All auto-approved except explicit ask_user rules
+4. **plan** — Read-only, blocks modifications, allows planning docs
+
+### Shell Command Safety
+
+- Parses multi-command sequences (&&, ;, ||)
+- Detects injection: $(...), `...`, <(...), >(...), --flag=$(...)
+- Each subcommand evaluated independently
+- DENY overrides everything; ASK_USER escalates; ALLOW only if all pass
+- Redirections (>) downgrade ALLOW → ASK_USER unless allowRedirection=true
+
+### Security Constraints
+
+- Extensions cannot contribute ALLOW rules or YOLO mode
+- Regex patterns validated for ReDoS
+- Tool name typos detected via Levenshtein distance ≤3
+- Policy file integrity: SHA-256 hash checking
+
+### Key Insight for Abstraction
+
+Policy is evaluated at the tool execution boundary. For the interface layer:
+
+- If CLI controls tool execution → policy naturally applies
+- If agent controls tool execution internally → policy bypassed (danger!)
+- This reinforces the `pauseOnToolCalls: true` approach for ADK
+- Need a `PolicyEvaluator` interface that any executor can call
+
+---
+
+## Tool System (Complete)
+
+### Core Abstraction Chain
+
+```
+ToolBuilder (metadata + schema)
+  → build(params) validates → ToolInvocation (ready to execute)
+    → shouldConfirmExecute() → execute(signal) → ToolResult
+```
+
+### DeclarativeTool Pattern
+
+- `build(params)` — Validate and create invocation
+- `buildAndExecute(params)` — One-step convenience
+- `validateBuildAndExecute(params)` — Non-throwing variant
+
+### BaseToolInvocation
+
+- Message bus integration for policy decisions
+- Three decision paths: ALLOW → execute, DENY → reject, ASK_USER → confirm
+
+### ToolResult Structure
+
+- `llmContent` — For LLM conversation history
+- `returnDisplay` — For UI presentation
+- `displayContent` — Additional display formatting
+- `errorDetails` — Optional error info
+- `result` — Structured data payload
+- `tailCall` — Optional chaining requests
+
+### Confirmation System (6 types)
+
+1. **edit** — File modification with diff
+2. **execute** — Command execution
+3. **mcp** — MCP tool with allowlist mgmt
+4. **info** — Information-only
+5. **ask_user** — General user approval
+6. **exit_plan_mode** — Plan exit notification
+
+### Confirmation Outcomes (7 values)
+
+ProceedOnce, ProceedAlways, ProceedAlwaysAndSave, ProceedAlwaysServer,
+ProceedAlwaysTool, ModifyWithEditor, Cancel
+
+### Tool Kinds
+
+- **Mutator**: Edit, Delete, Move, Execute
+- **Read-Only**: Read, Search, Fetch
+- **Other**: Think, Agent, Communicate, Plan, SwitchMode, Other
+
+### MCP Tools
+
+- Naming: `mcp_<server>_<toolname>` (64-char limit)
+- Schema validation via LenientJsonSchemaValidator
+- Response types: McpTextBlock, McpMediaBlock, McpResourceBlock,
+  McpResourceLinkBlock
+- Transform to GenAI Parts format
+
+### Error Types (20+)
+
+- **Recoverable**: INVALID_TOOL_PARAMS, FILE_NOT_FOUND,
+  EDIT_NO_OCCURRENCE_FOUND, SHELL_TIMEOUT, MCP_TOOL_ERROR...
+- **Fatal**: NO_SPACE_LEFT (only one!)
+
+### ModifiableTool
+
+- Extends DeclarativeTool with external editor support
+- `getModifyContext()` → temp files → editor opens → `getUpdatedParams()` → diff
+
+---
+
+## Execution Loop (Complete)
+
+### LocalAgentExecutor Flow
+
+1. Collect user hints, setup deadline timer
+2. **Turn loop**: executeTurn() repeatedly until completion
+3. Per-turn: compress chat → callModel() → processFunctionCalls()
+4. On limit hit: executeFinalWarningTurn() with 60s grace period
+5. Return OutputObject { result, terminate_reason }
+
+### AgentTerminateMode
+
+GOAL | TIMEOUT | MAX_TURNS | ABORTED | ERROR | ERROR_NO_COMPLETE_TASK_CALL
+
+### SubagentTool Architecture
+
+```
+Parent Agent
+  └─ SubagentTool (wraps AgentDefinition as DeclarativeTool)
+       └─ SubagentToolWrapper (routes by agent kind)
+            ├─ LocalSubagentInvocation → LocalAgentExecutor
+            ├─ RemoteAgentInvocation → A2AClientManager
+            └─ BrowserAgentInvocation
+```
+
+### Agent Types
+
+- `LocalAgentDefinition` — kind: 'local', has promptConfig, modelConfig,
+  runConfig, toolConfig
+- `RemoteAgentDefinition` — kind: 'remote', has agentCardUrl, auth config
+
+### Key Defaults
+
+- DEFAULT_MAX_TURNS = 15
+- DEFAULT_MAX_TIME_MINUTES = 5
+- A2A_TIMEOUT = 1800000 (30 min for remote agents)
+
+---
+
+## Services/Config (Complete)
+
+### ModelConfigService
+
+- **Alias chains**: Inheritance with `extends`, merged root-to-leaf
+- **Overrides**: Contextual (model, scope, retry, isChatModel), sorted by
+  specificity
+- **Runtime registration**: Dynamic aliases and overrides
+- **Deep merge**: Objects merged, arrays replaced entirely
+
+### ModelRouterService (Strategy Chain)
+
+1. Fallback & Override → 2. Approval Mode → 3. Gemma Classifier → 4. Generic
+   Classifier → 5. Numerical Classifier → 6. Default
+
+### ModelAvailabilityService
+
+- Terminal (permanent), Sticky_retry (one retry per turn), Healthy
+- `selectFirstAvailable()` iterates fallback chain
+- `resetTurn()` at turn boundaries enables fresh retries
+
+### Config (~95KB!)
+
+Central dependency injection. Initializes: ModelAvailabilityService →
+ModelConfigService → FolderTrustDiscoveryService → PolicyEngine →
+FileDiscoveryService → GitService → ToolRegistry → MCP → GeminiClient →
+HookSystem
+
+### CoreEventEmitter (UI Events)
+
+Event types: UserFeedback, ModelChanged, ConsoleLog, Output, RetryAttempt,
+ConsentRequest, McpProgress, Hook, QuotaChanged
+
+Backlog buffering (max 10,000) with head-pointer eviction and auto-compaction.
+
+### Scheduler Types
+
+```typescript
+ToolCallRequestInfo {
+  callId, name, args, originalRequestName,
+  isClientInitiated, prompt_id, checkpoint, traceId,
+  parentCallId, schedulerId
+}
+ToolCallResponseInfo {
+  callId, responseParts, resultDisplay, error, errorType,
+  outputFile, contentLength, data
+}
+CoreToolCallStatus: Validating → AwaitingApproval → Scheduled → Executing → Success|Error|Cancelled
+```
+
+### FolderTrust
+
+Scans: commands (.toml), skills (SKILL.md), settings.json, MCP servers, hooks
+Security warnings: auto-approved tools, autonomous agents, disabled trust,
+disabled sandbox Pattern: discovery → review → execution (no code runs during
+scan)

docs/adk-replat/PRIORITY-ANALYSIS.md

@@ -0,0 +1,349 @@
+# Interface Priority Analysis & Open Questions
+
+## The Big Picture
+
+We're defining **framework-agnostic interfaces** that allow gemini-cli to:
+
+1. Keep its existing execution loop working unchanged (Legacy path)
+2. Swap in ADK as an alternative runtime via config flag
+3. Eventually support OpenRouter or other agent backends
+4. Maintain all existing CLI behavior: hooks, policies, confirmations, UI events
+
+## Proposed Interface Layers (Priority Order)
+
+---
+
+### P0 (Critical Path - Must Define First)
+
+#### 1. AgentEvent / Event Stream Contract
+
+**Why first:** Everything else consumes or produces these events. The UI renders
+them. The hooks intercept them. The adapters translate to/from them.
+
+**Key decision:** Merge Dewitt's simpler model with Coworker's richer model?
+
+**Recommendation:** Coworker's approach is more complete. Key additions:
+
+- `threadId` for sub-agent tracking (AG-UI has `parentRunId`)
+- `tool_update` for progress on long-running tools
+- `elicitation_request/response` as first-class (not just tool_confirmation)
+- `usage` event for token tracking
+- `_meta` escape hatch (matches AG-UI's extensibility philosophy)
+- `initialize` event (matches AG-UI's RunStarted)
+
+**Open questions:**
+
+- Do we need AG-UI's start/content/end triple pattern for streaming? Or is
+  yielding partial events sufficient?
+- How do ContentPart types map to existing gemini-cli Part types?
+- Should events carry a `source` field? (useful for hook attribution)
+
+#### 2. Agent Interface
+
+**Why second:** This is the primary abstraction that LocalAgentExecutor, ADK
+adapters, and future OpenRouter adapters all implement.
+
+**Key decision:** Dewitt's `runAsync/runEphemeral` vs Coworker's
+`send(Trajectory|string)`
+
+**Recommendation:** Hybrid approach:
+
+- Dewitt's `runAsync/runEphemeral` split is ADK-aligned and cleaner for the
+  factory pattern
+- BUT add Coworker's elicitation support via AgentSend union type
+- The Trajectory concept is powerful but may be too opinionated for Phase 2
+
+```
+Agent<TInput, TOutput>
+  name: string
+  description: string
+  runAsync(input, options) → AsyncGenerator<AgentEvent, TOutput>
+  runEphemeral(input, options) → AsyncGenerator<AgentEvent, TOutput>
+```
+
+**Open questions:**
+
+- Should Agent also support `send()` for mid-stream interactions (elicitations)?
+- How does AbortSignal propagate through the adapter boundary?
+- Do we need a `capabilities` field (supports elicitation? supports HITL? etc.)?
+
+#### 3. Tool Execution Contract
+
+**Why third:** Tools are the primary action mechanism. Both the policy engine
+and hooks system wrap tool execution.
+
+**What needs abstracting:**
+
+- Tool declaration (name, schema) — already somewhat generic via JSON Schema
+- Tool execution (args → result)
+- Tool confirmation flow (ASK_USER → user decision → proceed/deny)
+- Tool result shape (llmContent + displayContent + error + tailCalls)
+
+**Key decision:** Keep DeclarativeTool pattern or flatten to a simpler
+interface?
+
+**Recommendation:** Define a minimal `ToolExecutor` interface:
+
+```
+ToolExecutor {
+  name: string
+  description: string
+  schema: JSONSchema
+  execute(args, context): Promise<ToolResult>
+  requiresConfirmation?(args, context): Promise<boolean>
+}
+```
+
+DeclarativeTool remains the concrete implementation. ADK's BaseTool adapts to
+this.
+
+**Open questions:**
+
+- How do MCP tools fit? They already have their own protocol.
+- Tool annotations (destructive hints) — should these be in the interface?
+- Long-running tools need progress reporting — how does this interact with
+  tool_update events?
+
+---
+
+### P1 (Important - Define After P0)
+
+#### 4. Policy / Permission Interface
+
+**Why important:** Every tool call goes through policy. External agents need
+policy enforcement too.
+
+**Current state:** gemini-cli has a sophisticated TOML-based policy engine with
+tiered priorities. ADK-TS has a simpler SecurityPlugin with PolicyOutcome
+(DENY/CONFIRM/ALLOW).
+
+**What needs abstracting:**
+
+```
+PolicyEngine {
+  evaluate(toolName, args, context): PolicyDecision  // ALLOW | DENY | ASK_USER
+  getExcludedTools(): string[]  // Tools statically denied
+}
+```
+
+**Key decision:** Do external agents (OpenRouter, etc.) get the same policy
+enforcement?
+
+**Open questions:**
+
+- If an ADK agent calls a tool internally, does gemini-cli's policy apply?
+- With `pauseOnToolCalls: true` in ADK, the CLI controls execution — but what
+  about headless mode?
+- How do agent-level policies work? (allow/deny entire agents, not just tools)
+- Should policy be a middleware (AG-UI pattern) or a callback (ADK plugin
+  pattern)?
+
+#### 5. Hooks Interface
+
+**Why important:** Hooks are a major gemini-cli feature. They need to work
+regardless of which agent backend runs.
+
+**Current state:** 11 hook types firing at specific lifecycle points.
+
+**What needs abstracting:**
+
+- Hook lifecycle must be backend-agnostic
+- BeforeModel/AfterModel hooks need to work even when ADK controls the model
+- BeforeTool/AfterTool hooks need to intercept regardless of who executes the
+  tool
+
+**Key challenge:** When ADK runs the model internally, gemini-cli hooks can't
+easily intercept. **Dewitt's solution:** ADK uses gemini-cli's model via
+AdkGeminiModel adapter — hooks fire inside GeminiChat.
+
+**Open questions:**
+
+- If OpenRouter runs the model, how do BeforeModel/AfterModel hooks work?
+- Do we need a "model steering" abstraction (injecting context mid-stream)?
+- Can hooks be expressed as AG-UI middleware? (intercept event stream)
+
+#### 6. Model / LLM Interface
+
+**Why important:** Model abstraction enables swapping LLM providers.
+
+**Dewitt's approach:** Exposes Model interface, ADK uses it via AdkGeminiModel
+adapter. **Coworker's approach:** Model is internal to Agent (no separate Model
+interface).
+
+**Recommendation:** Keep Dewitt's separate Model interface BUT make it
+provider-agnostic:
+
+- Remove `@google/genai` types from the interface signature
+- Define generic Message/Content types
+- Model interface is an implementation detail, not part of the Agent contract
+
+**Open questions:**
+
+- Can we define a truly provider-agnostic Model interface?
+- Or is the Model always tied to the agent backend? (ADK uses Gemini, OpenRouter
+  uses whatever)
+- Model routing (choosing which model) — is this a concern of the Model
+  interface or a separate service?
+
+---
+
+### P2 (Important but Can Follow)
+
+#### 7. Session / State Interface
+
+**Current state:** gemini-cli uses ChatRecordingService (JSON files). ADK uses
+Session with BaseSessionService.
+
+**What needs abstracting:**
+
+- Session creation/retrieval
+- State persistence across turns
+- History/trajectory management
+
+**Open questions:**
+
+- Does the trajectory (coworker's concept) replace gemini-cli's chat recording?
+- Should session state be shared between gemini-cli and the agent backend?
+
+#### 8. Elicitation / User Interaction Interface
+
+**What it covers:** Model fallback dialogs, tool confirmations, Ctrl+B
+interrupts, user questions
+
+**Current state:** gemini-cli uses ConfirmationBus + MessageBus. AG-UI uses
+frontend tools.
+
+**Open questions:**
+
+- Is elicitation just a special case of tool calls (AG-UI approach)?
+- Or is it a first-class event type (coworker's approach)?
+- How does Ctrl+B (cancel/interrupt) propagate through the agent boundary?
+
+#### 9. Configuration / Capability Discovery
+
+**What it covers:** Feature flags, experiment settings, agent capabilities
+
+**Open questions:**
+
+- How does an external agent declare its capabilities?
+- Does OpenRouter support HITL? Elicitation? Tool confirmation? Each agent may
+  differ.
+- Need a `capabilities` negotiation at connection time?
+
+---
+
+### P3 (Future / Can Defer)
+
+#### 10. A2UI / Rich UI Interface
+
+- Declarative UI generation from agents
+- Not critical for Phase 2 but important for differentiation
+
+#### 11. Memory / Artifact Interface
+
+- ADK has memory/artifact services
+- gemini-cli has ChatRecordingService + memory tools
+- Can standardize later
+
+#### 12. Telemetry / Observability Interface
+
+- Both systems have telemetry
+- Can standardize later
+
+---
+
+## Critical Open Questions (Need Team Discussion)
+
+### 1. OpenRouter Integration Model
+
+**Question:** When OpenRouter (or any external agent) is used, what does the
+integration look like?
+
+**Option A: Full Agent Interface** — OpenRouter implements the Agent interface
+directly
+
+- Pro: Clean, uniform
+- Con: OpenRouter doesn't support HITL, hooks, policies natively
+
+**Option B: ACP Shim** — Agent Communication Protocol between CLI and external
+agents
+
+- Pro: Standards-based
+- Con: Additional protocol layer, may be premature
+
+**Option C: Model-only Integration** — OpenRouter is just an alternative Model,
+not Agent
+
+- Pro: Simpler, leverages existing agent loop
+- Con: Doesn't support OpenRouter-specific features
+
+**Recommendation:** Start with Option C (model-only). OpenRouter provides an LLM
+endpoint. Gemini-cli's own agent loop handles tools, policies, hooks. This means
+defining a provider-agnostic Model interface is the key enabler.
+
+### 2. Tool Execution: Client-side vs Agent-side
+
+**Question:** Who executes tools — the CLI or the agent backend?
+
+**Option A: Always client-side** (CLI executes, agent suspends)
+
+- ADK: `pauseOnToolCalls: true`
+- Pro: CLI maintains control, policies enforced, hooks fire
+- Con: Higher latency, more round-trips
+
+**Option B: Agent-side execution** (agent runs tools internally)
+
+- Pro: Faster, simpler
+- Con: Bypasses CLI policies, hooks, confirmations
+
+**Option C: Configurable** — CLI decides per-tool or per-agent
+
+- Pro: Flexible
+- Con: Complex
+
+**Recommendation:** Option A for safety-critical CLI use case. Option B only for
+trusted/sandboxed sub-agents.
+
+### 3. Model Steering (Hooks that inject context mid-stream)
+
+**Question:** How do user-local hooks (like injecting project context) work with
+external agents?
+
+**Answer:** They can only work if:
+
+- The CLI controls the model (via Model interface adapter) — then BeforeModel
+  hook injects context
+- OR the agent supports a "system instruction update" mechanism
+
+For OpenRouter: model steering works because CLI controls the model call. For
+ADK: model steering works because AdkGeminiModel wraps GeminiChat. For fully
+opaque agents: model steering **cannot work** — this is a known limitation.
+
+### 4. Elicitation Flow
+
+**Question:** When the agent needs user input (model fallback, clarification),
+how does it work?
+
+**For CLI-controlled agents:** Agent yields an elicitation_request event → CLI
+renders prompt → user responds → CLI sends response back via session.stream({
+kind: 'elicitation_response', ... }) to resume
+
+**For external agents:** Agent uses A2A protocol or similar to send elicitation
+→ CLI bridges the request to user → response sent back via protocol
+
+**Key insight:** Elicitation is fundamentally about the agent SUSPENDING and
+waiting for user input. ADK already supports this via `pauseOnToolCalls`. Can we
+generalize to `pauseOnElicitation`?
+
+### 5. Sub-agent Identity and Policies
+
+**Question:** When a sub-agent spawns, does it inherit parent policies? Get its
+own?
+
+**Current gemini-cli behavior:** Sub-agents registered as tools, go through same
+policy engine. **ADK behavior:** Sub-agents are child nodes in agent tree, get
+parent's plugins.
+
+**Recommendation:** Sub-agents inherit parent policy context. Additional
+restrictions can be layered (e.g., sub-agent X cannot use shell tool). This is
+already how gemini-cli works.

docs/adk-replat/adk_migration_design_doc.md

@@ -0,0 +1,438 @@
+# 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/unified-review.md

@@ -0,0 +1,554 @@
+# Unified ADK CLI Design Review
+
+Date: 2026-04-06
+
+> **Rollout:** All ADK migration work is feature-gated behind `experimental.adk` flags. No behavioral changes ship without an explicit opt-in. This applies to both non-interactive and interactive flows.
+
+Inputs merged:
+- `claude-adk-cli-design-review.md` (adversarial code-level review)
+- `codex-adk-cli-design-review.md`
+- Follow-up review discussion on subagent architecture, session semantics, and `BaseContextCompactor`
+
+Scope reviewed:
+- `gemini-cli/docs/adk-replat/adk_migration_design_doc.md`
+- `gemini-cli` `AgentProtocol` / `AgentSession` / interactive migration work
+- `adk-js` runner / session / tool / security / model architecture
+- PR context for interactive migration, including `google-gemini/gemini-cli#24297`
+
+## Executive Summary
+
+The design is directionally sound and the migration goal is correct. However, the document is not yet principal-review ready due to:
+
+1. **Four non-compilable code samples** (C1-C4) that will immediately erode reviewer confidence
+2. **An under-specified translation boundary** — the ADK→AgentProtocol mapping is the real architecture, but the doc treats it as an afterthought
+3. **Overclaimed parity** in routing, telemetry, and approvals
+4. **Missing phased plan** with clear milestones and non-goals
+
+The central architectural insight is right: the migration boundary is:
+
+- `adk-js Event -> Gemini CLI AgentEvent`
+- `adk-js session/runtime semantics -> AgentProtocol / AgentSession semantics`
+
+That boundary carries stream lifecycle, replay/resume, event projection, approval correlation, and persistence correctness. Until the translation architecture is explicit, parity claims remain unsupported.
+
+## Compilation Blockers (Must Fix First)
+
+These are binary errors — the code samples in the design doc will not compile against current ADK types.
+
+### C1. `LlmRequest` has no `headers` field
+
+`adk-js/core/src/models/llm_request.ts` defines: `model?`, `contents`, `config?`, `liveConnectConfig`, `toolsDict`. The design doc's `request.headers = {...}` will silently fail or not compile. **Fix:** use `llmRequest.config.httpOptions.headers` or pass headers at `Gemini` constructor time.
+
+### C2. `BaseLlm.connect()` is abstract and unimplemented
+
+`adk-js/core/src/models/base_llm.ts:67-78` has TWO abstract methods: `generateContentAsync` and `connect()`. `GcliAgentModel` must implement both. **Fix:** add `connect()` — stub with `throw new Error('not supported')` if live connections are out of scope.
+
+### C3. `BaseToolset` constructor signature is wrong
+
+`adk-js/core/src/tools/base_toolset.ts:46-49`: `constructor(readonly toolFilter: ToolPredicate | string[], readonly prefix?: string)`. The design doc's `super([])` passes an empty array as `toolFilter`, which makes `isToolSelected` return false for all tools — a silent bug. Also `close()` is abstract and must be implemented. **Fix:** match the actual signature.
+
+### C4. `FunctionalTool` does not exist
+
+The design doc references `FunctionalTool` for subagent wrapping. This class does not exist in adk-js. The correct classes are `FunctionTool` (wraps a plain function) and `AgentTool` (wraps an agent with isolated runner). See subagent architecture section below for the recommended approach.
+
+---
+
+## High-Risk Findings
+
+### 1. The actual migration boundary is under-specified
+
+Current `AgentProtocol` requires `send()` timing guarantees, replay/reattach semantics, `streamId`, and optional `threadId` for subagent threads in `gemini-cli/packages/core/src/agent/types.ts` and `gemini-cli/packages/core/src/agent/agent-session.ts`.
+
+ADK emits a different event model in `adk-js/core/src/events/event.ts`.
+
+The doc needs a first-class architecture section for:
+- `AdkSessionRuntime`
+- `AdkEventTranslator`
+- event buffering / replay
+- `threadId` mapping
+- `tool_update` mapping
+- `agent_start` / `agent_end` ownership
+
+Without that, the rest of the design sits on an unstated core contract.
+
+### 2. The consolidated decorator needs two concerns extracted
+
+The `GcliAgentModel.generateContentAsync` pipeline is a reasonable orchestrator pattern — each concern is a separate injected service call, not a monolithic class. However, two concerns don't belong in the model layer:
+
+- **Quota/availability prompting** — involves interactive UI suspension, not request mutation. Should use `beforeModelCallback` on `LlmAgent`.
+- **Policy/approval control flow** — involves blocking for user input. Should use `beforeToolCallback` or the `ApprovalBridge` (see architecture section).
+
+The remaining concerns (auth header injection, routing/model rewrite, compaction, masking) are legitimate request-preprocessing and can stay in the model pipeline.
+
+### 3. The design frequently conflates “possible with custom logic” with “supported by current ADK architecture”
+
+This is one of the main wording risks.
+
+Several statements currently read like native ADK parity when the real meaning is:
+- possible with substantial Gemini CLI-owned bridge logic
+- possible by bypassing native ADK facilities
+- possible only for phase 1 with intentionally degraded semantics
+
+That distinction needs to be explicit everywhere the doc uses strong language like “validated” or “100% possible today.”
+
+### 4. Auth architecture is deeper than header injection — Coast Assist requires a custom transport
+
+The auth section has two distinct problems:
+
+**Problem A: API surface mismatch (C1).** `LlmRequest` has no `headers` field. Per-request headers are possible via `llmRequest.config.httpOptions.headers`, and `Gemini` constructor accepts a `headers` param (`google_llm.ts:57,79`). This is fixable.
+
+**Problem B: Coast Assist / `LOGIN_WITH_GOOGLE` uses a different backend entirely.** The current `CodeAssistServer` (`packages/core/src/code_assist/server.ts:407`) does NOT call the standard Gemini API. It uses `google-auth-library`'s `AuthClient.request()` to talk to a Code Assist backend endpoint. The OAuth flow (`packages/core/src/code_assist/oauth2.ts`) handles browser launch (L305), local callback server (L492-615), token exchange (L546-550), credential caching (L739-750), and automatic token refresh via `OAuth2Client`.
+
+This means `GcliAgentModel` cannot wrap a standard `Gemini` BaseLlm and just inject headers. For Coast Assist auth, `GcliAgentModel` must **extend `BaseLlm` directly** and implement its own HTTP transport using `AuthClient.request()`, translating between `LlmRequest`/`LlmResponse` and the Code Assist protocol.
+
+What works:
+- The OAuth dance itself (browser launch, token caching, refresh) runs before the agent session starts — no blocking inside `generateContentAsync`
+- `OAuth2Client.getAccessToken()` handles mid-session token refresh transparently
+- Per-request header injection works for API-key-based auth via `httpOptions.headers`
+
+What the design doc must change:
+- Stop assuming `Gemini` as the inner model — `GcliAgentModel extends BaseLlm` directly
+- Define two transport paths: standard Gemini API (API key) and Code Assist backend (OAuth)
+- The dummy-key workaround is irrelevant for Coast Assist — you never call `GoogleGenAI.models.generateContent`
+
+### 5. Approval / elicitation bridging is acceptable only as a temporary non-native bridge
+
+The design’s callback-based approval approach is pragmatic for phase 1, but it bypasses native ADK confirmation semantics.
+
+`adk-js/core/src/plugins/security_plugin.ts` and `adk-js/core/src/agents/processors/request_confirmation_llm_request_processor.ts` show that ADK’s model is:
+- `ALLOW | DENY | CONFIRM`
+- persisted confirmation state
+- later resumption from history
+
+Blocking in callbacks may be acceptable for the first rollout, but the doc must say clearly:
+- local-only bridge
+- not resumable across process death
+- not long-term SDK behavior
+- intentionally non-native pending future elicitation/bidi work
+
+### 6. Rewind is deeper than file truncation
+
+The doc treats rewind as storage truncation. The storage part is straightforward — `GcliFileSessionService` wraps the existing `ChatRecordingService` and implements 4 abstract methods (`createSession`, `getSession`, `listSessions`, `deleteSession`). DB-level concerns (locking, stale-writer detection, `PESSIMISTIC_WRITE`) do not apply to a single-user CLI.
+
+However, rewind itself is not just storage:
+- `adk-js/core/src/agents/processors/request_confirmation_llm_request_processor.ts` scans event history to reconstruct pending confirmations and resume tool execution
+- `adk-js/core/src/runner/runner.ts:447` has a TODO acknowledging the event log is used as a transaction log
+- Truncating events without rolling back derived state (pending confirmations, app/user state prefixes) will break resumption
+
+The doc should define rewind as: event-log truncation + session state recomputation + confirmation/auth state rollback.
+
+Note: `BaseSessionService.appendEvent` handles state merging with `app:`, `user:`, `temp:` prefixed keys automatically — this is inherited for free.
+
+### 7. Routing, telemetry, and plan mode are all overclaimed
+
+Routing:
+- current routing requires a richer `RoutingContext`
+- `contents.slice(0, -1)` / `contents.pop()` is not a sufficient or type-accurate mapping
+- model banning via simulated error is not the same as model routing
+
+Telemetry:
+- **The stream-interceptor approach in section 3.6 is wrong.** The correct mechanism is ADK's `BasePlugin` system.
+- `event.id` is not a safe per-tool correlation key — use `functionCall.id` via `beforeToolCallback`/`afterToolCallback`
+- ADK can batch multiple function calls or responses in one event — stream interception cannot distinguish them, but plugin hooks fire per-tool with distinct `functionCallId`
+- **Correction:** Token usage IS available on ADK events. `llm_agent.ts:831-834` spreads `LlmResponse` (including `usageMetadata`) into the event via `createEvent({...modelResponseEvent, ...llmResponse})`. Additionally, `afterModelCallback` receives the raw `LlmResponse` with `usageMetadata` directly — providing a second capture point.
+- HTTP-level metrics (status code, request duration) are NOT on ADK events — must be captured in the `GcliAgentModel` wrapper
+- The sample APIs in the design do not match the current `ClearcutLogger` taxonomy (~195 distinct metadata keys)
+
+**Recommended telemetry architecture:**
+
+| Metric Category | Capture Mechanism | ADK Hook |
+|---|---|---|
+| Token counts (input, output, cached, thinking) | `afterModelCallback` → `LlmResponse.usageMetadata` | `BasePlugin.afterModelCallback` |
+| Per-tool timing | Timer keyed on `functionCallId` | `BasePlugin.beforeToolCallback` / `afterToolCallback` |
+| Agent lifecycle | Start/end tracking | `BasePlugin.beforeAgentCallback` / `afterAgentCallback` |
+| Model errors | Error classification | `BasePlugin.onModelErrorCallback` |
+| HTTP status, API duration | Captured in model wrapper | `GcliAgentModel.generateContentAsync` |
+| Routing decisions, latency | Captured in model or beforeModelCallback | `beforeModelCallback` / model wrapper |
+| Context token breakdowns (system, tools, history) | Computed in request pipeline | Model wrapper |
+| Tool approval decisions | Injected from approval layer | `ApprovalBridge` |
+| Session config, compression, rewind, IDE, extensions, billing, slash commands, hooks, plan execution, onboarding | **Unchanged** — stays in current call sites | Existing gemini-cli code |
+
+~30% of Clearcut metrics map to ADK plugin hooks. ~70% remain in their current call sites unchanged.
+
+Plan mode:
+- current behavior is broader than prompt + tool filtering
+- policy, approval mode, routing, and config refresh are all part of the behavior
+
+### 8. Retry safety around side effects (note)
+
+The “full turn reset” proposal could duplicate side effects (file writes, shell commands, MCP mutations) if the turn already executed side-effecting tools before the stream failure. This is an ADK-wide concern, not specific to this migration. A brief note acknowledging this limitation is sufficient — a full retry safety taxonomy is out of scope for this design.
+
+### 9. Design ignores ADK's native `BaseContextCompactor`
+
+ADK already has a compaction extension point: `BaseContextCompactor` (`adk-js/core/src/context/base_context_compactor.ts`) with `shouldCompact(invocationContext)` + `compact(invocationContext)`. It's wired into the request processor pipeline via `ContextCompactorRequestProcessor` at `llm_agent.ts:407-420`.
+
+The design doc proposes running compaction inside `GcliAgentModel.generateContentAsync` instead. This works but bypasses the native slot. Recommendation: implement `BaseContextCompactor`, delegate to the existing `ChatCompressionService` internally. ADK provides the trigger point; your service provides the logic. Note that `BaseContextCompactor` returns void — failure states (COMPRESSED, NOOP, CONTENT_TRUNCATED, etc.) must be communicated via session state or custom events.
+
+### 10. Existing `isStructuredError` type-guard bug
+
+`gemini-cli/packages/core/src/agent/event-translator.ts:431-438`: `isStructuredError()` checks only `typeof error === 'object' && 'message' in error && typeof error.message === 'string'`. Since every `Error` instance has `message: string`, plain `Error` objects pass this guard. In `mapError` (lines 390-429), the structured branch runs before `instanceof Error`, so plain errors get incorrect HTTP→gRPC status mapping. This should be fixed before the translator becomes the long-term session boundary. **Fix:** add `'status' in error` to the guard, or check `instanceof Error` first.
+
+### 11. The review should distinguish architecture defects from rollout-status evidence
+
+The interactive PR findings matter:
+- stacked-branch dependency
+- hook-order risk in `#24297`
+- `_meta.legacyState` leakage into protocol events
+
+But they are secondary to the core design defect, which is the missing runtime/translation architecture.
+
+These findings should stay in the review, but as credibility and rollout-risk evidence rather than the centerpiece.
+
+## Recommended Architecture
+
+This is the cleanest merged recommendation from both reviews plus follow-up discussion.
+
+### Core principle
+
+Use one shared ADK-based execution/runtime core, then put different adapters on top of it.
+
+Do not make `AgentSession` the innermost engine.
+
+### Recommended split
+
+1. `AdkRuntimeCore`
+- owns the ADK runner loop
+- owns tool execution, policy integration, routing integration, masking, compaction hooks, and persistence hooks
+- emits runtime-level activity/events
+
+2. `TopLevelSessionAdapter`
+- exposes the runtime as `AgentProtocol` / `AgentSession`
+- owns replay, reattach, `streamId`, `threadId`, `agent_start` / `agent_end`, and top-level event projection
+
+3. `SubagentTools` (custom `BaseTool` implementations)
+- subagents invoke the same shared runtime core as the main agent
+- the only difference is the type mapping at the boundary (projecting child activity into parent-facing `tool_update` / `tool_response` or `threadId`-scoped events)
+- `AgentTool` is explicitly rejected — it creates a fully isolated runner/session, which conflicts with the shared-core goal
+- custom `BaseTool` wrappers allow subagents to share policy, routing, tool definitions, and config with the parent while keeping the door open for future resumability and richer state sharing
+
+4. `ApprovalBridge`
+- phase-1 callback bridge for approvals / elicitation using existing callbacks
+- clearly documented as temporary and non-native
+- eventual migration to full elicitation bidi format
+
+5. `GcliFileSessionService`
+- file-backed persistence wrapping existing `ChatRecordingService`
+- implements 4 abstract methods from `BaseSessionService`
+- inherits state-merging (app/user/temp prefixes) for free
+- single-writer model — concurrent runs per session are forbidden
+
+### Subagent architecture decision
+
+`AgentTool` is not the right abstraction for this migration. It creates an isolated runner with its own `InMemorySessionService`, meaning:
+- state is NOT shared with the parent
+- events are NOT projected into the parent stream
+- policy, routing, and config are NOT inherited
+
+The core requirement is that subagents use the same core loop functionality as the main agent — the only difference is how results are mapped back to the parent. Custom `BaseTool` implementations that invoke the shared `AdkRuntimeCore` achieve this. This also positions subagents for future complexity (resumability, richer state sharing, MCP-scoped tool sets) without fighting AgentTool's isolation model.
+
+### Session conclusion
+
+Main agent and subagents can share the same underlying runtime core.
+
+But they should not necessarily share the exact same public adapter.
+
+The right formulation is:
+- same core runtime
+- different event/session projections depending on embedding context
+
+## Section-by-Section Unified Review
+
+### 3.1 Authentication Flexibility
+
+Assessment: implementable, but the design doc’s approach is wrong for Coast Assist.
+
+Keep:
+- ADK `Gemini` does not natively accept the CLI’s auth shape
+
+Change:
+- `GcliAgentModel` must extend `BaseLlm` directly, not wrap `Gemini` — Coast Assist uses `AuthClient.request()` against a non-standard backend, not `GoogleGenAI`
+- fix `request.headers` to `llmRequest.config.httpOptions.headers` (C1)
+- define two transport paths: API-key (standard Gemini) and OAuth (Code Assist)
+- token refresh is transparent via `OAuth2Client` — this works as-is
+- browser-based OAuth runs before agent session starts — no blocking concern
+
+### 3.2 Model Steering and Mid-Stream Injection
+
+Assessment: next-turn steering is plausible now; true live interruption is still blocked.
+
+Required change:
+- split “next-step steering” from “true mid-turn interruption”
+- define temporary user-visible behavior until live input-stream support exists
+
+### 3.3 State Management and Token Compaction
+
+Assessment: plausible, but too wrapper-centric.
+
+Required change:
+- specify whether compaction operates on persisted history, outgoing request history, or both
+- define recursion guards and utility-call isolation
+- define artifact ownership across sessions and subagents
+
+### 3.4 Model Configuration and Hierarchical Overrides
+
+Assessment: under-specified.
+
+Required change:
+- model config resolution should remain request-scoped
+- preserve scoped overrides and retry-aware behavior
+- explain subagent and utility-call override behavior
+
+### 3.5 Universal Policy Enforcement
+
+Assessment: acceptable as a bridge, not as full parity.
+
+Required change:
+- explicitly document reduced phase-1 semantics
+- list policy inputs lost unless extra context plumbing is added
+- separate short-term callback bridge from long-term native confirmation flow
+
+### 3.6 Telemetry and Observability (Clearcut)
+
+Assessment: fully implementable, but the stream-interceptor approach must be replaced with a `BasePlugin`.
+
+Required change:
+- replace stream interception with `ClearcutTelemetryPlugin extends BasePlugin`
+- use `afterModelCallback` for token counts (`LlmResponse.usageMetadata` is available)
+- use `beforeToolCallback`/`afterToolCallback` with `functionCallId` for per-tool timing
+- capture HTTP-level metrics (status code, duration) in `GcliAgentModel` wrapper
+- ~70% of Clearcut metrics stay in their current call sites unchanged — document which
+- replace fake API examples with a telemetry parity matrix showing capture mechanism per metric
+
+### 3.7 Dynamic Model Routing and Configurability
+
+Assessment: partly feasible, materially overstated.
+
+Required change:
+- remove “100% possible today”
+- separate alias rewrite, fallback selection, classifier routing, and banning/rejection behavior
+- define a real `RoutingContextBuilder`
+
+### 3.8 Fallbacks and Availability Management
+
+Assessment: incomplete.
+
+Required change:
+- split preflight fallback from post-failure transition behavior
+- define retry safety
+- define main-call vs utility-call fallback ownership
+
+### 3.9 State-Driven Mode Switching
+
+Assessment: too narrow.
+
+Required change:
+- define a single mode state source of truth
+- enumerate all consumers: prompt, toolset, policy, router, UI
+
+### 3.10 Tool Output Masking
+
+Assessment: one of the stronger sections.
+
+Required change:
+- define whether masking mutates persisted history or only outgoing request history
+- define ordering and idempotence relative to compaction
+- define file/artifact lifecycle
+
+### 4. SDK Facade / Stateful Orchestration
+
+Assessment: this should become the architectural center of the document.
+
+Required change:
+- expand ownership boundaries
+- describe the shared runtime plus adapter model
+- document temporary approval/elicitation limitations explicitly
+
+### 4.1 Hybrid Tool Instantiation
+
+Assessment: directionally good.
+
+Required change:
+- include message bus derivation
+- include MCP discovery scoping
+- include recursion prevention and tool isolation details
+
+### 4.2 Custom File-Based Persistence
+
+Assessment: straightforward for storage, but rewind semantics need work.
+
+The storage layer itself is low-risk — `GcliFileSessionService` wraps existing `ChatRecordingService` and implements 4 abstract methods. DB concerns (locking, stale-writer, crash recovery) don't apply to a single-user CLI.
+
+Required change:
+- define rewind as event-log truncation + state recomputation (not just file truncation)
+- state that concurrent runs per session are forbidden (single-writer)
+- define how app/user/temp state prefixes map to existing workspace JSON
+
+### 4.3 Decomposing `AgentLoopContext`
+
+Assessment: right instinct, incomplete decomposition.
+
+Required change:
+- account for message bus / confirmation routing
+- account for injection queues
+- account for prompt/resource registries and MCP scoping
+
+### 5.1 Real-Time User Message Injections
+
+Assessment: blocker analysis is incomplete.
+
+Required change:
+- mention TS live runtime gaps directly
+- describe temporary UX until true interruption exists
+
+### 5.2 Conversation Rewind and State Reversal
+
+Assessment: too shallow today.
+
+Required change:
+- define rewind as event-log truncation plus state rollback semantics
+- define confirmation/auth rollback semantics
+- define artifact/version rollback expectations
+
+### 5.3 Concurrent Sessions
+
+Assessment: a single-user CLI does not need DB-level locking.
+
+Required change:
+- state that concurrent runs per session are forbidden (single-writer model)
+- this is sufficient for a CLI — no further locking design needed
+
+## Corrections to Earlier Reviews
+
+### Auth is implementable, not blocked
+API-key auth works via `httpOptions.headers`. Coast Assist / `LOGIN_WITH_GOOGLE` requires `GcliAgentModel` to extend `BaseLlm` directly with its own transport (using `AuthClient.request()`), not wrap `Gemini`. The OAuth flow, token refresh, and credential caching all work as-is — the issue was the design doc's assumption about the inner model, not auth capability.
+
+### Persistence is simpler than initially claimed
+DB-level concerns (PESSIMISTIC_WRITE, stale-writer detection, concurrent append policy) come from `DatabaseSessionService` and don't apply. The file-backed service wraps existing `ChatRecordingService`. Only rewind semantics need deeper design.
+
+### Interactive PR findings are rollout-risk evidence, not architecture defects
+The branch-stack dependency, hook-order risk, and `_meta.legacyState` leakage in PR #24297 are real but secondary to the core architecture gaps above.
+
+## What To Change Before Principal Review
+
+1. **Fix the 4 compilation blockers** (C1-C4) — these will be the first thing reviewers check
+2. **Add an explicit ADK→AgentProtocol translation architecture section** — this is the real design center
+3. **Add the shared-core subagent architecture** — custom `BaseTool` over shared runtime, not `AgentTool`
+4. **Use `BaseContextCompactor`** for compaction instead of embedding it in the model layer
+5. **Replace “100% possible today” and similar language** with explicit labels: native / bridgeable / blocked
+6. **Add a parity matrix** (feature | ADK mechanism | status | bridge workaround | long-term target)
+
+## Phased Migration Plan
+
+### Phase 0: Foundation (current state → near-term)
+**Goal:** Establish the shared runtime core and translation layer.
+
+- [ ] Fix compilation blockers (C1-C4) in design doc code samples
+- [ ] Implement `AdkRuntimeCore` wrapping ADK `Runner` + `LlmAgent`
+- [ ] Implement `AdkEventTranslator` (ADK `Event` → gemini-cli `AgentEvent`)
+- [ ] Implement `GcliAgentModel extends BaseLlm` with dual transport (API-key via `httpOptions.headers`, Coast Assist via `AuthClient.request()`)
+- [ ] Implement `GcliFileSessionService extends BaseSessionService` wrapping `ChatRecordingService`
+- [ ] Implement `GcliContextCompactor implements BaseContextCompactor` wrapping `ChatCompressionService`
+- [ ] Wire behind `experimental.adk` feature gate
+
+**Non-goals for Phase 0:**
+- No interactive flow changes
+- No subagent support
+- No live/bidi connections
+- No resumable approvals
+
+**Exit criteria:** Non-interactive flow produces identical output behind feature gate.
+
+### Phase 1: Non-Interactive Parity
+**Goal:** Feature-gated non-interactive flow matches legacy behavior.
+
+- [ ] Tool output masking via `BaseLlmRequestProcessor`
+- [ ] Model routing via `beforeModelCallback` + `RoutingContextBuilder` adapter
+- [ ] Policy enforcement via `beforeToolCallback` using existing callbacks (temporary bridge)
+- [ ] Quota/availability handling via `beforeModelCallback`
+- [ ] `ClearcutTelemetryPlugin extends BasePlugin` for token counts (`afterModelCallback`), per-tool timing (`beforeToolCallback`/`afterToolCallback` with `functionCallId`), agent lifecycle, model errors
+- [ ] HTTP-level telemetry (status code, duration) captured in `GcliAgentModel` wrapper
+- [ ] Verify ~70% of existing Clearcut call sites work unchanged
+
+**Non-goals for Phase 1:**
+- No interactive UI changes
+- No plan mode switching
+- No subagents
+- Approvals are callback-based, not resumable
+
+**Exit criteria:** Non-interactive tests pass with `experimental.adk.enabled = true`. Legacy path remains default.
+
+### Phase 2: Interactive Flow Migration
+**Goal:** Interactive flow uses the same ADK runtime behind `TopLevelSessionAdapter`.
+
+- [ ] `TopLevelSessionAdapter` exposing runtime as `AgentProtocol` / `AgentSession`
+- [ ] Stream lifecycle (`agent_start` / `agent_end` / `streamId` ownership)
+- [ ] Replay/reattach semantics matching current `AgentSession.stream()` behavior
+- [ ] Plan mode via dynamic `BaseToolset` + `InstructionProvider` + mode state
+- [ ] `ApprovalBridge` for tool confirmations using existing UI callbacks
+- [ ] Elicitation via existing callbacks (not yet bidi)
+- [ ] `_meta.legacyState` bridge for UI rendering (documented as temporary)
+
+**Non-goals for Phase 2:**
+- No live/bidi parity (`runLiveImpl` is still a stub in ADK TS)
+- No true mid-turn interruption (steering limited to once-per-LLM-call)
+- No resumable approvals across process death
+- No concurrent multi-stream sessions
+
+**Exit criteria:** Interactive flow works behind feature gate. Legacy path remains default.
+
+### Phase 3: Subagents and SDK Readiness
+**Goal:** Subagents share the core runtime. The architecture is SDK-reusable.
+
+- [ ] Custom `BaseTool` subagent wrappers over shared `AdkRuntimeCore`
+- [ ] `threadId`-scoped event projection for child activity
+- [ ] Shared policy, routing, and config inheritance
+- [ ] Remove `_meta.legacyState` — replace with proper event/adapter separation
+- [ ] Migrate approval bridge to native ADK elicitation/bidi (when available)
+- [ ] Define SDK public API surface
+
+**Non-goals for Phase 3:**
+- Full ADK Dev UI compatibility
+- Agent-to-agent transfer via ADK's native mechanism
+
+**Exit criteria:** Subagent invocation works. Architecture is documented for SDK consumers.
+
+## Positive Signals
+
+- Feature-gating behind `experimental.adk` is the right rollout pattern
+- Tool output masking maps cleanly to request-preprocessing
+- Dynamic toolset + `InstructionProvider` for plan mode is a good ADK-native fit
+- The phased migration checklist with tracking issues shows good engineering discipline
+- The doc correctly identifies 3 known ADK gaps (sections 5.1-5.3)
+- `AgentProtocol` / `AgentSession` is the right consumer-facing boundary
+- The policy adapter pattern is directionally sound even with reduced phase-1 semantics
+
+## Concern Decomposition
+
+| Concern | Level | ADK Mechanism |
+|---|---|---|
+| Auth (API key) | Transport | `BaseLlm` constructor / `httpOptions.headers` |
+| Auth (Coast Assist) | Transport | `BaseLlm` direct — custom transport via `AuthClient.request()` |
+| Model rewrite | Transport | `BaseLlm.generateContentAsync` model override |
+| Model routing | Agent | `beforeModelCallback` + `RoutingContextBuilder` |
+| Token compaction | Agent | `BaseContextCompactor` (native ADK) |
+| Quota/availability | Agent | `beforeModelCallback` |
+| Tool masking | Agent | `BaseLlmRequestProcessor` |
+| Tool confirmations | Agent+Consumer | `beforeToolCallback` + existing callbacks (phase 1) |
+| Telemetry (lifecycle) | Agent | `ClearcutTelemetryPlugin` — `afterModelCallback`, `beforeToolCallback`/`afterToolCallback` |
+| Telemetry (HTTP) | Transport | `GcliAgentModel` wrapper (status code, duration) |
+| Telemetry (CLI) | Consumer | Existing call sites (~70% of Clearcut metrics, unchanged) |
+| UI rendering | Consumer | Event subscriber / adapter |
+| Subagent invocation | Agent | Custom `BaseTool` over shared runtime core |
+
+## Final Verdict
+
+The design is architecturally correct in its goal. To be principal-review ready:
+
+1. Fix the 4 compilation blockers
+2. Add the ADK→AgentProtocol translation architecture as the design center
+3. Adopt native `BaseContextCompactor` instead of model-layer compaction
+4. Use custom `BaseTool` subagents over shared core (not `AgentTool`)
+5. Downgrade parity claims to match reality
+6. Add the phased plan with explicit non-goals per phase
+
+The migration path is: shared runtime core → translation layer → adapters (top-level session, subagent tools, approval bridge). Each phase ships independently behind the feature gate.

docs/admin/enterprise-controls.md

@@ -72,7 +72,7 @@ organization.
 **Supported Fields:**
 
 - `url`: (Required) The full URL of the MCP server endpoint.
-- `type`: (Required) The connection type (for example, `sse` or `http`).
+- `type`: (Required) The connection type (e.g., `sse` or `http`).
 - `trust`: (Optional) If set to `true`, the server is trusted and tool execution
   will not require user approval.
 - `includeTools`: (Optional) An explicit list of tool names to allow. If

docs/changelogs/index.md

@@ -18,194 +18,6 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |
 
-## Announcements: v0.52.0 - 2026-07-22
-
-- **Caretaker Triage & Egress Services:** Implemented the core triage worker
-  foundational modules, main worker execution loops, and egress action
-  publishers alongside the octokit GitHub Action handler for egress services
-  ([#28163](https://github.com/google-gemini/gemini-cli/pull/28163),
-  [#28306](https://github.com/google-gemini/gemini-cli/pull/28306) by @chadd28).
-- **Core Tool Enhancements:** Bypassed LLM correction for JSON and IPYNB files
-  in `write_file` and `replace` tools, and simplified plan mode write policy to
-  support relative paths
-  ([#28223](https://github.com/google-gemini/gemini-cli/pull/28223) by
-  @amelidev, [#28398](https://github.com/google-gemini/gemini-cli/pull/28398) by
-  @DavidAPierce).
-- **Auth & Privacy Improvements:** Displayed clear error messages when user
-  account has no Code Assist tier, and bumped `google-auth-library` to version
-  10.9.0 ([#28304](https://github.com/google-gemini/gemini-cli/pull/28304) by
-  @ompatel-aiml,
-  [#28385](https://github.com/google-gemini/gemini-cli/pull/28385) by
-  @jerrylin3321).
-
-## Announcements: v0.50.0 - 2026-07-08
-
-- **Tool Registry Discovery:** Introduced tool registry discovery capabilities
-  to automatically detect and register available tools
-  ([#28113](https://github.com/google-gemini/gemini-cli/pull/28113) by @ved015).
-- **Release Verification & CI Stability:** Enhanced release verification by
-  ignoring scripts during verification, preventing workspace binary shadowing,
-  and safeguarding against bad NPM releases
-  ([#28116](https://github.com/google-gemini/gemini-cli/pull/28116) by
-  @rmedranollamas,
-  [#28132](https://github.com/google-gemini/gemini-cli/pull/28132) by
-  @galdawave).
-
-## Announcements: v0.45.0 - 2026-06-03
-
-- **Context Simplification:** Completed major architectural work to simplify the
-  `ContextManager`, improving system robustness and performance
-  ([#27345](https://github.com/google-gemini/gemini-cli/pull/27345) by
-  @joshualitt).
-- **A2A Usage Metadata:** Exposed critical usage metadata in the Agent-to-Agent
-  (A2A) protocol for better resource tracking
-  ([#27288](https://github.com/google-gemini/gemini-cli/pull/27288) by
-  @jvargassanchez-dot).
-- **Reliability Fixes:** Addressed Termux relaunch loops, PTY resize errors, and
-  forced sequential execution for topic updates
-  ([#27110](https://github.com/google-gemini/gemini-cli/pull/27110) by @saymanq,
-  [#27357](https://github.com/google-gemini/gemini-cli/pull/27357) by
-  @jvargassanchez-dot,
-  [#27461](https://github.com/google-gemini/gemini-cli/pull/27461) by
-  @scidomino).
-
-## Announcements: v0.44.0 - 2026-05-27
-
-- **Unified Auto Mode:** Streamlined the automation experience by merging
-  specialized Auto modes into a single, unified mode
-  ([#26714](https://github.com/google-gemini/gemini-cli/pull/26714) by
-  @DavidAPierce).
-- **New Editor Integrations:** Added native support for Sublime Text and Emacs
-  Client ([#21090](https://github.com/google-gemini/gemini-cli/pull/21090) by
-  @alberti42).
-- **Enhanced TUI Testing:** Introduced `agent-tui` and `tui-tester` skills for
-  programmatic testing and automation of terminal UI applications
-  ([#27121](https://github.com/google-gemini/gemini-cli/pull/27121) by
-  @adamfweidman).
-
-## Announcements: v0.43.0 - 2026-05-22
-
-- **Surgical Code Edits:** Steered Gemini models to prefer the `edit` tool for
-  surgical modifications, improving speed and precision
-  ([#26480](https://github.com/google-gemini/gemini-cli/pull/26480) by
-  @aishaneeshah).
-- **Session Export and Import:** Added the ability to export sessions to files
-  and import them via a new flag, facilitating session portability
-  ([#26514](https://github.com/google-gemini/gemini-cli/pull/26514) by
-  @cocosheng-g).
-- **Adaptive Token Estimation:** Introduced an adaptive token calculator for
-  more accurate content size estimation, enhancing context management efficiency
-  ([#26888](https://github.com/google-gemini/gemini-cli/pull/26888) by
-  @joshualitt).
-
-## Announcements: v0.42.0 - 2026-05-12
-
-- **Auto Memory Inbox:** Introduced a new inbox flow for Auto Memory with a
-  canonical-patch contract for seamless skill management
-  ([#26338](https://github.com/google-gemini/gemini-cli/pull/26338) by
-  @SandyTao520).
-- **Gemma 4 by Default:** Enabled Gemma 4 models by default via the Gemini API
-  for all users
-  ([#26307](https://github.com/google-gemini/gemini-cli/pull/26307) by
-  @Abhijit-2592).
-- **Voice Mode Enhancements:** Added wave animations and privacy/compliance UX
-  warnings for the Gemini Live backend
-  ([#26284](https://github.com/google-gemini/gemini-cli/pull/26284) by
-  @devr0306, [#26454](https://github.com/google-gemini/gemini-cli/pull/26454) by
-  @cocosheng-g).
-
-## Announcements: v0.41.0 - 2026-05-05
-
-- **Real-time Voice Mode:** Implemented real-time voice mode with cloud and
-  local backends
-  ([#24174](https://github.com/google-gemini/gemini-cli/pull/24174) by
-  @Abhijit-2592).
-- **Secure Environment Loading:** Enforced workspace trust and secured .env
-  loading in headless mode
-  ([#25814](https://github.com/google-gemini/gemini-cli/pull/25814) by
-  @ehedlund).
-- **Advanced Shell Validation:** Enhanced shell command validation and added
-  core tools allowlist for improved security
-  ([#25720](https://github.com/google-gemini/gemini-cli/pull/25720) by @galz10).
-
-## Announcements: v0.40.0 - 2026-04-28
-
-- **Offline Search and Themes:** Bundled ripgrep for offline search support and
-  added GitHub-style colorblind themes
-  ([#25342](https://github.com/google-gemini/gemini-cli/pull/25342) by
-  @scidomino, [#15504](https://github.com/google-gemini/gemini-cli/pull/15504)
-  by @Z1xus).
-- **Advanced Resource and Memory Management:** Introduced MCP resource tools and
-  transitioned to a prompt-driven, four-tier memory management system
-  ([#25395](https://github.com/google-gemini/gemini-cli/pull/25395) by
-  @ruomengz, [#25716](https://github.com/google-gemini/gemini-cli/pull/25716) by
-  @SandyTao520).
-- **UX and Local Models:** Enabled topic update narrations by default and
-  streamlined Gemma local model setup with `gemini gemma`
-  ([#25586](https://github.com/google-gemini/gemini-cli/pull/25586) by
-  @gundermanc, [#25498](https://github.com/google-gemini/gemini-cli/pull/25498)
-  by @Samee24).
-
-## Announcements: v0.39.0 - 2026-04-23
-
-- **Skill Management:** Added a new `/memory` inbox command for reviewing and
-  patching skills extracted during sessions
-  ([#24544](https://github.com/google-gemini/gemini-cli/pull/24544) by
-  @SandyTao520, [#25148](https://github.com/google-gemini/gemini-cli/pull/25148)
-  by @SandyTao520).
-- **Improved Transparency:** Plan Mode now requires confirmation for skill
-  activation and allows plan inspection
-  ([#24946](https://github.com/google-gemini/gemini-cli/pull/24946),
-  [#25058](https://github.com/google-gemini/gemini-cli/pull/25058) by
-  @ruomengz).
-- **Architecture & Reliability:** Introduced a decoupled `ContextManager`
-  architecture and resolved several critical memory leaks and PTY exhaustion
-  issues ([#24752](https://github.com/google-gemini/gemini-cli/pull/24752) by
-  @joshualitt, [#25079](https://github.com/google-gemini/gemini-cli/pull/25079)
-  by @spencer426).
-
-## Announcements: v0.38.0 - 2026-04-14
-
-- **Chapters Narrative Flow:** Group agent interactions into "Chapters" based on
-  intent and tool usage for better session structure
-  ([#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).
-- **Context Compression Service:** Advanced context management to efficiently
-  distill conversation history
-  ([#24483](https://github.com/google-gemini/gemini-cli/pull/24483) by
-  @joshualitt).
-- **UI Flicker & UX Enhancements:** Solved rendering flicker with "Terminal
-  Buffer" mode and introduced selective topic expansion
-  ([#24512](https://github.com/google-gemini/gemini-cli/pull/24512) by
-  @jacob314, [#24793](https://github.com/google-gemini/gemini-cli/pull/24793) by
-  @Abhijit-2592).
-- **Persistent Policy Approvals:** Implemented context-aware persistent
-  approvals for tool execution
-  ([#23257](https://github.com/google-gemini/gemini-cli/pull/23257) by @jerop).
-
-## 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
@@ -540,7 +352,6 @@ on GitHub.
   headlessly in notebook cells or interactively in the built-in terminal
   ([pic](https://imgur.com/a/G0Tn7vi))
 - 🎉**Gemini CLI Extensions:**
-
   - **Conductor:** Planning++, Gemini works with you to build out a detailed
     plan, pull in extra details as needed, ultimately to give the LLM guardrails
     with artifacts. Measure twice, implement once!
@@ -669,7 +480,6 @@ on GitHub.
   - **Announcement:**
     [https://developers.googleblog.com/en/making-the-terminal-beautiful-one-pixel-at-a-time/](https://developers.googleblog.com/en/making-the-terminal-beautiful-one-pixel-at-a-time/)
 - **🎉 New partner extensions:**
-
   - **Arize:** Seamlessly instrument AI applications with Arize AX and grant
     direct access to Arize support:
 
@@ -709,7 +519,6 @@ on GitHub.
 ![Codebase investigator subagent in Gemini CLI.](https://i.imgur.com/4J1njsx.png)
 
 - **🎉 New partner extensions:**
-
   - **🤗 Hugging Face extension:** Access the Hugging Face hub.
     ([gif](https://drive.google.com/file/d/1LEzIuSH6_igFXq96_tWev11svBNyPJEB/view?usp=sharing&resourcekey=0-LtPTzR1woh-rxGtfPzjjfg))
 

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.52.0
+# Latest stable release: v0.36.0
 
-Released: July 22, 2026
+Released: April 1, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,59 +11,372 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Caretaker Services:** Introduced a new caretaker triage worker including
-  core foundational modules, main worker execution loops, egress action
-  publishers, and octokit GitHub Action handlers.
-- **Robust File Editing:** Core tools like `write_file` and `replace` now bypass
-  LLM corrections for JSON and IPYNB files to ensure accurate and direct file
-  modifications.
-- **Plan Mode Improvements:** Simplified plan mode write policies to natively
-  support writing to relative paths, enhancing project directory navigation.
-- **Enhanced Account Visibility:** Improved clear user-facing messages when the
-  user account does not have a Code Assist tier, and enriched shared project
-  quota limit errors with setup instructions.
+- **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.
 
 ## What's Changed
 
-- Refactor: exclude transient CI configuration files from workspace context by
-  @DavidAPierce in
-  [#28216](https://github.com/google-gemini/gemini-cli/pull/28216)
-- feat(caretaker-triage): add triage worker core foundational modules by
-  @chadd28 in [#28163](https://github.com/google-gemini/gemini-cli/pull/28163)
-- feat(caretaker-egress): implement octokit github action handler for egress
-  service by @chadd28 in
-  [#28303](https://github.com/google-gemini/gemini-cli/pull/28303)
-- chore(release): bump version to 0.52.0-nightly.20260707.g27a3da3e8 by
+- 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
-  [#28323](https://github.com/google-gemini/gemini-cli/pull/28323)
-- Changelog for v0.51.0-preview.0 by @gemini-cli-robot in
-  [#28320](https://github.com/google-gemini/gemini-cli/pull/28320)
-- Changelog for v0.50.0 by @gemini-cli-robot in
-  [#28322](https://github.com/google-gemini/gemini-cli/pull/28322)
-- fix(core-tools): bypass LLM correction for JSON and IPYNB files in write_file
-  and replace by @amelidev in
-  [#28223](https://github.com/google-gemini/gemini-cli/pull/28223)
-- fix(core): use unambiguous previous intent label in fallback summary by
-  @amelidev in [#28343](https://github.com/google-gemini/gemini-cli/pull/28343)
-- feat(caretaker-triage): implement main worker execution loop and egress action
-  publisher by @chadd28 in
-  [#28306](https://github.com/google-gemini/gemini-cli/pull/28306)
-- fix(privacy): show a clear message when the account has no Code Assist tier by
-  @ompatel-aiml in
-  [#28304](https://github.com/google-gemini/gemini-cli/pull/28304)
-- fix(core): enrich shared project quota limit errors with setup hint by
-  @amelidev in [#28391](https://github.com/google-gemini/gemini-cli/pull/28391)
-- fix(a2a-server): ensure task cancellation aborts execution loop by
-  @luisfelipe-alt in
-  [#28316](https://github.com/google-gemini/gemini-cli/pull/28316)
-- fix(core): simplify plan mode write policy to support relative paths by
-  @DavidAPierce in
-  [#28398](https://github.com/google-gemini/gemini-cli/pull/28398)
-- feat(core): Bump node google-auth-library version to 10.9.0 by @jerrylin3321
-  in [#28385](https://github.com/google-gemini/gemini-cli/pull/28385)
-- chore/release: bump version to 0.52.0-nightly.20260715.gfa975395b by
+  [#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
+  @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
+  @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
+  @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
+  @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
   @gemini-cli-robot in
-  [#28402](https://github.com/google-gemini/gemini-cli/pull/28402)
+  [#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
+  @gemini-cli-robot in
+  [#24061](https://github.com/google-gemini/gemini-cli/pull/24061)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.51.0...v0.52.0
+https://github.com/google-gemini/gemini-cli/compare/v0.35.3...v0.36.0

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: v0.53.0-preview.0
+# Preview release: v0.37.0-preview.1
 
-Released: July 22, 2026
+Released: April 02, 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).
@@ -13,42 +13,410 @@ npm install -g @google/gemini-cli@preview
 
 ## Highlights
 
-- **Caretaker LLM Triage Orchestrator**: Implemented the LLM triage orchestrator
-  and container build configuration to support caretaker triage workflows.
-- **Enhanced Workspace Trust & Sandbox Hardening**: Aligned macOS permissive
-  Seatbelt profiles with the deny-default model and enforced workspace trust and
-  task isolation in the Agent-to-Agent (A2A) server to prevent remote code
-  execution (RCE).
-- **Core Robustness & API Protections**: Mitigated infinite ReAct and prompt
-  injection loops, and prevented 400 Bad Request errors by grouping cancelled
-  tool responses and coalescing consecutive roles.
-- **Robust Credentials & Fallbacks**: Restored the
-  `GOOGLE_APPLICATION_CREDENTIALS` environment variable fallback and
-  sequentially verified cached credentials.
-- **Evaluation Coverage Reporting**: Added a new command to generate
-  comprehensive eval coverage reports.
+- **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.
 
 ## What's Changed
 
-- fix(core,a2a): group cancelled tool responses and coalesce consecutive roles
-  to prevent 400 Bad Request by @luisfelipe-alt in
-  [#28407](https://github.com/google-gemini/gemini-cli/pull/28407)
-- feat(caretaker-triage): implement LLM triage orchestrator and container build
-  by @chadd28 in
-  [#28345](https://github.com/google-gemini/gemini-cli/pull/28345)
-- refactor(cli): align macOS permissive Seatbelt profiles with deny-default
-  model by @ompatel-aiml in
-  [#28424](https://github.com/google-gemini/gemini-cli/pull/28424)
-- fix(core): mitigate infinite ReAct loops and prompt injection loops by
-  @amelidev in [#28429](https://github.com/google-gemini/gemini-cli/pull/28429)
-- fix(a2a-server): enforce workspace trust and task isolation to prevent RCE by
-  @luisfelipe-alt in
-  [#28470](https://github.com/google-gemini/gemini-cli/pull/28470)
-- fix(core): sequentially verify cached credentials and restore
-  GOOGLE_APPLICATION_CREDENTIALS fallback by @luisfelipe-alt in
-  [#28472](https://github.com/google-gemini/gemini-cli/pull/28472)
-- feat(evals): add eval coverage report command by @ved015 in
-  [#28169](https://github.com/google-gemini/gemini-cli/pull/28169)
+- 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
+  @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
+  @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)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.52.0-preview.0...v0.53.0-preview.0
+https://github.com/google-gemini/gemini-cli/compare/v0.36.0-preview.8...v0.37.0-preview.1

docs/cli/acp-mode.md

@@ -44,8 +44,8 @@ and Gemini CLI (the server).
 
 - **Communication:** The entire communication happens over standard input/output
   (stdio) using the JSON-RPC 2.0 protocol.
-- **Client's role:** The client is responsible for sending requests (for
-  example, prompts) and handling responses and notifications from Gemini CLI.
+- **Client's role:** The client is responsible for sending requests (e.g.,
+  prompts) and handling responses and notifications from Gemini CLI.
 - **Gemini CLI's role:** In ACP mode, Gemini CLI listens for incoming JSON-RPC
   requests, processes them, and sends back responses.
 
@@ -72,8 +72,8 @@ leverage the IDE's capabilities to perform tasks. The MCP client logic is in
 
 ## Capabilities and supported methods
 
-The ACP protocol exposes a number of methods for ACP clients (for example IDEs)
-to control Gemini CLI.
+The ACP protocol exposes a number of methods for ACP clients (e.g. IDEs) to
+control Gemini CLI.
 
 ### Core methods
 
@@ -87,8 +87,8 @@ to control Gemini CLI.
 
 ### Session control
 
-- `setSessionMode`: Allows changing the approval level for tool calls (for
-  example, to `auto-approve`).
+- `setSessionMode`: Allows changing the approval level for tool calls (e.g., to
+  `auto-approve`).
 - `unstable_setSessionModel`: Changes the model for the current session.
 
 ### File system proxy

docs/cli/auto-memory.md

@@ -1,164 +0,0 @@
-# Auto Memory
-
-Auto Memory is an experimental feature that mines your past Gemini CLI sessions
-in the background and proposes durable memory updates and reusable
-[Agent Skills](./skills.md). You review each candidate before it becomes
-available to future sessions: apply memory updates, promote skills, or discard
-anything you do not want.
-
-<!-- prettier-ignore -->
-> [!NOTE]
-> This is an experimental feature currently under active development.
-
-## Overview
-
-Every session you run with Gemini CLI is recorded locally as a transcript. Auto
-Memory scans those transcripts for durable facts, preferences, workflow
-constraints, and procedural patterns that recur across sessions. It can draft
-memory updates as unified diff `.patch` files and draft reusable procedures as
-`SKILL.md` files. All candidates are held in a project-local inbox until you
-approve or discard them.
-
-You'll use Auto Memory when you want to:
-
-- **Capture team workflows** that you find yourself walking the agent through
-  more than once.
-- **Preserve durable project context** such as repeated verification commands,
-  local constraints, or personal project notes.
-- **Codify hard-won fixes** for project-specific landmines so future sessions
-  avoid them.
-- **Bootstrap a skills library** without writing every `SKILL.md` by hand.
-
-Auto Memory complements direct memory-file editing. The agent can still persist
-explicit user instructions by editing the appropriate Markdown memory file; Auto
-Memory infers candidates from past sessions, writes reviewable patches or skill
-drafts, and never applies them without your approval.
-
-## Prerequisites
-
-- Gemini CLI installed and authenticated.
-- At least one idle project session with 10 or more user messages. Auto Memory
-  ignores active, trivial, and sub-agent sessions.
-
-## How to enable Auto Memory
-
-Auto Memory is off by default. Enable it in your settings file:
-
-1.  Open your global settings file at `~/.gemini/settings.json`. If you only
-    want Auto Memory in one project, edit `.gemini/settings.json` in that
-    project instead.
-
-2.  Add the experimental flag:
-
-    ```json
-    {
-      "experimental": {
-        "autoMemory": true
-      }
-    }
-    ```
-
-3.  Restart Gemini CLI. The flag requires a restart because the extraction
-    service starts during session boot.
-
-## How Auto Memory works
-
-Auto Memory runs as a background task on session startup. It does not block the
-UI, consume your interactive turns, or surface tool prompts.
-
-1.  **Eligibility scan.** The service indexes recent sessions from
-    `~/.gemini/tmp/<project>/chats/`. Sessions are eligible only if they have
-    been idle for at least three hours and contain at least 10 user messages.
-2.  **Lock acquisition.** A lock file in the project's memory directory
-    coordinates across multiple CLI instances so extraction runs at most once at
-    a time. A state file records processed session versions, and extraction is
-    throttled so short back-to-back CLI launches do not repeatedly scan history.
-3.  **Candidate extraction.** A background extraction agent reviews the session
-    index, reads any sessions that look like they contain durable memory or
-    repeated procedural workflows, and drafts candidates. It defaults to
-    creating no artifacts unless the evidence is strong, so many runs produce no
-    inbox items.
-4.  **Safety boundaries.** Auto Memory writes candidates to a review inbox. It
-    cannot directly edit active memory files, settings, credentials, or project
-    `GEMINI.md` files.
-5.  **Patch validation.** Skill update patches are parsed and dry-run before
-    they are surfaced. Memory patches are parsed, target-allowlisted, and
-    applied atomically only when you approve them from the inbox.
-6.  **Notification.** When a run produces new candidates, Gemini CLI surfaces an
-    inline message telling you how many items are waiting.
-
-## How to review extracted items
-
-Use the `/memory inbox` slash command to open the inbox dialog at any time:
-
-**Command:** `/memory inbox`
-
-The dialog groups pending items into new skills, skill updates, and memory
-updates. From there you can:
-
-- **Read** the full `SKILL.md` body before deciding.
-- **Promote** a skill to your user (`~/.gemini/skills/`) or workspace
-  (`.gemini/skills/`) directory.
-- **Discard** a skill you do not want.
-- **Apply** or reject a `.patch` proposal against an existing skill.
-- **Review** memory diffs before they touch active files.
-- **Apply** or dismiss private and global memory patches. Private patches target
-  the project memory directory; global patches target only your personal
-  `~/.gemini/GEMINI.md` file.
-
-Promoted skills become discoverable in the next session and follow the standard
-[skill discovery precedence](./skills.md#skill-discovery-tiers). Applied memory
-patches update the underlying memory files and reload memory for the current
-session.
-
-## How to disable Auto Memory
-
-To turn off background extraction, set the flag back to `false` in your settings
-file and restart Gemini CLI:
-
-```json
-{
-  "experimental": {
-    "autoMemory": false
-  }
-}
-```
-
-Disabling the flag stops the background service immediately on the next session
-start. Existing inbox items remain on disk; you can either drain them with
-`/memory inbox` first or remove the project memory directory manually.
-
-## Data and privacy
-
-- Auto Memory only reads session files that already exist locally on your
-  machine.
-- Auto Memory uses model calls to analyze selected local transcript content
-  during extraction. No candidates are applied automatically, but transcript
-  excerpts may be sent to the configured model as part of those calls.
-- The extraction agent is instructed to redact secrets, tokens, and credentials
-  it encounters and to never copy large tool outputs verbatim.
-- Drafted skills and memory patches live in your project's memory directory
-  until you promote, apply, dismiss, or discard them. They are not automatically
-  loaded into any session.
-
-## Limitations
-
-- The extraction agent runs on a preview Gemini Flash model. Extraction quality
-  depends on the model's ability to recognize durable patterns versus one-off
-  incidents.
-- Auto Memory does not extract memory or skills from the current session. It
-  only considers sessions that have been idle for three hours or more.
-- Project or workspace shared instructions in project `GEMINI.md` files are not
-  auto-extractable. Auto Memory can propose private project memory, global
-  personal memory, and skills.
-- Inbox items are stored per project. Skills extracted in one workspace are not
-  visible from another until you promote them to the user-scope skills
-  directory.
-
-## Next steps
-
-- Learn how skills are discovered and activated in [Agent Skills](./skills.md).
-- Explore the [memory management tutorial](./tutorials/memory-management.md) for
-  the complementary explicit-memory and `GEMINI.md` workflows.
-- Review the experimental settings catalog in
-  [Settings](./settings.md#experimental).

docs/cli/checkpointing.md

@@ -1,9 +1,9 @@
 # Checkpointing
 
-Gemini CLI includes a Checkpointing feature that automatically saves a snapshot
-of your project's state before any file modifications are made by AI-powered
-tools. This lets you safely experiment with and apply code changes, knowing you
-can instantly revert back to the state before the tool was run.
+The Gemini CLI includes a Checkpointing feature that automatically saves a
+snapshot of your project's state before any file modifications are made by
+AI-powered tools. This lets you safely experiment with and apply code changes,
+knowing you can instantly revert back to the state before the tool was run.
 
 ## How it works
 
@@ -72,7 +72,7 @@ To see a list of all saved checkpoints for the current project, simply run:
 
 The CLI will display a list of available checkpoint files. These file names are
 typically composed of a timestamp, the name of the file being modified, and the
-name of the tool that was about to be run (for example,
+name of the tool that was about to be run (e.g.,
 `2025-06-22T10-00-00_000Z-my-file.txt-write_file`).
 
 ### Restore a specific checkpoint

docs/cli/cli-reference.md

@@ -9,7 +9,7 @@ and parameters.
 | ---------------------------------- | ---------------------------------- | ------------------------------------------------------------ |
 | `gemini`                           | Start interactive REPL             | `gemini`                                                     |
 | `gemini -p "query"`                | Query non-interactively            | `gemini -p "summarize README.md"`                            |
-| gemini "query"                     | Query and continue interactively   | gemini "explain this project"                                |
+| `gemini "query"`                   | Query and continue interactively   | `gemini "explain this project"`                              |
 | `cat file \| gemini`               | Process piped content              | `cat logs.txt \| gemini`<br>`Get-Content logs.txt \| gemini` |
 | `gemini -i "query"`                | Execute and continue interactively | `gemini -i "What is the purpose of this project?"`           |
 | `gemini -r "latest"`               | Continue most recent session       | `gemini -r "latest"`                                         |
@@ -29,17 +29,16 @@ and parameters.
 
 These commands are available within the interactive REPL.
 
-| Command              | Description                                     |
-| -------------------- | ----------------------------------------------- |
-| `/skills reload`     | Reload discovered skills from disk              |
-| `/agents reload`     | Reload the agent registry                       |
-| `/commands list`     | List available custom slash commands            |
-| `/commands reload`   | Reload custom slash commands                    |
-| `/memory reload`     | Reload context files (for example, `GEMINI.md`) |
-| `/mcp reload`        | Restart and reload MCP servers                  |
-| `/extensions reload` | Reload all active extensions                    |
-| `/help`              | Show help for all commands                      |
-| `/quit`              | Exit the interactive session                    |
+| Command              | Description                              |
+| -------------------- | ---------------------------------------- |
+| `/skills reload`     | Reload discovered skills from disk       |
+| `/agents reload`     | Reload the agent registry                |
+| `/commands reload`   | Reload custom slash commands             |
+| `/memory reload`     | Reload context files (e.g., `GEMINI.md`) |
+| `/mcp reload`        | Restart and reload MCP servers           |
+| `/extensions reload` | Reload all active extensions             |
+| `/help`              | Show help for all commands               |
+| `/quit`              | Exit the interactive session             |
 
 ## CLI Options
 
@@ -53,7 +52,6 @@ These commands are available within the interactive REPL.
 | `--prompt-interactive`           | `-i`  | string  | -         | Execute prompt and continue in interactive mode                                                                                                                        |
 | `--worktree`                     | `-w`  | string  | -         | Start Gemini in a new git worktree. If no name is provided, one is generated automatically. Requires `experimental.worktrees: true` in settings.                       |
 | `--sandbox`                      | `-s`  | boolean | `false`   | Run in a sandboxed environment for safer execution                                                                                                                     |
-| `--skip-trust`                   | -     | boolean | `false`   | Trust the current workspace for this session, skipping the folder trust check.                                                                                         |
 | `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`, `plan`                                                                                      |
 | `--yolo`                         | `-y`  | boolean | `false`   | **Deprecated.** Auto-approve all actions. Use `--approval-mode=yolo` instead.                                                                                          |
 | `--experimental-acp`             | -     | boolean | -         | Start in ACP (Agent Code Pilot) mode. **Experimental feature.**                                                                                                        |
@@ -62,7 +60,7 @@ These commands are available within the interactive REPL.
 | `--allowed-tools`                | -     | array   | -         | **Deprecated.** Use the [Policy Engine](../reference/policy-engine.md) instead. Tools that are allowed to run without confirmation (comma-separated or multiple flags) |
 | `--extensions`                   | `-e`  | array   | -         | List of extensions to use. If not provided, all extensions are enabled (comma-separated or multiple flags)                                                             |
 | `--list-extensions`              | `-l`  | boolean | -         | List all available extensions and exit                                                                                                                                 |
-| `--resume`                       | `-r`  | string  | -         | Resume a previous session. Use `"latest"` for most recent or index number (for example `--resume 5`)                                                                   |
+| `--resume`                       | `-r`  | string  | -         | Resume a previous session. Use `"latest"` for most recent or index number (e.g. `--resume 5`)                                                                          |
 | `--list-sessions`                | -     | boolean | -         | List available sessions for the current project and exit                                                                                                               |
 | `--delete-session`               | -     | string  | -         | Delete a session by index number (use `--list-sessions` to see available sessions)                                                                                     |
 | `--include-directories`          | -     | array   | -         | Additional directories to include in the workspace (comma-separated or multiple flags)                                                                                 |

docs/cli/creating-skills.md

@@ -1,138 +1,43 @@
 # Creating Agent Skills
 
-Agent Skills let you extend Gemini CLI with specialized expertise, procedural
-workflows, and task-specific resources. This guide walks you through both
-automated and manual methods for creating and organizing your skills.
+This guide provides an overview of how to create your own Agent Skills to extend
+the capabilities of Gemini CLI.
 
-## Quickstart: Create a skill with a prompt
+## Getting started: The `skill-creator` skill
 
-The fastest way to create a new skill is to use the built-in `skill-creator`.
-This meta-skill guides you through designing, scaffolding, and validating your
-expertise.
+The recommended way to create a new skill is to use the built-in `skill-creator`
+skill. To use it, ask Gemini CLI to create a new skill for you.
 
-Simply ask Gemini CLI to create a skill for you:
+**Example prompt:**
 
-> "Create a new skill called 'code-reviewer' that analyzes local files for
-> common errors and style violations."
+> "create a new skill called 'code-reviewer'"
 
-Gemini will then:
+Gemini CLI will then use the `skill-creator` to generate the skill:
 
-1.  Generate a new directory for your skill (for example, `my-new-skill/`).
+1.  Generate a new directory for your skill (e.g., `my-new-skill/`).
 2.  Create a `SKILL.md` file with the necessary YAML frontmatter (`name` and
     `description`).
 3.  Create the standard resource directories: `scripts/`, `references/`, and
     `assets/`.
 
-Once created, you can find your new skill in `.gemini/skills/code-reviewer/`.
+## Manual skill creation
 
-## Manual creation
+If you prefer to create skills manually:
 
-1.  **Create a directory** for your skill (for example, `my-new-skill/`).
+1.  **Create a directory** for your skill (e.g., `my-new-skill/`).
 2.  **Create a `SKILL.md` file** inside the new directory.
 
-### 1. Create the directory structure
+To add additional resources that support the skill, refer to the skill
+structure.
 
-The first step is to create the necessary folders for your skill and its
-scripts.
+## Skill structure
 
-**macOS/Linux**
+A skill is a directory containing a `SKILL.md` file at its root.
 
-```bash
-mkdir -p .gemini/skills/code-reviewer/scripts
-```
-
-**Windows (PowerShell)**
-
-```powershell
-New-Item -ItemType Directory -Force -Path ".gemini\skills\code-reviewer\scripts"
-```
-
-### 2. Define the skill (`SKILL.md`)
-
-The `SKILL.md` file defines the skill's purpose and instructions for the agent.
-Create a file at `.gemini/skills/code-reviewer/SKILL.md`.
-
-```markdown
----
-name: code-reviewer
-description:
-  Expertise in reviewing code changes for correctness, security, and style. Use
-  when the user asks to "review" their code or a PR.
----
-
-# Code Reviewer Instructions
-
-You act as a senior software engineer specialized in code quality. When this
-skill is active, you MUST:
-
-1.  **Analyze**: Review the provided code for logical errors, security
-    vulnerabilities, and style violations.
-2.  **Review**: Use the bundled `scripts/review.js` utility to perform an
-    automated check.
-3.  **Feedback**: Provide constructive feedback, clearly distinguishing between
-    critical issues and minor improvements.
-```
-
-### 3. Add the tool logic
-
-Skills can bundle resources like scripts to perform deterministic tasks. Create
-a file at `.gemini/skills/code-reviewer/scripts/review.js`.
-
-```javascript
-// .gemini/skills/code-reviewer/scripts/review.js
-const file = process.argv[2];
-
-if (!file) {
-  console.error('Usage: node review.js <file>');
-  process.exit(1);
-}
-
-console.log(`Reviewing ${file}...`);
-// Simple mock review logic
-setTimeout(() => {
-  console.log(`Result: Success (No major issues found in ${file})`);
-}, 500);
-```
-
-### 4. Test the skill
-
-Gemini CLI automatically discovers skills in the `.gemini/skills` directory.
-
-1.  Start a new session and ask a question that triggers the skill's
-    description: "Can you review index.js"
-2.  Gemini identifies the request matches the `code-reviewer` description and
-    asks for permission to activate it.
-3.  Once you approve, Gemini executes the bundled script:
-    `node .gemini/skills/code-reviewer/scripts/review.js index.js`
-
-To determine whether your skill has been correctly loaded, run the command:
-
-```bash
-/skills
-```
-
-### 5. Optional: Share your skill
-
-You can share your skills in several ways depending on your target audience.
-
-- **Workspace skills**: Commit your skill to a `.gemini/skills/` directory in
-  your project repository.
-- **Extensions**: Bundle your skill within a
-  [Gemini CLI extension](../extensions/writing-extensions.md).
-- **Git repositories**: Share the skill directory as a standalone Git repo and
-  install it using `gemini skills install <url>`.
-
----
-
-## Core concepts
-
-Now that you've built your first skill, let's explore the core components and
-workflows for developing more complex expertise.
-
-### Skill structure
+### Folder structure
 
 While a `SKILL.md` file is the only required component, we recommend the
-following structure for organizing your skill's resources.
+following structure for organizing your skill's resources:
 
 ```text
 my-skill/
@@ -142,66 +47,34 @@ my-skill/
 └── assets/        (Optional) Templates and other resources
 ```
 
-When a skill is activated, the model is granted access to this entire directory.
-You can instruct the model to use the tools and files found within these
-folders.
+### `SKILL.md` file
 
-### Metadata and triggers
+The `SKILL.md` file is the core of your skill. This file uses YAML frontmatter
+for metadata and Markdown for instructions. For example:
 
-The `SKILL.md` file uses YAML frontmatter for metadata.
+```markdown
+---
+name: code-reviewer
+description:
+  Use this skill to review code. It supports both local changes and remote Pull
+  Requests.
+---
+
+# Code Reviewer
+
+This skill guides the agent in conducting thorough code reviews.
+
+## Workflow
+
+### 1. Determine Review Target
+
+- **Remote PR**: If the user gives a PR number or URL, target that remote PR.
+- **Local Changes**: If changes are local... ...
+```
 
 - **`name`**: A unique identifier for the skill. This should match the directory
   name.
-- **`description`**: **CRITICAL.** This is how Gemini decides when to use the
-  skill. Be specific about the tasks it handles and the keywords that should
-  trigger it.
-
-### Discovery tiers
-
-Gemini CLI discovers skills from several locations, following a specific order
-of precedence (lowest to highest):
-
-1.  **Built-in Skills**: Included with Gemini CLI (pre-approved).
-2.  **Extension Skills**: Bundled within [extensions](../extensions/).
-3.  **User Skills**: `~/.gemini/skills/` or the `~/.agents/skills/` alias.
-4.  **Workspace Skills**: `.gemini/skills/` or the `.agents/skills/` alias.
-
-### Discovery aliases
-
-You can use `.agents/skills` as an alternative to `.gemini/skills`. This alias
-is compatible with other AI agent tools following the
-[Agent Skills](https://agentskills.io) standard.
-
-## Advanced development
-
-Once you've built a basic skill, you can use specialized scripts and workflows
-to streamline your development process.
-
-### Creation scripts
-
-If you are developing a skill and want to use the same scripts the built-in
-tools use, you can find them in the core package. These scripts help automate
-the initialization, validation, and packaging of skills.
-
-- **Initialize**: `node scripts/init_skill.cjs <name> --path <dir>`
-- **Validate**: `node scripts/validate_skill.cjs <path/to/skill>`
-- **Package**: `node scripts/package_skill.cjs <path/to/skill>` (Creates a
-  `.skill` zip file)
-
-### Linking for local development
-
-If you are developing a skill in a separate directory, you can link it to your
-user skills directory for testing:
-
-```bash
-gemini skills link .
-```
-
-## Next steps
-
-- [Skill best practices](./skills-best-practices.md): Learn strategies for
-  building reliable and effective skills.
-- [Agent Skills overview](./skills.md): Deep dive into discovery tiers and the
-  skill lifecycle.
-- [Get started with Agent Skills](./tutorials/skills-getting-started.md): A
-  quick walkthrough of triggering and using skills.
+- **`description`**: A description of what the skill does and when Gemini should
+  use it.
+- **Body**: The Markdown body of the file contains the instructions that guide
+  the agent's behavior when the skill is active.

docs/cli/custom-commands.md

@@ -34,7 +34,6 @@ separator (`/` or `\`) being converted to a colon (`:`).
 > [!TIP]
 > After creating or modifying `.toml` command files, run
 > `/commands reload` to pick up your changes without restarting the CLI.
-> To see all available command files, run `/commands list`.
 
 ## TOML file format (v1)
 
@@ -86,8 +85,8 @@ The model receives:
 **B. Using arguments in shell commands (inside `!{...}` blocks)**
 
 When you use `{{args}}` inside a shell injection block (`!{...}`), the arguments
-are automatically **shell-escaped** before replacement. This lets you safely
-pass arguments to shell commands, ensuring the resulting command is
+are automatically **shell-escaped** before replacement. This allows you to
+safely pass arguments to shell commands, ensuring the resulting command is
 syntactically correct and secure while preventing command injection
 vulnerabilities.
 
@@ -106,8 +105,8 @@ When you run `/grep-code It's complicated`:
 
 1. The CLI sees `{{args}}` used both outside and inside `!{...}`.
 2. Outside: The first `{{args}}` is replaced raw with `It's complicated`.
-3. Inside: The second `{{args}}` is replaced with the escaped version (for
-   example, on Linux: `"It\'s complicated"`).
+3. Inside: The second `{{args}}` is replaced with the escaped version (e.g., on
+   Linux: `"It\'s complicated"`).
 4. The command executed is `grep -r "It's complicated" .`.
 5. The CLI prompts you to confirm this exact, secure command before execution.
 6. The final prompt is sent.
@@ -117,13 +116,13 @@ When you run `/grep-code It's complicated`:
 If your `prompt` does **not** contain the special placeholder `{{args}}`, the
 CLI uses a default behavior for handling arguments.
 
-If you provide arguments to the command (for example, `/mycommand arg1`), the
-CLI will append the full command you typed to the end of the prompt, separated
-by two newlines. This allows the model to see both the original instructions and
-the specific arguments you just provided.
+If you provide arguments to the command (e.g., `/mycommand arg1`), the CLI will
+append the full command you typed to the end of the prompt, separated by two
+newlines. This allows the model to see both the original instructions and the
+specific arguments you just provided.
 
-If you do **not** provide any arguments (for example, `/mycommand`), the prompt
-is sent to the model exactly as it is, with nothing appended.
+If you do **not** provide any arguments (e.g., `/mycommand`), the prompt is sent
+to the model exactly as it is, with nothing appended.
 
 **Example (`changelog.toml`):**
 
@@ -189,7 +188,7 @@ ensure that only intended commands can be run.
     dialog will appear showing the exact command(s) to be executed.
 5.  **Execution and error reporting:** The command is executed. If the command
     fails, the output injected into the prompt will include the error messages
-    (stderr) followed by a status line, for example,
+    (stderr) followed by a status line, e.g.,
     `[Shell command exited with code 1]`. This helps the model understand the
     context of the failure.
 
@@ -230,10 +229,9 @@ operate on specific files.
 
 - **File injection**: `@{path/to/file.txt}` is replaced by the content of
   `file.txt`.
-- **Multimodal support**: If the path points to a supported image (for example,
-  PNG, JPEG), PDF, audio, or video file, it will be correctly encoded and
-  injected as multimodal input. Other binary files are handled gracefully and
-  skipped.
+- **Multimodal support**: If the path points to a supported image (e.g., PNG,
+  JPEG), PDF, audio, or video file, it will be correctly encoded and injected as
+  multimodal input. Other binary files are handled gracefully and skipped.
 - **Directory listing**: `@{path/to/dir}` is traversed and each file present
   within the directory and all subdirectories is inserted into the prompt. This
   respects `.gitignore` and `.geminiignore` if enabled.

docs/cli/enterprise.md

@@ -175,8 +175,8 @@ the enterprise settings are always loaded with the highest precedence.
 **Example wrapper script:**
 
 Administrators can create a script named `gemini` and place it in a directory
-that appears earlier in the user's `PATH` than the actual Gemini CLI binary (for
-example, `/usr/local/bin/gemini`).
+that appears earlier in the user's `PATH` than the actual Gemini CLI binary
+(e.g., `/usr/local/bin/gemini`).
 
 ```bash
 #!/bin/bash
@@ -285,7 +285,7 @@ environment to a blocklist.
 <!-- prettier-ignore -->
 > [!WARNING]
 > Blocklisting with `excludeTools` is less secure than
-> allowlisting with `tools.core`, as it relies on blocking known-bad commands,
+> allowlisting with `coreTools`, as it relies on blocking known-bad commands,
 > and clever users may find ways to bypass simple string-based blocks.
 > **Allowlisting is the recommended approach.**
 
@@ -325,9 +325,9 @@ User. When it comes to the `mcpServers` object, these configurations are
 1.  **Merging:** The lists of servers from all three levels are combined into a
     single list.
 2.  **Precedence:** If a server with the **same name** is defined at multiple
-    levels (for example, a server named `corp-api` exists in both system and
-    user settings), the definition from the highest-precedence level is used.
-    The order of precedence is: **System > Workspace > User**.
+    levels (e.g., a server named `corp-api` exists in both system and user
+    settings), the definition from the highest-precedence level is used. The
+    order of precedence is: **System > Workspace > User**.
 
 This means a user **cannot** override the definition of a server that is already
 defined in the system-level settings. However, they **can** add new servers with
@@ -343,8 +343,8 @@ canonical servers and adding their names to an allowlist.
 For even greater security, especially when dealing with third-party MCP servers,
 you can restrict which specific tools from a server are exposed to the model.
 This is done using the `includeTools` and `excludeTools` properties within a
-server's definition. This lets you use a subset of tools from a server without
-allowing potentially dangerous ones.
+server's definition. This allows you to use a subset of tools from a server
+without allowing potentially dangerous ones.
 
 Following the principle of least privilege, it is highly recommended to use
 `includeTools` to create an allowlist of only the necessary tools.
@@ -481,8 +481,9 @@ an environment variable, but it can also be enforced for custom tools via the
 ## Telemetry and auditing
 
 For auditing and monitoring purposes, you can configure Gemini CLI to send
-telemetry data to a central location. This lets you track tool usage and other
-events. For more information, see the [telemetry documentation](./telemetry.md).
+telemetry data to a central location. This allows you to track tool usage and
+other events. For more information, see the
+[telemetry documentation](./telemetry.md).
 
 **Example:** Enable telemetry and send it to a local OTLP collector. If
 `otlpEndpoint` is not specified, it defaults to `http://localhost:4317`.
@@ -505,19 +506,15 @@ events. For more information, see the [telemetry documentation](./telemetry.md).
 ## Authentication
 
 You can enforce a specific authentication method for all users by setting the
-`security.auth.enforcedType` in the system-level `settings.json` file. This
-prevents users from choosing a different authentication method. See the
-[Authentication docs](../get-started/authentication.mdx) for more details.
+`enforcedAuthType` in the system-level `settings.json` file. This prevents users
+from choosing a different authentication method. See the
+[Authentication docs](../get-started/authentication.md) for more details.
 
 **Example:** Enforce the use of Google login for all users.
 
 ```json
 {
-  "security": {
-    "auth": {
-      "enforcedType": "oauth-personal"
-    }
-  }
+  "enforcedAuthType": "oauth-personal"
 }
 ```
 

docs/cli/gemini-ignore.md

@@ -1,9 +1,9 @@
 # Ignoring files
 
 This document provides an overview of the Gemini Ignore (`.geminiignore`)
-feature of Gemini CLI.
+feature of the Gemini CLI.
 
-Gemini CLI includes the ability to automatically ignore files, similar to
+The Gemini CLI includes the ability to automatically ignore files, similar to
 `.gitignore` (used by Git) and `.aiexclude` (used by Gemini Code Assist). Adding
 paths to your `.geminiignore` file will exclude them from tools that support
 this feature, although they will still be visible to other services (such as

docs/cli/gemini-md.md

@@ -16,12 +16,10 @@ sends them to the model with every prompt. The CLI loads files in the following
 order:
 
 1.  **Global context file:**
-
     - **Location:** `~/.gemini/GEMINI.md` (in your user home directory).
     - **Scope:** Provides default instructions for all your projects.
 
 2.  **Environment and workspace context files:**
-
     - **Location:** The CLI searches for `GEMINI.md` files in your configured
       workspace directories and their parent directories.
     - **Scope:** Provides context relevant to the projects you are currently
@@ -67,6 +65,8 @@ You can interact with the loaded context files by using the `/memory` command.
   being provided to the model.
 - **`/memory reload`**: Forces a re-scan and reload of all `GEMINI.md` files
   from all configured locations.
+- **`/memory add <text>`**: Appends your text to your global
+  `~/.gemini/GEMINI.md` file. This lets you add persistent memories on the fly.
 
 ## Modularize context with imports
 

docs/cli/generation-settings.md

@@ -1,28 +1,26 @@
 # Advanced Model Configuration
 
-This guide details the Model Configuration system within Gemini CLI. Designed
-for researchers, AI quality engineers, and advanced users, this system provides
-a rigorous framework for managing generative model hyperparameters and
+This guide details the Model Configuration system within the Gemini CLI.
+Designed for researchers, AI quality engineers, and advanced users, this system
+provides a rigorous framework for managing generative model hyperparameters and
 behaviors.
 
-<!-- prettier-ignore -->
-> [!WARNING]
-> This is a power-user feature. Configuration values are passed
+> **Warning**: This is a power-user feature. Configuration values are passed
 > directly to the model provider with minimal validation. Incorrect settings
-> (for example, incompatible parameter combinations) may result in runtime
-> errors from the API.
+> (e.g., incompatible parameter combinations) may result in runtime errors from
+> the API.
 
 ## 1. System Overview
 
 The Model Configuration system (`ModelConfigService`) enables deterministic
-control over model generation. It decouples the requested model identifier (for
-example, a CLI flag or agent request) from the underlying API configuration.
-This allows for:
+control over model generation. It decouples the requested model identifier
+(e.g., a CLI flag or agent request) from the underlying API configuration. This
+allows for:
 
 - **Precise Hyperparameter Tuning**: Direct control over `temperature`, `topP`,
   `thinkingBudget`, and other SDK-level parameters.
 - **Environment-Specific Behavior**: Distinct configurations for different
-  operating contexts (for example, testing vs. production).
+  operating contexts (e.g., testing vs. production).
 - **Agent-Scoped Customization**: Applying specific settings only when a
   particular agent is active.
 
@@ -73,7 +71,7 @@ context. They are evaluated dynamically for each model request.
   specified `match` properties.
   - `model`: Matches the requested model name or alias.
   - `overrideScope`: Matches the distinct scope of the request (typically the
-    agent name, for example, `codebaseInvestigator`).
+    agent name, e.g., `codebaseInvestigator`).
 
 **Example Override**:
 
@@ -115,8 +113,8 @@ and `overrideScope`).
 1.  **Filtering**: All matching overrides are identified.
 2.  **Sorting**: Matches are prioritized by **specificity** (the number of
     matched keys in the `match` object).
-    - Specific matches (for example, `model` + `overrideScope`) override broad
-      matches (for example, `model` only).
+    - Specific matches (e.g., `model` + `overrideScope`) override broad matches
+      (e.g., `model` only).
     - Tie-breaking: If specificity is equal, the order of definition in the
       `overrides` array is preserved (last one wins).
 3.  **Merging**: The configurations from the sorted overrides are merged
@@ -130,10 +128,10 @@ The configuration follows the `ModelConfigServiceConfig` interface.
 
 Defines the actual parameters for the model.
 
-| Property                | Type     | Description                                                               |
-| :---------------------- | :------- | :------------------------------------------------------------------------ |
-| `model`                 | `string` | The identifier of the model to be called (for example, `gemini-2.5-pro`). |
-| `generateContentConfig` | `object` | The configuration object passed to the `@google/genai` SDK.               |
+| Property                | Type     | Description                                                        |
+| :---------------------- | :------- | :----------------------------------------------------------------- |
+| `model`                 | `string` | The identifier of the model to be called (e.g., `gemini-2.5-pro`). |
+| `generateContentConfig` | `object` | The configuration object passed to the `@google/genai` SDK.        |
 
 ### `GenerateContentConfig` (Common Parameters)
 
@@ -144,7 +142,7 @@ Directly maps to the SDK's `GenerateContentConfig`. Common parameters include:
 - **`topP`**: (`number`) Nucleus sampling probability.
 - **`maxOutputTokens`**: (`number`) Limit on generated response length.
 - **`thinkingConfig`**: (`object`) Configuration for models with reasoning
-  capabilities (for example, `thinkingBudget`, `includeThoughts`).
+  capabilities (e.g., `thinkingBudget`, `includeThoughts`).
 
 ## 5. Practical Examples
 
@@ -172,7 +170,7 @@ configuration but enforcing zero temperature.
 ### Agent-Specific Parameter Injection
 
 Enforce extended thinking budgets for a specific agent without altering the
-global default, for example for the `codebaseInvestigator`.
+global default, e.g. for the `codebaseInvestigator`.
 
 ```json
 "modelConfigs": {

docs/cli/model-routing.md

@@ -10,8 +10,8 @@ Model routing is managed by the `ModelAvailabilityService`, which monitors model
 health and automatically routes requests to available models based on defined
 policies.
 
-1.  **Model failure:** If the currently selected model fails (for example, due
-    to quota or server errors), the CLI will initiate the fallback process.
+1.  **Model failure:** If the currently selected model fails (e.g., due to quota
+    or server errors), the CLI will initiate the fallback process.
 
 2.  **User consent:** Depending on the failure and the model's policy, the CLI
     may prompt you to switch to a fallback model (by default always prompts
@@ -34,11 +34,11 @@ Gemini CLI will use a locally-running **Gemma** model to make routing decisions
 reduce costs associated with hosted model usage while offering similar routing
 decision latency and quality.
 
-The easiest way to set this up is using the automated `gemini gemma setup`
-command.
+In order to use this feature, the local Gemma model **must** be served behind a
+Gemini API and accessible via HTTP at an endpoint configured in `settings.json`.
 
 For more details on how to configure local model routing, see
-[`gemini gemma` — Local Model Routing Setup](../core/gemma-setup.md).
+[Local Model Routing](../core/local-model-routing.md).
 
 ### Model selection precedence
 

docs/cli/model-steering.md

@@ -19,7 +19,7 @@ Model steering is an experimental feature and is disabled by default. You can
 enable it using the `/settings` command or by updating your `settings.json`
 file.
 
-1.  Type `/settings` in Gemini CLI.
+1.  Type `/settings` in the Gemini CLI.
 2.  Search for **Model Steering**.
 3.  Set the value to **true**.