feat(gemini): gemini cleanup and refactor

registry/coder-labs/modules/gemini/README.md

@@ -1,36 +1,41 @@
 ---
 display_name: Gemini CLI
+description: Run Gemini CLI in your workspace for AI pair programming
 icon: ../../../../.icons/gemini.svg
-description: Run Gemini CLI in your workspace with AgentAPI integration
 verified: true
 tags: [agent, gemini, ai, google, tasks]
 ---
 
 # Gemini CLI
 
-Run [Gemini CLI](https://ai.google.dev/gemini-api/docs/cli) in your workspace to access Google's Gemini AI models, and custom pre/post install scripts. This module integrates with [AgentAPI](https://github.com/coder/agentapi) for Coder Tasks compatibility.
+Run [Gemini CLI](https://github.com/google-gemini/gemini-cli) in your workspace to access Google's Gemini AI models for interactive coding assistance and automated task execution.
 
 ```tf
 module "gemini" {
-  source           = "registry.coder.com/coder-labs/gemini/coder"
-  version          = "1.0.0"
-  agent_id         = coder_agent.example.id
-  gemini_api_key   = var.gemini_api_key
-  gemini_model     = "gemini-2.5-pro"
-  install_gemini   = true
-  gemini_version   = "latest"
-  agentapi_version = "latest"
+  source   = "registry.coder.com/coder-labs/gemini/coder"
+  version  = "1.1.0"
+  agent_id = coder_agent.example.id
+  folder   = "/home/coder/project"
 }
 ```
 
+## Features
+
+- **Interactive AI Assistance**: Run Gemini CLI directly in your terminal for coding help
+- **Automated Task Execution**: Execute coding tasks automatically via AgentAPI integration
+- **Multiple AI Models**: Support for Gemini 2.5 Pro, Flash, and other Google AI models
+- **API Key Integration**: Seamless authentication with Gemini API
+- **MCP Server Integration**: Built-in Coder MCP server for task reporting
+- **Persistent Sessions**: Maintain context across workspace sessions
+
 ## Prerequisites
 
-- You must add the [Coder Login](https://registry.coder.com/modules/coder-login/coder) module to your template
 - Node.js and npm will be installed automatically if not present
+- The [Coder Login](https://registry.coder.com/modules/coder/coder-login) module is required
 
-## Usage Example
+## Examples
 
-- Example 1:
+### Basic setup
 
 ```tf
 variable "gemini_api_key" {
@@ -40,39 +45,97 @@ variable "gemini_api_key" {
 }
 
 module "gemini" {
-  count                     = data.coder_workspace.me.start_count
-  source                    = "registry.coder.com/coder-labs/gemini/coder"
-  version                   = "1.0.0"
-  agent_id                  = coder_agent.example.id
-  gemini_api_key            = var.gemini_api_key # we recommend providing this parameter inorder to have a smoother experience (i.e. no google sign-in)
-  gemini_model              = "gemini-2.5-flash"
-  install_gemini            = true
-  gemini_version            = "latest"
-  gemini_instruction_prompt = "Start every response with `Gemini says:`"
+  source         = "registry.coder.com/coder-labs/gemini/coder"
+  version        = "1.1.0"
+  agent_id       = coder_agent.example.id
+  gemini_api_key = var.gemini_api_key
+  folder         = "/home/coder/project"
 }
 ```
 
-## How it Works
+This basic setup will:
+
+- Install Gemini CLI in the workspace
+- Configure authentication with your API key
+- Set Gemini to run in `/home/coder/project` directory
+- Enable interactive use from the terminal
+- Set up MCP server integration for task reporting
+
+### Automated task execution (Experimental)
+
+> This functionality is in early access and is still evolving.
+> For now, we recommend testing it in a demo or staging environment,
+> rather than deploying to production
+>
+> Learn more in [the Coder documentation](https://coder.com/docs/ai-coder)
+
+```tf
+variable "gemini_api_key" {
+  type        = string
+  description = "Gemini API key"
+  sensitive   = true
+}
+
+module "coder-login" {
+  count    = data.coder_workspace.me.start_count
+  source   = "registry.coder.com/coder/coder-login/coder"
+  version  = "~> 1.0"
+  agent_id = coder_agent.example.id
+}
 
-- **Install**: The module installs Gemini CLI using npm (installs Node.js via NVM if needed)
-- **Instruction Prompt**: If `GEMINI_INSTRUCTION_PROMPT` and `GEMINI_START_DIRECTORY` are set, creates the directory (if needed) and writes the prompt to `GEMINI.md`
-- **Start**: Launches Gemini CLI in the specified directory, wrapped by AgentAPI
-- **Environment**: Sets `GEMINI_API_KEY`, `GOOGLE_GENAI_USE_VERTEXAI`, `GEMINI_MODEL` for the CLI (if variables provided)
+data "coder_parameter" "ai_prompt" {
+  type        = "string"
+  name        = "AI Prompt"
+  default     = ""
+  description = "Task prompt for automated Gemini execution"
+  mutable     = true
+}
+
+module "gemini" {
+  count                = data.coder_workspace.me.start_count
+  source               = "registry.coder.com/coder-labs/gemini/coder"
+  version              = "1.1.0"
+  agent_id             = coder_agent.example.id
+  gemini_api_key       = var.gemini_api_key
+  gemini_model         = "gemini-2.5-flash"
+  folder               = "/home/coder/project"
+  task_prompt          = data.coder_parameter.ai_prompt.value
+  enable_yolo_mode     = true # Auto-approve all tool calls for automation
+  gemini_system_prompt = <<-EOT
+    You are a helpful coding assistant. Always explain your code changes clearly.
+    YOU MUST REPORT ALL TASKS TO CODER.
+  EOT
+}
+```
+
+> [!WARNING]
+> YOLO mode automatically approves all tool calls without user confirmation. The agent has access to your machine's file system and terminal. Only enable in trusted, isolated environments.
+
+### Using Vertex AI (Enterprise)
+
+For enterprise users who prefer Google's Vertex AI platform:
+
+```tf
+module "gemini" {
+  source         = "registry.coder.com/coder-labs/gemini/coder"
+  version        = "1.1.0"
+  agent_id       = coder_agent.example.id
+  gemini_api_key = var.gemini_api_key
+  folder         = "/home/coder/project"
+  use_vertexai   = true
+}
+```
 
 ## Troubleshooting
 
-- If Gemini CLI is not found, ensure `install_gemini = true` and your API key is valid
-- Node.js and npm are installed automatically if missing (using NVM)
-- Check logs in `/home/coder/.gemini-module/` for install/start output
-- We highly recommend using the `gemini_api_key` variable, this also ensures smooth tasks running without needing to sign in to Google.
+- If Gemini CLI is not found, ensure your API key is valid (`install_gemini` defaults to `true`)
+- Check logs in `~/.gemini-module/` for install/start output
+- Use the `gemini_api_key` variable to avoid requiring Google sign-in
 
-> [!IMPORTANT]
-> To use tasks with Gemini CLI, ensure you have the `gemini_api_key` variable set, and **you pass the `AI Prompt` Parameter**.
-> By default we inject the "theme": "Default" and "selectedAuthType": "gemini-api-key" to your ~/.gemini/settings.json along with the coder mcp server.
-> In `gemini_instruction_prompt` and `AI Prompt` text we recommend using (\`\`) backticks instead of quotes to avoid escaping issues. Eg: gemini_instruction_prompt = "Start every response with \`Gemini says:\` "
+The module creates log files in the workspace's `~/.gemini-module` directory for debugging purposes.
 
 ## References
 
-- [Gemini CLI Documentation](https://ai.google.dev/gemini-api/docs/cli)
+- [Gemini CLI Documentation](https://github.com/google-gemini/gemini-cli/blob/main/docs/index.md)
 - [AgentAPI Documentation](https://github.com/coder/agentapi)
-- [Coder AI Agents Guide](https://coder.com/docs/tutorials/ai-agents)
+- [Coder AI Agents Guide](https://coder.com/docs/ai-coder)

registry/coder-labs/modules/gemini/main.test.ts

@@ -8,7 +8,6 @@ import {
 } from "bun:test";
 import { execContainer, readFileContainer, runTerraformInit } from "~test";
 import {
-  loadTestFile,
   writeExecutable,
   setup as setupUtil,
   execModuleScript,
@@ -54,10 +53,24 @@ const setup = async (props?: SetupProps): Promise<{ id: string }> => {
     agentapiMockScript: props?.agentapiMockScript,
   });
   if (!props?.skipGeminiMock) {
+    const geminiMockContent = `#!/bin/bash
+
+if [[ "$1" == "--version" ]]; then
+  echo "HELLO: $(bash -c env)"
+  echo "gemini version v2.5.0"
+  exit 0
+fi
+
+set -e
+
+while true; do
+    echo "$(date) - gemini-mock"
+    sleep 15
+done`;
     await writeExecutable({
       containerId: id,
       filePath: "/usr/bin/gemini",
-      content: await loadTestFile(import.meta.dir, "gemini-mock.sh"),
+      content: geminiMockContent,
     });
   }
   return { id };
@@ -70,7 +83,7 @@ describe("gemini", async () => {
     await runTerraformInit(import.meta.dir);
   });
 
-  test("happy-path", async () => {
+  test("agent-api", async () => {
     const { id } = await setup();
     await execModuleScript(id);
     await expectAgentAPIStarted(id);
@@ -117,7 +130,7 @@ describe("gemini", async () => {
     await execModuleScript(id);
 
     const resp = await readFileContainer(id, "/home/coder/.gemini-module/agentapi-start.log");
-    expect(resp).toContain("gemini_api_key provided !");
+    expect(resp).toContain("Using direct Gemini API with API key");
   });
 
   test("use-vertexai", async () => {
@@ -197,6 +210,20 @@ describe("gemini", async () => {
     expect(resp).toContain(prompt);
   });
 
+  test("task-prompt", async () => {
+    const taskPrompt = "Create a simple Hello World function";
+    const { id } = await setup({
+      moduleVariables: {
+        task_prompt: taskPrompt,
+      },
+    });
+    await execModuleScript(id, {
+      GEMINI_TASK_PROMPT: taskPrompt,
+    });
+    const resp = await readFileContainer(id, "/home/coder/.gemini-module/agentapi-start.log");
+    expect(resp).toContain("Running automated task:");
+  });
+
   test("start-without-prompt", async () => {
     const { id } = await setup();
     await execModuleScript(id);

registry/coder-labs/modules/gemini/main.tf

@@ -74,14 +74,14 @@ variable "use_vertexai" {
 
 variable "install_agentapi" {
   type        = bool
-  description = "Whether to install AgentAPI."
+  description = "Whether to install AgentAPI for web UI and task automation."
   default     = true
 }
 
 variable "agentapi_version" {
   type        = string
   description = "The version of AgentAPI to install."
-  default     = "v0.3.0"
+  default     = "v0.2.3"
 }
 
 variable "gemini_model" {
@@ -102,12 +102,10 @@ variable "post_install_script" {
   default     = null
 }
 
-data "coder_parameter" "ai_prompt" {
-  type        = "string"
-  name        = "AI Prompt"
+variable "task_prompt" {
+  type        = string
+  description = "Task prompt for automated Gemini execution"
   default     = ""
-  description = "Initial prompt for the Gemini CLI"
-  mutable     = true
 }
 
 variable "additional_extensions" {
@@ -122,12 +120,24 @@ variable "gemini_system_prompt" {
   default     = ""
 }
 
+variable "enable_yolo_mode" {
+  type        = bool
+  description = "Enable YOLO mode to automatically approve all tool calls without user confirmation. Use with caution."
+  default     = false
+}
+
 resource "coder_env" "gemini_api_key" {
   agent_id = var.agent_id
   name     = "GEMINI_API_KEY"
   value    = var.gemini_api_key
 }
 
+resource "coder_env" "google_api_key" {
+  agent_id = var.agent_id
+  name     = "GOOGLE_API_KEY"
+  value    = var.gemini_api_key
+}
+
 resource "coder_env" "gemini_use_vertex_ai" {
   agent_id = var.agent_id
   name     = "GOOGLE_GENAI_USE_VERTEXAI"
@@ -166,7 +176,7 @@ EOT
 
 module "agentapi" {
   source  = "registry.coder.com/coder/agentapi/coder"
-  version = "1.0.0"
+  version = "1.0.2"
 
   agent_id             = var.agent_id
   web_app_slug         = local.app_slug
@@ -181,22 +191,7 @@ module "agentapi" {
   agentapi_version     = var.agentapi_version
   pre_install_script   = var.pre_install_script
   post_install_script  = var.post_install_script
-  start_script         = <<-EOT
-     #!/bin/bash
-     set -o errexit
-     set -o pipefail
-
-     echo -n '${base64encode(local.start_script)}' | base64 -d > /tmp/start.sh
-     chmod +x /tmp/start.sh
-     GEMINI_API_KEY='${var.gemini_api_key}' \
-     GOOGLE_GENAI_USE_VERTEXAI='${var.use_vertexai}' \
-     GEMINI_MODEL='${var.gemini_model}' \
-     GEMINI_START_DIRECTORY='${var.folder}' \
-     GEMINI_TASK_PROMPT='${base64encode(data.coder_parameter.ai_prompt.value)}' \
-     /tmp/start.sh
-   EOT
-
-  install_script = <<-EOT
+  install_script       = <<-EOT
     #!/bin/bash
     set -o errexit
     set -o pipefail
@@ -209,7 +204,23 @@ module "agentapi" {
     BASE_EXTENSIONS='${base64encode(replace(local.base_extensions, "'", "'\\''"))}' \
     ADDITIONAL_EXTENSIONS='${base64encode(replace(var.additional_extensions != null ? var.additional_extensions : "", "'", "'\\''"))}' \
     GEMINI_START_DIRECTORY='${var.folder}' \
-    GEMINI_INSTRUCTION_PROMPT='${base64encode(var.gemini_system_prompt)}' \
+    GEMINI_SYSTEM_PROMPT='${base64encode(var.gemini_system_prompt)}' \
     /tmp/install.sh
   EOT
+  start_script         = <<-EOT
+     #!/bin/bash
+     set -o errexit
+     set -o pipefail
+
+     echo -n '${base64encode(local.start_script)}' | base64 -d > /tmp/start.sh
+     chmod +x /tmp/start.sh
+     GEMINI_API_KEY='${var.gemini_api_key}' \
+     GOOGLE_API_KEY='${var.gemini_api_key}' \
+     GOOGLE_GENAI_USE_VERTEXAI='${var.use_vertexai}' \
+     GEMINI_YOLO_MODE='${var.enable_yolo_mode}' \
+     GEMINI_MODEL='${var.gemini_model}' \
+     GEMINI_START_DIRECTORY='${var.folder}' \
+     GEMINI_TASK_PROMPT='${var.task_prompt}' \
+     /tmp/start.sh
+   EOT
 }