@mmmbuto/gemini-cli-termux 0.30.3-termux → 0.30.5-termux

package/README.md

@@ -1,232 +1,81 @@
-# 🤖 Gemini CLI – Termux Edition
+# Gemini CLI Termux Edition
 
-Android/Termux optimized fork of **Google Gemini CLI**
-(`google-gemini/gemini-cli`).
+Termux-only fork of Google Gemini CLI for Android devices.
 
-- ✅ Tracks upstream regularly
-- ✅ Minimal, Termux-focused patches
-- ✅ Tested release: **v0.30.0-termux** (tag: `v0.30.0-termux`)
+This fork keeps upstream updates and applies a small Termux patch set focused on runtime stability.
 
-[![npm](https://img.shields.io/npm/v/@mmmbuto/gemini-cli-termux?style=flat-square&logo=npm)](https://www.npmjs.com/package/@mmmbuto/gemini-cli-termux)
-[![downloads](https://img.shields.io/npm/dt/@mmmbuto/gemini-cli-termux?style=flat-square)](https://www.npmjs.com/package/@mmmbuto/gemini-cli-termux)
-[![license](https://img.shields.io/badge/license-Apache--2.0-blue?style=flat-square)](./LICENSE)
-[![ko-fi](https://img.shields.io/badge/%E2%98%95%20Support-Ko--fi-FF5E5B?style=flat-square&logo=ko-fi)](https://ko-fi.com/dionanos)
+## Scope
 
----
+- Termux / Android only
+- Release versions use the `-termux` suffix (no nightly naming in fork releases)
+- Upstream base for this branch: `v0.30.0-nightly.20260224.544df749a`
 
-<div align="center">
-  <img src="./docs/assets/hero.png" alt="Gemini CLI Termux screenshot" width="800" />
-</div>
+## Termux Features Kept
 
-## What is this?
+- ARM64 PTY support via `@mmmbuto/pty-termux-utils` + `@mmmbuto/node-pty-android-arm64`
+- `termux-open-url` integration for auth/browser flows
+- TTS tool: `tts_notification` (uses `termux-tts-speak`)
+- Termux-safe build/bundle scripts (`prepare-termux`, Android build path)
+- Bundle update-check metadata (`bundle/package.json`)
+- Termux helper scripts (`scripts/termux-tools/*`, `scripts/termux-setup.sh`)
 
-This repository packages a **Termux-first build** of Gemini CLI:
-
-- **Upstream project**: https://github.com/google-gemini/gemini-cli
-- **Upstream docs**: https://geminicli.com/docs/
-- **This fork**: https://github.com/DioNanos/gemini-cli-termux
-
-If you are on **macOS / Linux / Windows**, you should install the upstream
-package:
-
-```bash
-npm install -g @google/gemini-cli
-```
-
----
-
-## Why a Termux fork?
-
-Gemini CLI is designed for desktop platforms. On Termux/Android, a few
-dependencies and environment assumptions can break or degrade UX.
-
-This fork keeps the upstream experience intact while adding the **smallest
-possible patch-set** to make it reliable on Android:
-
-- Native **ARM64 PTY** support (no node-gyp build on device)
-- Termux-friendly clipboard detection
-- Mobile filesystem + environment guardrails
-- **Context Memory** integration (persistent memory in
-  `~/.gemini/context_memory/`)
-- **TTS (Text-to-Speech)** support via `termux-tts-speak`
-
----
-
-## Installation (Termux)
-
-### Prerequisites
+## Install (Termux)
 
 ```bash
 pkg update && pkg upgrade -y
-pkg install -y nodejs-lts
-```
-
-Optional but recommended for a better mobile experience:
-
-```bash
-pkg install -y termux-api
-```
-
-### Install
-
-```bash
+pkg install -y nodejs-lts termux-api
 npm install -g @mmmbuto/gemini-cli-termux@latest
 
 gemini --version
 ```
 
-### Update
+## Quick Checks (Termux)
 
 ```bash
-npm install -g @mmmbuto/gemini-cli-termux@latest
+which termux-open-url
+which termux-tts-speak
+node -e "console.log(process.platform, process.env.PREFIX)"
+gemini --version
 ```
 
-### Upstream release channels
+## TTS Tool
 
-Upstream publishes `latest`, `preview`, and `nightly` builds. This fork is meant
-to track upstream **stable** while keeping Termux fixes.
+The `tts_notification` tool is available in the fork and uses `termux-tts-speak`.
 
----
+Enable notifications in `/settings` (`General -> Enable Notifications`) to allow TTS alerts.
 
-## Quick start
-
-Interactive mode:
+## Build From Source (Termux)
 
 ```bash
-cd /path/to/your/project
-
-gemini
-```
-
-Useful slash commands inside the session:
-
-```text
-/help
-/auth
+git clone https://github.com/DioNanos/gemini-cli-termux.git
+cd gemini-cli-termux
+npm install
+npm run build
+npm run bundle
+node bundle/gemini.js --version
 ```
 
-Headless / CI usage:
+Alternative helper:
 
 ```bash
-gemini -p "Explain the project structure" \
-  -o json
+bash scripts/termux-setup.sh
 ```
 
----
-
-## Authentication
-
-Gemini CLI supports multiple authentication methods (Google login, Gemini API
-key, Vertex AI). Termux users can use the same options as upstream.
-
-### Interactive (recommended)
+## Patch Verification
 
-Start `gemini`, then run:
+Run the local patch integrity check after merges:
 
 ```bash
-/auth
+bash scripts/check-termux-patches.sh
 ```
 
-Follow the on-screen flow.
-
-> Note (Android): Google login uses a browser flow that redirects to a
-> `localhost` URL the CLI listens on during setup. Use the browser on the same
-> device.
-
-### Environment variables (headless / CI)
-
-**Gemini API key (Google AI Studio):**
-
-```bash
-export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"
-```
-
-**Vertex AI (examples):**
-
-```bash
-export GOOGLE_GENAI_USE_VERTEXAI=true
-export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
-export GOOGLE_CLOUD_LOCATION="us-central1"
-
-# Option A: API key
-export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
-
-# Option B: Service account
-# export GOOGLE_APPLICATION_CREDENTIALS="/absolute/path/to/keyfile.json"
-```
-
-**Persisting without leaking secrets:** create a `.gemini/.env` file
-(project-level) or `~/.gemini/.env` (user-level).
-
-Full docs:
-
-- https://google-gemini.github.io/gemini-cli/docs/get-started/authentication.html
-
----
-
-## Termux optimizations
-
-This fork applies a minimal set of Termux-specific fixes:
-
-- **Clipboard detection fixes** for Android/Termux environments.
-- **ARM64 PTY prebuild** for responsive interactive UI on Android.
-- **Termux-API tool discovery** (when `termux-api` is installed).
-- **Mobile-safe guards** (avoids desktop-only assumptions for paths, keychains,
-  etc.).
-- **googleSearch tool fix** - works without requiring additional NPM installs.
-
-See `docs/TERMUX.md` for Termux-specific documentation.
-
----
-
-## Known differences vs upstream (v0.30.0-termux)
-
-**Termux ARM64 (Android):**
-
-- **PTY**: ✅ loaded correctly via @mmmbuto/node-pty-android-arm64
-- **Termux-API**: ✅ detection & discovery OK
-- **Context Memory**: ✅ **Fixed** in v0.30.0-termux
-- **TTS**: ✅ Works via `termux-tts-speak`
-- **Update check**: ✅ Points to `@mmmbuto/gemini-cli-termux` on npm
-
-Full reports in [`test-reports/`](./test-reports/) directory.
-
----
-
 ## Documentation
 
-- **Test Suite**: [`test-reports/suites/basic-smoke.md`](./test-reports/suites/basic-smoke.md)
-- **Test Reports**: [`test-reports/`](./test-reports/)
-- **Changelog**: [`CHANGELOG.md`](./CHANGELOG.md)
-- **Context Memory**: `docs/cli/context-memory.md`
-- **Termux-specific docs**: `docs/TERMUX.md`
-
----
-
-## Build from source (Termux)
-
-```bash
-git clone https://github.com/DioNanos/gemini-cli-termux.git
-cd gemini-cli-termux
-npm install
-npm run build && npm run bundle
-node bundle/gemini.js --version
-```
-
----
-
-## Disclaimer
-
-This is an **independent community fork** created to improve the Termux
-experience.
-
-Gemini CLI is an upstream project by Google, licensed under Apache-2.0.
-
----
-
-## Support
+- [CHANGELOG.md](./CHANGELOG.md)
+- [test-reports/README.md](./test-reports/README.md)
+- `docs/TERMUX.md`
 
-If this project saved you time (or helped you run real work from your phone),
-you can support it here:
+## Upstream
 
-- ☕ Ko-fi: https://ko-fi.com/dionanos
+- Upstream project: <https://github.com/google-gemini/gemini-cli>
+- This fork: <https://github.com/DioNanos/gemini-cli-termux>

package/bundle/docs/cli/settings.md

@@ -112,15 +112,14 @@ they appear in the UI.
 
 ### Security
 
-| UI Label                              | Setting                                         | Description                                                                                                                                                                                                                          | Default |
-| ------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------- |
-| Disable YOLO Mode                     | `security.disableYoloMode`                      | Disable YOLO mode, even if enabled by a flag.                                                                                                                                                                                        | `false` |
-| Allow Permanent Tool Approval         | `security.enablePermanentToolApproval`          | Enable the "Allow for all future sessions" option in tool confirmation dialogs.                                                                                                                                                      | `false` |
-| Blocks extensions from Git            | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.                                                                                                                                                                                   | `false` |
-| Extension Source Regex Allowlist      | `security.allowedExtensions`                    | List of Regex patterns for allowed extensions. If nonempty, only extensions that match the patterns in this list are allowed. Overrides the blockGitExtensions setting.                                                              | `[]`    |
-| Folder Trust                          | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.                                                                                                                                                                                    | `true`  |
-| Enable Environment Variable Redaction | `security.environmentVariableRedaction.enabled` | Enable redaction of environment variables that may contain secrets.                                                                                                                                                                  | `false` |
-| Enable Context-Aware Security         | `security.enableConseca`                        | Enable the context-aware security checker. This feature uses an LLM to dynamically generate and enforce security policies for tool use based on your prompt, providing an additional layer of protection against unintended actions. | `false` |
+| UI Label                              | Setting                                         | Description                                                                                                                                                             | Default |
+| ------------------------------------- | ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Disable YOLO Mode                     | `security.disableYoloMode`                      | Disable YOLO mode, even if enabled by a flag.                                                                                                                           | `false` |
+| Allow Permanent Tool Approval         | `security.enablePermanentToolApproval`          | Enable the "Allow for all future sessions" option in tool confirmation dialogs.                                                                                         | `false` |
+| Blocks extensions from Git            | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.                                                                                                                      | `false` |
+| Extension Source Regex Allowlist      | `security.allowedExtensions`                    | List of Regex patterns for allowed extensions. If nonempty, only extensions that match the patterns in this list are allowed. Overrides the blockGitExtensions setting. | `[]`    |
+| Folder Trust                          | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.                                                                                                                       | `true`  |
+| Enable Environment Variable Redaction | `security.environmentVariableRedaction.enabled` | Enable redaction of environment variables that may contain secrets.                                                                                                     | `false` |
 
 ### Advanced
 

package/bundle/docs/extensions/reference.md

@@ -116,9 +116,7 @@ The manifest file defines the extension's behavior and configuration.
   "description": "My awesome extension",
   "mcpServers": {
     "my-server": {
-      "command": "node",
-      "args": ["${extensionPath}/my-server.js"],
-      "cwd": "${extensionPath}"
+      "command": "node my-server.js"
     }
   },
   "contextFileName": "GEMINI.md",
@@ -126,41 +124,19 @@ The manifest file defines the extension's behavior and configuration.
 }
 ```
 
-- `name`: The name of the extension. This is used to uniquely identify the
-  extension and for conflict resolution when extension commands have the same
-  name as user or project commands. The name should be lowercase or numbers and
-  use dashes instead of underscores or spaces. This is how users will refer to
-  your extension in the CLI. Note that we expect this name to match the
-  extension directory name.
-- `version`: The version of the extension.
-- `description`: A short description of the extension. This will be displayed on
-  [geminicli.com/extensions](https://geminicli.com/extensions).
-- `mcpServers`: A map of MCP servers to settings. The key is the name of the
-  server, and the value is the server configuration. These servers will be
-  loaded on startup just like MCP servers defined in a
-  [`settings.json` file](../reference/configuration.md). If both an extension
-  and a `settings.json` file define an MCP server with the same name, the server
-  defined in the `settings.json` file takes precedence.
-  - Note that all MCP server configuration options are supported except for
-    `trust`.
-  - For portability, you should use `${extensionPath}` to refer to files within
-    your extension directory.
-  - Separate your executable and its arguments using `command` and `args`
-    instead of putting them both in `command`.
-- `contextFileName`: The name of the file that contains the context for the
-  extension. This will be used to load the context from the extension directory.
-  If this property is not used but a `GEMINI.md` file is present in your
-  extension directory, then that file will be loaded.
-- `excludeTools`: An array of tool names to exclude from the model. You can also
-  specify command-specific restrictions for tools that support it, like the
-  `run_shell_command` tool. For example,
-  `"excludeTools": ["run_shell_command(rm -rf)"]` will block the `rm -rf`
-  command. Note that this differs from the MCP server `excludeTools`
-  functionality, which can be listed in the MCP server config.
-
-When Gemini CLI starts, it loads all the extensions and merges their
-configurations. If there are any conflicts, the workspace configuration takes
-precedence.
+- `name`: A unique identifier for the extension. Use lowercase letters, numbers,
+  and dashes. This name must match the extension's directory name.
+- `version`: The current version of the extension.
+- `description`: A short summary shown in the extension gallery.
+- <a id="mcp-servers"></a>`mcpServers`: A map of Model Context Protocol (MCP)
+  servers. Extension servers follow the same format as standard
+  [CLI configuration](../reference/configuration.md).
+- `contextFileName`: The name of the context file (defaults to `GEMINI.md`). Can
+  also be an array of strings to load multiple context files.
+- `excludeTools`: An array of tools to block from the model. You can restrict
+  specific arguments, such as `run_shell_command(rm -rf)`.
+- `themes`: An optional list of themes provided by the extension. See
+  [Themes](../cli/themes.md) for more information.
 
 ### Extension settings
 

package/bundle/docs/hooks/reference.md

@@ -98,8 +98,6 @@ and parameter rewriting.
   - `tool_name`: (`string`) The name of the tool being called.
   - `tool_input`: (`object`) The raw arguments generated by the model.
   - `mcp_context`: (`object`) Optional metadata for MCP-based tools.
-  - `original_request_name`: (`string`) The original name of the tool being
-    called, if this is a tail tool call.
 - **Relevant Output Fields**:
   - `decision`: Set to `"deny"` (or `"block"`) to prevent the tool from
     executing.
@@ -122,18 +120,12 @@ hiding sensitive output from the agent.
   - `tool_response`: (`object`) The result containing `llmContent`,
     `returnDisplay`, and optional `error`.
   - `mcp_context`: (`object`)
-  - `original_request_name`: (`string`) The original name of the tool being
-    called, if this is a tail tool call.
 - **Relevant Output Fields**:
   - `decision`: Set to `"deny"` to hide the real tool output from the agent.
   - `reason`: Required if denied. This text **replaces** the tool result sent
     back to the model.
   - `hookSpecificOutput.additionalContext`: Text that is **appended** to the
     tool result for the agent.
-  - `hookSpecificOutput.tailToolCallRequest`: (`{ name: string, args: object }`)
-    A request to execute another tool immediately after this one. The result of
-    this "tail call" will replace the original tool's response. Ideal for
-    programmatic tool routing.
   - `continue`: Set to `false` to **kill the entire agent loop** immediately.
 - **Exit Code 2 (Block Result)**: Hides the tool result. Uses `stderr` as the
   replacement content sent to the agent. **The turn continues.**

package/bundle/docs/reference/configuration.md

@@ -873,14 +873,6 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `undefined`
   - **Requires restart:** Yes
 
-- **`security.enableConseca`** (boolean):
-  - **Description:** Enable the context-aware security checker. This feature
-    uses an LLM to dynamically generate and enforce security policies for tool
-    use based on your prompt, providing an additional layer of protection
-    against unintended actions.
-  - **Default:** `false`
-  - **Requires restart:** Yes
-
 #### `advanced`
 
 - **`advanced.autoConfigureMemory`** (boolean):