rework the docker:shell script to reuse an existing container

* changeset version bump

* Updating CHANGELOG.md format

* Update changelog for version 3.37.1

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions <github-actions@github.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>

.clinerules/hooks/PostToolUse.example

@@ -1,54 +1,19 @@
 #!/usr/bin/env bash
-# PostToolUse Hook Example
-# 
-# This hook runs AFTER a tool is executed. It can:
-# 1. Observe tool results and outcomes
-# 2. Add context for FUTURE tool uses via contextModification
-# 3. Log or track tool usage patterns
-#
-# IMPORTANT: Context injection affects FUTURE AI decisions, not the current tool execution.
-# The tool has already completed when this hook runs.
 
-# Read the hook input (JSON via stdin)
+echo "PostToolUse running inside local cline/.clinerules/hooks/ directory"
+
 input=$(cat)
+echo $input | jq .
 
-# Extract tool information
-tool_name=$(echo "$input" | jq -r '.postToolUse.toolName // "unknown"')
-parameters=$(echo "$input" | jq -r '.postToolUse.parameters // {}')
-result=$(echo "$input" | jq -r '.postToolUse.result // ""')
-success=$(echo "$input" | jq -r '.postToolUse.success // false')
-execution_time=$(echo "$input" | jq -r '.postToolUse.executionTimeMs // 0')
+for i in {1..5}; do
+  sleep 1
+  echo "$i"
+done
 
-# Example 1: Learning from file operations
-# Track successful file creations to build context about project structure
-# if [[ "$tool_name" == "write_to_file" && "$success" == "true" ]]; then
-#   path=$(echo "$parameters" | jq -r '.path // ""')
-#   cat <<EOF
-# {
-#   "shouldContinue": true,
-#   "contextModification": "FILE_OPERATIONS: Successfully created '$path'. Future operations should maintain consistency with this file's patterns and structure."
-# }
-# EOF
-#   exit 0
-# fi
-
-# Example 2: Performance monitoring
-# Warn about slow operations
-# if [[ "$execution_time" -gt 5000 ]]; then
-#   cat <<EOF
-# {
-#   "shouldContinue": true,
-#   "contextModification": "PERFORMANCE: Tool '$tool_name' took ${execution_time}ms to complete. Consider optimizing future similar operations or breaking them into smaller steps."
-# }
-# EOF
-#   exit 0
-# fi
-
-# Example 3: Context injection for future tool uses
-# The context will be available in the NEXT API request
 cat <<EOF
 {
-  "shouldContinue": true,
-  "contextModification": "TOOL_RESULT: The tool '$tool_name' completed with success=$success. Consider validating the results before proceeding to the next step."
+  "cancel": false,
+  "contextModification": "PostToolUse response from the local cline/.clinerules/hooks/ directory.",
+  "errorMessage": "PostToolUse hook custom errorMessage"
 }
 EOF

.clinerules/hooks/PreToolUse.example

@@ -1,42 +1,19 @@
 #!/usr/bin/env bash
-# PreToolUse Hook Example
-# 
-# This hook runs BEFORE a tool is executed. It can:
-# 1. Block execution by returning {"shouldContinue": false}
-# 2. Add context for FUTURE tool uses via contextModification
-# 3. Validate tool parameters
-#
-# IMPORTANT: Context injection affects FUTURE AI decisions, not the current tool execution.
-# The tool parameters are already determined when this hook runs.
 
-# Read the hook input (JSON via stdin)
+echo "PreToolUse running inside local cline/.clinerules/hooks/ directory"
+
 input=$(cat)
+echo $input | jq .
 
-# Extract tool information
-tool_name=$(echo "$input" | jq -r '.preToolUse.toolName // "unknown"')
-parameters=$(echo "$input" | jq -r '.preToolUse.parameters // {}')
+for i in {1..5}; do
+  sleep 1
+  echo "$i"
+done
 
-# Example 1: Validation - Block invalid operations
-# Uncomment to prevent creating .js files in a TypeScript project
-# if [[ "$tool_name" == "write_to_file" ]]; then
-#   path=$(echo "$parameters" | jq -r '.path // ""')
-#   if [[ "$path" == *.js ]]; then
-#     cat <<EOF
-# {
-#   "shouldContinue": false,
-#   "errorMessage": "VALIDATION FAILED: Cannot create .js files in TypeScript project. Please use .ts extension instead.",
-#   "contextModification": "WORKSPACE_RULES: This is a strict TypeScript project. All new files must use .ts or .tsx extensions."
-# }
-# EOF
-#     exit 0
-#   fi
-# fi
-
-# Example 2: Context injection for future tool uses
-# The context will be available in the NEXT API request after this tool completes
 cat <<EOF
 {
-  "shouldContinue": true,
-  "contextModification": "WORKSPACE_RULES: [For future tool uses] This is a TypeScript React project. When creating files, use .ts/.tsx extensions and include detailed comments explaining the purpose and usage of each function."
+  "cancel": false,
+  "contextModification": "PreToolUse response from the local cline/.clinerules/hooks/ directory.",
+  "errorMessage": "PreToolUse hook custom errorMessage"
 }
 EOF

.clinerules/hooks/README.md

@@ -3,8 +3,8 @@
 ## Overview
 
 Cline hooks allow you to execute custom scripts at specific points in the agentic workflow. Hooks can be placed in either:
-- **Global hooks directory**: `~/Documents/Cline/Rules/Hooks/` (applies to all workspaces)
-- **Workspace hooks directory**: `.clinerules/hooks/` (applies to specific workspace)
+- **Global hooks directory**: `~/Documents/Cline/Hooks/` (applies to all workspaces)
+- **Workspace hooks directory**: `.clinerules/hooks/` (applies to the workspace the repo is part of)
 
 Hooks run automatically when enabled.
 
@@ -17,17 +17,54 @@ Hooks run automatically when enabled.
 
 ## Available Hooks
 
+### TaskStart Hook
+- **When**: Runs when a NEW task is started (not when resuming)
+- **Purpose**: Initialize task context, validate task requirements, set up environment
+- **Global Location**: `~/Documents/Cline/Hooks/TaskStart`
+- **Workspace Location**: `.clinerules/hooks/TaskStart`
+
+### TaskResume Hook
+- **When**: Runs when an EXISTING task is resumed (after user clicks resume button)
+- **Purpose**: Validate resumed task state, restore context, check for changes since last run
+- **Global Location**: `~/Documents/Cline/Hooks/TaskResume`
+- **Workspace Location**: `.clinerules/hooks/TaskResume`
+
+### TaskCancel Hook
+- **When**: Runs when a task is cancelled or a hook is aborted by the user (only if there's actual active work or work was started)
+- **Purpose**: Clean up resources, log cancellation, save state
+- **Global Location**: `~/Documents/Cline/Hooks/TaskCancel`
+- **Workspace Location**: `.clinerules/hooks/TaskCancel`
+- **Note**: This hook is NOT cancellable
+
+### TaskComplete Hook (coming soon!)
+- **When**: Runs when a task is marked as complete
+- **Purpose**: Log completion status, perform final cleanup, generate reports
+- **Global Location**: `~/Documents/Cline/Hooks/TaskComplete`
+- **Workspace Location**: `.clinerules/hooks/TaskComplete`
+
+### UserPromptSubmit Hook
+- **When**: Runs when the user submits a prompt/message (initial task, resume, or feedback)
+- **Purpose**: Validate user input, preprocess prompts, add context to user messages
+- **Global Location**: `~/Documents/Cline/Hooks/UserPromptSubmit`
+- **Workspace Location**: `.clinerules/hooks/UserPromptSubmit`
+
 ### PreToolUse Hook
 - **When**: Runs BEFORE a tool is executed
 - **Purpose**: Validate parameters, block execution, or add context
-- **Global Location**: `~/Documents/Cline/Rules/Hooks/PreToolUse` (all platforms)
-- **Workspace Location**: `.clinerules/hooks/PreToolUse` (all platforms)
+- **Global Location**: `~/Documents/Cline/Hooks/PreToolUse`
+- **Workspace Location**: `.clinerules/hooks/PreToolUse`
 
 ### PostToolUse Hook
 - **When**: Runs AFTER a tool completes
 - **Purpose**: Observe results, track patterns, or add context
-- **Global Location**: `~/Documents/Cline/Rules/Hooks/PostToolUse` (all platforms)
-- **Workspace Location**: `.clinerules/hooks/PostToolUse` (all platforms)
+- **Global Location**: `~/Documents/Cline/Hooks/PostToolUse`
+- **Workspace Location**: `.clinerules/hooks/PostToolUse`
+
+### PreCompact Hook (coming soon!)
+- **When**: Runs BEFORE the conversation context is compacted/truncated
+- **Purpose**: Observe compaction events, log context management, track token usage
+- **Global Location**: `~/Documents/Cline/Hooks/PreCompact`
+- **Workspace Location**: `.clinerules/hooks/PreCompact`
 
 ## Cross-Platform Hook Format
 
@@ -37,13 +74,12 @@ Cline uses a git-style approach for hooks that works consistently across all pla
 - **No file extensions**: Hooks are named exactly `PreToolUse` or `PostToolUse` (no `.bat`, `.cmd`, `.sh` etc.)
 - **Shebang required**: First line must be a shebang (e.g., `#!/usr/bin/env bash` or `#!/usr/bin/env node`)
 - **Executable on Unix**: On Unix/Linux/macOS, hooks must be executable: `chmod +x PreToolUse`
-- **Windows**: No special permissions needed - hooks are executed through the shell
+- **Windows**: Not currently supported.
 
 ### How It Works
 
 Like git hooks, Cline executes hook files through a shell that interprets the shebang line:
 - On Unix/Linux/macOS: Native shell execution with shebang support
-- On Windows: Shell execution handles shebang interpretation
 
 This means:
 - ✅ Same hook script works on all platforms
@@ -55,16 +91,10 @@ This means:
 **On Unix/Linux/macOS:**
 ```bash
 # Create hook file
-nano ~/Documents/Cline/Rules/Hooks/PreToolUse
+nano ~/Documents/Cline/Hooks/PreToolUse
 
 # Make executable
-chmod +x ~/Documents/Cline/Rules/Hooks/PreToolUse
-```
-
-**On Windows:**
-```batch
-REM Create hook file (note: no file extension)
-notepad %USERPROFILE%\Documents\Cline\Rules\Hooks\PreToolUse
+chmod +x ~/Documents/Cline/Hooks/PreToolUse
 ```
 
 ## Context Injection Timing
@@ -107,11 +137,46 @@ All hooks receive:
 ```json
 {
   "clineVersion": "string",
-  "hookName": "PreToolUse" | "PostToolUse",
+  "hookName": "TaskStart" | "TaskResume" | "TaskCancel" | "TaskComplete" | "UserPromptSubmit" | "PreToolUse" | "PostToolUse" | "PreCompact",
   "timestamp": "string",
   "taskId": "string",
   "workspaceRoots": ["string"],
   "userId": "string",
+  "taskStart": {  // Only for TaskStart
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string",
+      "initialTask": "string"
+    }
+  },
+  "taskResume": {  // Only for TaskResume
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string"
+    },
+    "previousState": {
+      "lastMessageTs": "string",
+      "messageCount": "string",
+      "conversationHistoryDeleted": "string"
+    }
+  },
+  "taskCancel": {  // Only for TaskCancel
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string",
+      "completionStatus": "string"
+    }
+  },
+  "taskComplete": {  // Only for TaskComplete
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string"
+    }
+  },
+  "userPromptSubmit": {  // Only for UserPromptSubmit
+    "prompt": "string",
+    "attachments": ["string"]
+  },
   "preToolUse": {  // Only for PreToolUse
     "toolName": "string",
     "parameters": {}
@@ -122,6 +187,11 @@ All hooks receive:
     "result": "string",
     "success": boolean,
     "executionTimeMs": number
+  },
+  "preCompact": {  // Only for PreCompact
+    "contextSize": number,
+    "messagesToCompact": number,
+    "compactionStrategy": "string"
   }
 }
 ```
@@ -131,38 +201,21 @@ All hooks receive:
 All hooks must return:
 ```json
 {
-  "shouldContinue": boolean,           // Required: Allow or block execution
-  "contextModification": "string",      // Optional: Context for future tool uses
+  "cancel": boolean,                   // Required: false to continue, true to block execution
+  "contextModification": "string",     // Optional: Context for future AI decisions
   "errorMessage": "string"             // Optional: Error details if blocking
 }
 ```
 
-## Context Modification Format
-
-Use structured prefixes to help the AI understand context type:
-
-- `WORKSPACE_RULES:` - Project conventions and requirements
-- `FILE_OPERATIONS:` - File creation/modification patterns
-- `TOOL_RESULT:` - Outcomes of tool executions
-- `PERFORMANCE:` - Performance concerns
-- `VALIDATION:` - Validation results
-- Custom prefixes as needed
-
-Example:
-```bash
-cat <<EOF
-{
-  "shouldContinue": true,
-  "contextModification": "WORKSPACE_RULES: This is a TypeScript project. All new files must use .ts or .tsx extensions."
-}
-EOF
-```
+**Note**: The `cancel` field works as follows:
+- `false` (or omitted): Allow execution to continue
+- `true`: Block execution and show error message to user
 
 ## Hook Execution Limits
 
-- **Timeout**: Hooks must complete within 30 seconds
-- **Context Size**: Context modifications are limited to 50KB
-- **Error Handling**: Unexpected file system errors are propagated; expected errors (file not found, permission denied) are handled silently
+- **Timeout**: Hooks must complete within 30 seconds (configurable via `HOOK_EXECUTION_TIMEOUT_MS`)
+- **Context Size**: Context modifications are limited to 50KB (configurable via `MAX_CONTEXT_MODIFICATION_SIZE`)
+- **Error Handling**: Expected errors (file not found, permission denied, not a directory) are handled silently; unexpected file system errors are propagated
 
 ## Common Use Cases
 
@@ -177,15 +230,15 @@ path=$(echo "$input" | jq -r '.preToolUse.parameters.path // ""')
 if [[ "$tool_name" == "write_to_file" && "$path" == *.js ]]; then
   cat <<EOF
 {
-  "shouldContinue": false,
+  "cancel": true,
   "errorMessage": "Cannot create .js files in TypeScript project",
-  "contextModification": "WORKSPACE_RULES: Use .ts/.tsx extensions only"
+  "contextModification": "Use .ts/.tsx extensions only"
 }
 EOF
   exit 0
 fi
 
-echo '{"shouldContinue": true}'
+echo '{"cancel": false}'
 ```
 
 ### 2. Context Building - Learn from Operations
@@ -200,12 +253,12 @@ path=$(echo "$input" | jq -r '.postToolUse.parameters.path // ""')
 if [[ "$tool_name" == "write_to_file" && "$success" == "true" ]]; then
   cat <<EOF
 {
-  "shouldContinue": true,
-  "contextModification": "FILE_OPERATIONS: Created '$path'. Maintain consistency with this file's patterns in future operations."
+  "cancel": false,
+  "contextModification": "Created '$path'. Maintain consistency with this file's patterns in future operations."
 }
 EOF
 else
-  echo '{"shouldContinue": true}'
+  echo '{"cancel": false}'
 fi
 ```
 
@@ -220,12 +273,12 @@ tool_name=$(echo "$input" | jq -r '.postToolUse.toolName')
 if [[ "$execution_time" -gt 5000 ]]; then
   cat <<EOF
 {
-  "shouldContinue": true,
-  "contextModification": "PERFORMANCE: Tool '$tool_name' took ${execution_time}ms. Consider optimizing future similar operations."
+  "cancel": false,
+  "contextModification": "Tool '$tool_name' took ${execution_time}ms. Consider optimizing future similar operations."
 }
 EOF
 else
-  echo '{"shouldContinue": true}'
+  echo '{"cancel": false}'
 fi
 ```
 
@@ -239,7 +292,7 @@ input=$(cat)
 echo "$input" >> ~/.cline/hook-logs/tool-usage.jsonl
 
 # Allow execution
-echo '{"shouldContinue": true}'
+echo '{"cancel": false}'
 ```
 
 ## Global vs Workspace Hooks
@@ -247,44 +300,40 @@ echo '{"shouldContinue": true}'
 Cline supports two levels of hooks:
 
 ### Global Hooks
-- **Location**: `~/Documents/Cline/Rules/Hooks/` (macOS/Linux) or `%USERPROFILE%\Documents\Cline\Rules\Hooks\` (Windows)
+- **Location**: `~/Documents/Cline/Hooks/` (macOS/Linux)
 - **Scope**: Apply to ALL workspaces and projects
 - **Use Case**: Organization-wide policies, personal preferences, universal validations
-- **Priority**: Execute FIRST, before workspace hooks
+- **Priority**: Order not guaranteed when combined with workspace hooks
 
 ### Workspace Hooks
 - **Location**: `.clinerules/hooks/` in each workspace root
 - **Scope**: Apply only to the specific workspace
 - **Use Case**: Project-specific rules, team conventions, repository requirements
-- **Priority**: Execute AFTER global hooks
+- **Priority**: Order not guaranteed when combined with global hooks
 
 ### Hook Execution
 
 When multiple hooks exist (global and/or workspace):
-- All hooks for a given step (PreToolUse or PostToolUse) are executed
-- **Execution order is not guaranteed** - hooks may run concurrently
-- If ALL hooks allow execution (`shouldContinue: true`), the tool proceeds
-- If ANY hook blocks (`shouldContinue: false`), execution is blocked
+- All hooks for a given step are executed **concurrently** using `Promise.all`
+- **Execution order is not guaranteed** - hooks run in parallel
+- If ALL hooks allow execution (`cancel: false`), the tool proceeds
+- If ANY hook blocks (`cancel: true`), execution is blocked
 
 **Result Combination:**
-- `shouldContinue`: Must be `true` from ALL hooks for execution to proceed
-- `contextModification`: All context strings are concatenated
-- `errorMessage`: All error messages are concatenated
+- `cancel`: If ANY hook returns `true`, execution is blocked
+- `contextModification`: All context strings are concatenated with double newlines (`\n\n`)
+- `errorMessage`: All error messages are concatenated with single newlines (`\n`)
 
 ### Setting Up Global Hooks
 
 1. The global hooks directory is automatically created at:
-   - macOS/Linux: `~/Documents/Cline/Rules/Hooks/`
-   - Windows: `%USERPROFILE%\Documents\Cline\Rules\Hooks\`
+   - macOS/Linux: `~/Documents/Cline/Hooks/`
 
 2. Add your hook script:
    ```bash
    # Unix/Linux/macOS
-   nano ~/Documents/Cline/Rules/Hooks/PreToolUse
-   chmod +x ~/Documents/Cline/Rules/Hooks/PreToolUse
-   
-   # Windows
-   notepad %USERPROFILE%\Documents\Cline\Rules\Hooks\PreToolUse
+   nano ~/Documents/Cline/Hooks/PreToolUse
+   chmod +x ~/Documents/Cline/Hooks/PreToolUse
    ```
 
 3. Enable hooks in Cline settings
@@ -294,18 +343,18 @@ When multiple hooks exist (global and/or workspace):
 **Global Hook** (applies to all projects):
 ```bash
 #!/usr/bin/env bash
-# ~/Documents/Cline/Rules/Hooks/PreToolUse
+# ~/Documents/Cline/Hooks/PreToolUse
 # Universal rule: Never delete package.json
 input=$(cat)
 tool_name=$(echo "$input" | jq -r '.preToolUse.toolName')
 path=$(echo "$input" | jq -r '.preToolUse.parameters.path // ""')
 
 if [[ "$tool_name" == "write_to_file" && "$path" == *"package.json"* ]]; then
-  echo '{"shouldContinue": false, "errorMessage": "Global policy: Cannot modify package.json"}'
+  echo '{"cancel": true, "errorMessage": "Global policy: Cannot modify package.json"}'
   exit 0
 fi
 
-echo '{"shouldContinue": true}'
+echo '{"cancel": false}'
 ```
 
 **Workspace Hook** (applies to specific project):
@@ -318,11 +367,11 @@ tool_name=$(echo "$input" | jq -r '.preToolUse.toolName')
 path=$(echo "$input" | jq -r '.preToolUse.parameters.path // ""')
 
 if [[ "$tool_name" == "write_to_file" && "$path" == *.js ]]; then
-  echo '{"shouldContinue": false, "errorMessage": "Project rule: Use .ts files only"}'
+  echo '{"cancel": true, "errorMessage": "Project rule: Use .ts files only"}'
   exit 0
 fi
 
-echo '{"shouldContinue": true}'
+echo '{"cancel": false}'
 ```
 
 **All hooks must allow execution for the tool to proceed.** Hooks may execute concurrently.
@@ -331,7 +380,7 @@ echo '{"shouldContinue": true}'
 
 If you have multiple workspace roots, you can place hooks in each root's `.clinerules/hooks/` directory. All hooks (global and workspace) may execute concurrently. Their results will be combined:
 
-- **shouldContinue**: If ANY hook returns false, execution is blocked
+- **cancel**: If ANY hook returns `true`, execution is blocked
 - **contextModification**: All context modifications are concatenated
 - **errorMessage**: All error messages are concatenated
 
@@ -352,7 +401,6 @@ If you have multiple workspace roots, you can place hooks in each root's `.cline
 
 ### Context Not Affecting Behavior
 - Remember: context affects FUTURE decisions, not the current tool
-- Use PreToolUse for validation (blocking) if you need immediate effect
 - Ensure context modifications are clear and actionable
 - Check that context isn't being truncated (50KB limit)
 

.clinerules/hooks/TaskCancel.example

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+echo "TaskCancel running inside local cline/.clinerules/hooks/ directory"
+
+input=$(cat)
+echo $input | jq .
+
+for i in {1..5}; do
+  sleep 1
+  echo "$i"
+done
+
+cat <<EOF
+{
+  "cancel": false,
+  "contextModification": "TaskCancel response from the local cline/.clinerules/hooks/ directory.",
+  "errorMessage": "TaskCancel hook custom errorMessage"
+}
+EOF

.clinerules/hooks/TaskResume.example

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+echo "TaskResume running inside local cline/.clinerules/hooks/ directory"
+
+input=$(cat)
+echo $input | jq .
+
+for i in {1..5}; do
+  sleep 1
+  echo "$i"
+done
+
+cat <<EOF
+{
+  "cancel": false,
+  "contextModification": "TaskResume response from the local cline/.clinerules/hooks/ directory.",
+  "errorMessage": "TaskResume hook custom errorMessage"
+}
+EOF

.clinerules/hooks/TaskStart.example

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+echo "TaskStart running inside local cline/.clinerules/hooks/ directory"
+
+input=$(cat)
+echo $input | jq .
+
+for i in {1..5}; do
+  sleep 1
+  echo "$i"
+done
+
+cat <<EOF
+{
+  "cancel": false,
+  "contextModification": "TaskStart response from the local cline/.clinerules/hooks/ directory.",
+  "errorMessage": "TaskStart hook custom errorMessage"
+}
+EOF

.clinerules/hooks/UserPromptSubmit.example

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+
+echo "UserPromptSubmit running inside local cline/.clinerules/hooks/ directory"
+
+input=$(cat)
+echo $input | jq .
+
+for i in {1..5}; do
+  sleep 1
+  echo "$i"
+done
+
+cat <<EOF
+{
+  "cancel": false,
+  "contextModification": "UserPromptSubmit response from the local cline/.clinerules/hooks/ directory.",
+  "errorMessage": "UserPromptSubmit hook custom errorMessage"
+}
+EOF

.clinerules/workflows/extension-release.md

@@ -122,9 +122,9 @@ const Announcement = ({ version, hideAnnouncement }: AnnouncementProps) => {
 					title="Previous Updates:"
 					classNames={{
 						trigger: "bg-transparent border-0 pl-0 pb-0 w-fit",
-						title: "font-bold text-[var(--vscode-foreground)]",
+						title: "font-bold text-(--vscode-foreground)",
 						indicator:
-							"text-[var(--vscode-foreground)] mb-0.5 -rotate-180 data-[open=true]:-rotate-90 rtl:rotate-0 rtl:data-[open=true]:-rotate-90",
+							"text-(--vscode-foreground) mb-0.5 -rotate-180 data-[open=true]:-rotate-90 rtl:rotate-0 rtl:data-[open=true]:-rotate-90",
 					}}>
 					<ul style={ulStyle}>
 						<li>

.github/workflows/publish-nightly.yml

@@ -74,10 +74,9 @@ jobs:
                   CLINE_ENVIRONMENT: production
                   # OpenTelemetry production defaults (can be overridden at runtime)
                   OTEL_TELEMETRY_ENABLED: ${{ secrets.OTEL_TELEMETRY_ENABLED }}
-                  OTEL_LOGS_EXPORTER: ${{ secrets.OTEL_LOGS_EXPORTER }}
-                  OTEL_METRICS_EXPORTER: ${{ secrets.OTEL_METRICS_EXPORTER }}
+                  OTEL_LOGS_EXPORTER: console,otlp
+                  OTEL_METRICS_EXPORTER: console,otlp
                   OTEL_EXPORTER_OTLP_PROTOCOL: ${{ secrets.OTEL_EXPORTER_OTLP_PROTOCOL }}
                   OTEL_EXPORTER_OTLP_ENDPOINT: ${{ secrets.OTEL_EXPORTER_OTLP_ENDPOINT }}
                   OTEL_EXPORTER_OTLP_HEADERS: ${{ secrets.OTEL_EXPORTER_OTLP_HEADERS }}
-                  OTEL_METRIC_EXPORT_INTERVAL: ${{ secrets.OTEL_METRIC_EXPORT_INTERVAL }}
               run: npm run publish:marketplace:nightly

.github/workflows/publish.yml

@@ -99,12 +99,11 @@ jobs:
                   ERROR_SERVICE_API_KEY: ${{ secrets.ERROR_SERVICE_API_KEY }}
                   # OpenTelemetry production defaults (can be overridden at runtime)
                   OTEL_TELEMETRY_ENABLED: ${{ secrets.OTEL_TELEMETRY_ENABLED }}
-                  OTEL_LOGS_EXPORTER: ${{ secrets.OTEL_LOGS_EXPORTER }}
-                  OTEL_METRICS_EXPORTER: ${{ secrets.OTEL_METRICS_EXPORTER }}
+                  OTEL_LOGS_EXPORTER: console,otlp
+                  OTEL_METRICS_EXPORTER: console,otlp
                   OTEL_EXPORTER_OTLP_PROTOCOL: ${{ secrets.OTEL_EXPORTER_OTLP_PROTOCOL }}
                   OTEL_EXPORTER_OTLP_ENDPOINT: ${{ secrets.OTEL_EXPORTER_OTLP_ENDPOINT }}
                   OTEL_EXPORTER_OTLP_HEADERS: ${{ secrets.OTEL_EXPORTER_OTLP_HEADERS }}
-                  OTEL_METRIC_EXPORT_INTERVAL: ${{ secrets.OTEL_METRIC_EXPORT_INTERVAL }}
               run: |
                   # Required to generate the .vsix
                   vsce package  --allow-package-secrets sendgrid --out "cline-${{ steps.get_version.outputs.version }}.vsix"

.vscodeignore

@@ -20,6 +20,9 @@ eslint-rules/**
 .husky/**
 .env
 
+# cli
+cli/**
+
 # Custom
 **/demo.gif
 .nvmrc

CHANGELOG.md

@@ -1,12 +1,90 @@
 # Changelog
 
+## 3.37.1
+
+- cf8dd1c: Comprehensive changes to better support GPT 5.1 - System prompt, tools, deep-planning, focus chain, etc.
+- 02abbcf: Add AGENTS.md support
+- 855db7d: feat(models): Add free minimax/mimax-m2 model to the model picker
+
+## [3.37.0]
+
+## Added
+
+- GPT-5.1 with model-specific prompting: tailored system prompts, tool usage, focus chain, and deep-planning optimizations
+- Nous Research provider with Hermes 4 model family and custom system prompts
+- Switched to Aqua Voice's Avalon model in speech to text transcription
+- Added Linux support for speech to text
+- Model-family breakouts for deep-planning prompting, laying groundwork for enhanced slash commands
+- Expanded HTTP proxy support throughout the codebase
+- Improved focus chain prompting for frontier models (Anthropic, OpenAI, Gemini, xAI)
+
+## Fixed
+
+- Duplicate tool results prevention through existence checking
+- XML entity escaping in model content processor
+- Commit message generation in command palette
+- OpenAI Compatible provider temperature parameter type conversion
+
+## Documentation
+
+- Added missing proto generation step in CONTRIBUTING.md
+- New `npm run dev` script for streamlined terminal workflow (fixes #7335)
+
+## [3.36.1]
+
+- fix: remove native tool calling support from Gemini and XAI provider due to invalid tool names issues
+- fix: disable native tool callings for grok code models
+- Add MCP tool usage to GLM
+- Removes reasoning_details content field from Anthropic providers
+
+## [3.36.0]
+
+- Add: Hooks allow you to inject custom logic into Cline's workflow
+- Add: new provider AIhubmix
+- Add: Use http_proxy, https_proxy and no_proxy in JetBrains
+- Fix: Oca Token Refresh logic
+- Fix: issues where assistant message with empty content is added to conversation history
+- Fix: bug where the checkbox shows in the model selector dropdown
+- Fix: Switch from defaultUserAgentProvider to customUserAgent for Bedrock
+- Fix: support for `<think>` tags for better compatibility with open-source models
+- Fix: refinements to the GLM-4.6 system prompt
+
+## [3.35.1]
+
+- Add: Hicap API integration as provider
+- Fix: enable Add Header button in OpenAICompatibleProvider UI
+- Fix: Remove orphaned tool_results after truncation and empty content field issues in native tool call
+- Fix: render model description in markdown
+
+## [3.35.0]
+
+- Add native tool calling support with configurable setting.
+- Auto-approve is now always-on with a redesigned expanding menu. Settings simplified and notifications moved to General Settings.
+- added zai-glm-4.6 as a Cerebras model
+- Created GPT5 family specific system prompt template
+- Fix: show reasoning budget slider to models with valid thinking config
+- Requesty base URL, and API key fixes
+- Delete all Auth Tokens when logging out
+- Support for <think> tags for models that prefer that over <thinking>
+
+## [3.34.1]
+
+- Added support for MiniMax provider with MiniMax-M2 model
+- Remove Cline/code-supernova-1-million model
+- Changes to allow users to manually enter model names (eg. presets) when using OpenRouter
+
+## [3.34.0]
+
+- Cline Teams is now free through 2025 for unlimited users. Includes Jetbrains, RBAC, centralized billing and more.
+- Use the “exacto” versions of GLM-4.6, Kimi-K2, and Qwen3-Coder in the Cline provider for the best balance of cost, speed, accuracy and tool-calling.
+
 ## [3.33.1]
 
 - Fix CLI installation copy text
 
 ## [3.33.0]
 
-- Added Cline CLI (Preview) 
+- Added Cline CLI (Preview)
 - Added Subagent support (Experimental)
 - Added Multi-Root Workspaces support (Enable in feature settings)
 - Add auto-retry with exponential backof for failed API requests

CONTRIBUTING.md

@@ -46,7 +46,11 @@ We also welcome contributions to our [documentation](https://github.com/cline/cl
     ```bash
     npm run install:all
     ```
-4. Launch by pressing `F5` (or `Run`->`Start Debugging`) to open a new VSCode window with the extension loaded. (You may need to install the [esbuild problem matchers extension](https://marketplace.visualstudio.com/items?itemName=connor4312.esbuild-problem-matchers) if you run into issues building the project.)
+4. Generate Protocol Buffer files (required before first build):
+    ```bash
+    npm run protos
+    ```
+5. Launch by pressing `F5` (or `Run`->`Start Debugging`) to open a new VSCode window with the extension loaded. (You may need to install the [esbuild problem matchers extension](https://marketplace.visualstudio.com/items?itemName=connor4312.esbuild-problem-matchers) if you run into issues building the project.)
 
 
 
@@ -85,8 +89,10 @@ We also welcome contributions to our [documentation](https://github.com/cline/cl
 
 2. **Local Development**
     - Run `npm run install:all` to install dependencies
+    - Run `npm run protos` to generate Protocol Buffer files (required before first build)
     - Run `npm run test` to run tests locally
     - Run → Start Debugging or `>Debug: Select and Start Debugging` and wait for a new VS Code instance to open
+    - **Terminal Workflow**: Use `npm run dev` (generates protos + runs watch mode) or `npm run watch` (if protos already generated)
     - Before submitting PR, run `npm run format:fix` to format your code
 
 3. **Linux-specific Setup**

README.md

@@ -2,7 +2,7 @@
 English | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md" target="_blank">Español</a> | <a href="https://github.com/cline/cline/blob/main/locales/de/README.md" target="_blank">Deutsch</a> | <a href="https://github.com/cline/cline/blob/main/locales/ja/README.md" target="_blank">日本語</a> | <a href="https://github.com/cline/cline/blob/main/locales/zh-cn/README.md" target="_blank">简体中文</a> | <a href="https://github.com/cline/cline/blob/main/locales/zh-tw/README.md" target="_blank">繁體中文</a> | <a href="https://github.com/cline/cline/blob/main/locales/ko/README.md" target="_blank">한국어</a>
 </sub></div>
 
-# Cline – \#1 on OpenRouter
+# Cline
 
 <p align="center">
   <img src="https://media.githubusercontent.com/media/cline/cline/main/assets/docs/demo.gif" width="100%" />
@@ -43,7 +43,7 @@ Thanks to [Claude Sonnet's agentic coding capabilities](https://www.anthropic.c
 4. When a task is completed, Cline will present the result to you with a terminal command like `open -a "Google Chrome" index.html`, which you run with a click of a button.
 
 > [!TIP]
-> Use the `CMD/CTRL + Shift + P` shortcut to open the command palette and type "Cline: Open In New Tab" to open the extension as a tab in your editor. This lets you use Cline side-by-side with your file explorer, and see how he changes your workspace more clearly.
+> Follow [this guide](https://docs.cline.bot/features/customization/opening-cline-in-sidebar) to open Cline on the right side of your editor. This lets you use Cline side-by-side with your file explorer, and see how he changes your workspace more clearly.
 
 ---
 

biome.jsonc

@@ -70,7 +70,7 @@
 				"noControlCharactersInRegex": "off",
 				"noShadowRestrictedNames": "off",
 				"noArrayIndexKey": "info",
-				"noAssignInExpressions": "warn"
+				"noAssignInExpressions": "info"
 			},
 			"complexity": {
 				"noUselessConstructor": "off",
@@ -82,7 +82,7 @@
 				"noStaticOnlyClass": "off"
 			},
 			"security": {
-				"noDangerouslySetInnerHtml": "warn"
+				"noDangerouslySetInnerHtml": "info"
 			}
 		}
 	},
@@ -114,17 +114,17 @@
 	"files": {
 		"includes": [
 			"**",
-			"!**/dist/**",
-			"!**/dist-*/**",
-			"!**/out/**",
-			"!**/evals/**",
-			"!**/playwright/**",
-			"!**/test-results/**",
-			"!**/node_modules/**",
-			"!**/webview-ui/build/**",
-			"!**/generated/**",
-			"!**/proto/**",
-			"!**/tests/specs/**"
+			"!**/dist",
+			"!**/dist-*",
+			"!**/out",
+			"!**/evals",
+			"!**/playwright",
+			"!**/test-results",
+			"!**/node_modules",
+			"!**/webview-ui/build",
+			"!**/generated",
+			"!**/proto",
+			"!**/tests/specs"
 		]
 	},
 	"plugins": [

cli/cmd/cline/main.go

@@ -101,10 +101,7 @@ see the manual page: man cline`,
 				if !isUserReadyToUse(ctx, instanceAddress) {
 					// Create renderer for welcome messages
 					renderer := display.NewRenderer(global.Config.OutputFormat)
-
-					markdown := "## hey there! looks like you're new here. let's get you set up"
-					rendered := renderer.RenderMarkdown(markdown)
-					fmt.Printf("\n%s\n\n", rendered)
+					fmt.Printf("\n%s\n\n", renderer.Dim("Hey there! Looks like you're new here. Let's get you set up"))
 
 					if err := auth.HandleAuthMenuNoArgs(ctx); err != nil {
 						// Check if user cancelled - exit cleanly
@@ -119,9 +116,7 @@ see the manual page: man cline`,
 						return fmt.Errorf("credentials still not configured - please run 'cline auth' to complete setup")
 					}
 
-					markdown = "## ✓ setup complete, you can now use the cline cli"
-					rendered = renderer.RenderMarkdown(markdown)
-					fmt.Printf("\n%s\n\n", rendered)
+					fmt.Printf("\n%s\n\n", renderer.Dim("✓ Setup complete, you can now use the Cline CLI"))
 				}
 			} else {
 				// User specified --address flag, use that
@@ -187,6 +182,7 @@ see the manual page: man cline`,
 	rootCmd.AddCommand(cli.NewVersionCommand())
 	rootCmd.AddCommand(cli.NewAuthCommand())
 	rootCmd.AddCommand(cli.NewLogsCommand())
+	// rootCmd.AddCommand(cli.NewDoctorCommand()) // Disabled for now
 
 	if err := rootCmd.ExecuteContext(context.Background()); err != nil {
 		os.Exit(1)
@@ -331,17 +327,20 @@ func getContentFromStdinAndArgs(args []string) (string, error) {
 
 	// Check if data is being piped to stdin
 	if (stat.Mode() & os.ModeCharDevice) == 0 {
-		stdinBytes, err := io.ReadAll(os.Stdin)
-		if err != nil {
-			return "", fmt.Errorf("failed to read from stdin: %w", err)
-		}
-
-		stdinContent := strings.TrimSpace(string(stdinBytes))
-		if stdinContent != "" {
-			if content.Len() > 0 {
-				content.WriteString(" ")
+		// Only try to read if there's actually data available
+		if stat.Size() > 0 {
+			stdinBytes, err := io.ReadAll(os.Stdin)
+			if err != nil {
+				return "", fmt.Errorf("failed to read from stdin: %w", err)
+			}
+
+			stdinContent := strings.TrimSpace(string(stdinBytes))
+			if stdinContent != "" {
+				if content.Len() > 0 {
+					content.WriteString(" ")
+				}
+				content.WriteString(stdinContent)
 			}
-			content.WriteString(stdinContent)
 		}
 	}
 

cli/go.mod

@@ -8,8 +8,10 @@ require (
 	github.com/charmbracelet/bubbletea v1.3.6
 	github.com/charmbracelet/glamour v0.10.0
 	github.com/charmbracelet/huh v0.7.1-0.20251005153135-a01a1e304532
+	github.com/charmbracelet/lipgloss v1.1.1-0.20250404203927-76690c660834
 	github.com/cline/grpc-go v0.0.0
 	github.com/glebarez/go-sqlite v1.22.0
+	github.com/muesli/termenv v0.16.0
 	github.com/spf13/cobra v1.8.0
 	golang.org/x/term v0.32.0
 	google.golang.org/grpc v1.75.0
@@ -24,7 +26,6 @@ require (
 	github.com/aymerick/douceur v0.2.0 // indirect
 	github.com/catppuccin/go v0.3.0 // indirect
 	github.com/charmbracelet/colorprofile v0.2.3-0.20250311203215-f60798e515dc // indirect
-	github.com/charmbracelet/lipgloss v1.1.1-0.20250404203927-76690c660834 // indirect
 	github.com/charmbracelet/x/ansi v0.9.3 // indirect
 	github.com/charmbracelet/x/cellbuf v0.0.13 // indirect
 	github.com/charmbracelet/x/exp/slice v0.0.0-20250327172914-2fdc97757edf // indirect
@@ -45,7 +46,6 @@ require (
 	github.com/muesli/ansi v0.0.0-20230316100256-276c6243b2f6 // indirect
 	github.com/muesli/cancelreader v0.2.2 // indirect
 	github.com/muesli/reflow v0.3.0 // indirect
-	github.com/muesli/termenv v0.16.0 // indirect
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect

cli/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "cline",
-	"version": "1.0.0-nightly.18",
+	"version": "1.0.3",
 	"description": "Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more",
 	"main": "cline-core.js",
 	"bin": {
@@ -20,7 +20,7 @@
 		"vscode-uri"
 	],
 	"engines": {
-		"node": ">=18.0.0"
+		"node": ">=20.0.0"
 	},
 	"keywords": [
 		"cline",

cli/pkg/cli/auth.go

@@ -6,18 +6,38 @@ import (
 )
 
 func NewAuthCommand() *cobra.Command {
-	return &cobra.Command{
+	cmd := &cobra.Command{
 		Use:   "auth",
-		Short: "Authenticate a provider and configure model used",
-		Long: `Authenticate  a provider and configure model used
+		Short: "Authenticate a provider and configure what model is used",
+		Long: `Authenticate a provider and configure what model is used
 
-This command opens an interactive menu where you can:
+Interactive Mode:
+  Run without flags to open an interactive menu where you can:
   - Sign in to your Cline account
   - Configure other LLM providers (Anthropic, OpenAI, etc.)
   - Select and switch between AI models
-  - Manage provider settings`,
+  - Manage provider settings
+
+Quick Setup Mode:
+  Use flags to quickly configure a BYO provider non-interactively:
+  
+  Examples:
+    cline auth --provider openai-native --apikey sk-xxx --modelid gpt-5
+    cline auth -p anthropic -k sk-ant-xxx -m claude-sonnet-4-5-20250929
+    cline auth -p openai-compatible -k xxx -m gpt-4 -b https://api.example.com/v1
+    
+  Supported providers: openai-native, openai, anthropic, gemini, openrouter, xai, cerebras, ollama
+  Note: Bedrock provider requires interactive setup due to complex auth fields`,
 		RunE: func(cmd *cobra.Command, args []string) error {
 			return auth.RunAuthFlow(cmd.Context(), args)
 		},
 	}
+
+	// Add flags for quick setup mode
+	cmd.Flags().StringVarP(&auth.QuickProvider, "provider", "p", "", "Provider ID for quick setup (e.g., openai-native, anthropic)")
+	cmd.Flags().StringVarP(&auth.QuickAPIKey, "apikey", "k", "", "API key for the provider")
+	cmd.Flags().StringVarP(&auth.QuickModelID, "modelid", "m", "", "Model ID to configure (e.g., gpt-4o, claude-sonnet-4-5-20250929)")
+	cmd.Flags().StringVarP(&auth.QuickBaseURL, "baseurl", "b", "", "Base URL (optional, only for openai provider)")
+
+	return cmd
 }

cli/pkg/cli/auth/auth_menu.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 
 	"github.com/charmbracelet/huh"
+	"github.com/cline/cli/pkg/cli/display"
 	"github.com/cline/cli/pkg/cli/global"
 	"github.com/cline/cli/pkg/cli/task"
 	"github.com/cline/grpc-go/cline"
@@ -38,7 +39,7 @@ const (
 //	┃   Change Cline model (only if authenticated)				- hidden if not authenticated
 //	┃   Authenticate with Cline account / Sign out of Cline		- changes based on auth status
 //	┃   Select active provider (Cline or BYO)					- always shown. Used to switch between Cline and BYO providers
-//	┃   Configure API provider									- always shown. Launches provider setup wizard
+//	┃   Configure BYO API providers								- always shown. Launches provider setup wizard
 //	┃   Exit authorization wizard								- always shown. Exits the auth menu
 
 // RunAuthFlow is the entry point for the entire auth flow with instance management
@@ -68,18 +69,25 @@ func RunAuthFlow(ctx context.Context, args []string) error {
 // Main entry point for handling the `cline auth` command
 // HandleAuthCommand routes the auth command based on the number of arguments
 func HandleAuthCommand(ctx context.Context, args []string) error {
+
+	// Check if flags are provided for quick setup
+	if QuickProvider != "" || QuickAPIKey != "" || QuickModelID != "" || QuickBaseURL != "" {
+		if QuickProvider == "" || QuickAPIKey == "" || QuickModelID == "" {
+			return fmt.Errorf("quick setup requires --provider, --apikey, and --modelid flags. Use 'cline auth --help' for more information")
+		}
+		return QuickSetupFromFlags(ctx, QuickProvider, QuickAPIKey, QuickModelID, QuickBaseURL)
+	}
+
 	switch len(args) {
 	case 0:
-		// No args: Show menu (ShowAuthMenuNoArgs)
+		// No args: Show uth wizard
 		return HandleAuthMenuNoArgs(ctx)
-	case 1:
-		// One arg: Provider ID only, prompt for API key
-		return QuickAPISetup(args[0], "")
-	case 2:
-		// Two args: Provider ID and API key
-		return QuickAPISetup(args[0], args[1])
+	case 1, 2, 3, 4:
+		fmt.Println("Invalid positional arguments. Correct usage:")
+		fmt.Println("  cline auth --provider <provider> --apikey <key> --modelid <model> --baseurl <optional>")
+		return nil
 	default:
-		return fmt.Errorf("quick BYO API setup is currently stubbed - not yet implemented")
+		return fmt.Errorf("too many arguments. Use flags for quick setup: --provider, --apikey, --modelid --baseurl(optional)")
 	}
 }
 
@@ -165,32 +173,34 @@ func ShowAuthMenuWithStatus(isClineAuthenticated bool, hasOrganizations bool, cu
 		options = append(options,
 			huh.NewOption("Sign out of Cline", AuthActionClineLogin),
 			huh.NewOption("Select active provider (Cline or BYO)", AuthActionSelectProvider),
-			huh.NewOption("Configure API provider", AuthActionBYOSetup),
+			huh.NewOption("Configure BYO API providers", AuthActionBYOSetup),
 			huh.NewOption("Exit authorization wizard", AuthActionExit),
 		)
 	} else {
 		options = []huh.Option[AuthAction]{
 			huh.NewOption("Authenticate with Cline account", AuthActionClineLogin),
 			huh.NewOption("Select active provider (Cline or BYO)", AuthActionSelectProvider),
-			huh.NewOption("Configure API provider", AuthActionBYOSetup),
+			huh.NewOption("Configure BYO API providers", AuthActionBYOSetup),
 			huh.NewOption("Exit authorization wizard", AuthActionExit),
 		}
 	}
 
 	// Determine menu title based on status
 	var title string
+	renderer := display.NewRenderer(global.Config.OutputFormat)
 
 	// Always show Cline authentication status
 	if isClineAuthenticated {
-		title = "Cline Account: \033[32m✓\033[0m Authenticated\n"
+		title = fmt.Sprintf("Cline Account: %s Authenticated\n", renderer.Green("✓"))
 	} else {
-		title = "Cline Account: \033[31m✗\033[0m Not authenticated\n"
+		title = fmt.Sprintf("Cline Account: %s Not authenticated\n", renderer.Red("✗"))
 	}
 
 	// Show active provider and model if configured (regardless of Cline auth status)
-	// ANSI color codes: Normal intensity = \033[22m, White = \033[37m, Reset = \033[0m
 	if currentProvider != "" && currentModel != "" {
-		title += fmt.Sprintf("Active Provider: \033[22m\033[37m%s\033[0m\nActive Model: \033[22m\033[37m%s\033[0m\n", currentProvider, currentModel)
+		title += fmt.Sprintf("Active Provider: %s\nActive Model: %s\n",
+			renderer.White(currentProvider),
+			renderer.White(currentModel))
 	}
 
 	// Always end with a huh?
@@ -258,11 +268,6 @@ func HandleSelectProvider(ctx context.Context) error {
 		return HandleAuthMenuNoArgs(ctx)
 	}
 
-	if len(providerOptions) == 1 {
-		fmt.Println("Only one provider is configured. Configure another provider to switch between them.")
-		return HandleAuthMenuNoArgs(ctx)
-	}
-
 	providerOptions = append(providerOptions, huh.NewOption("(Cancel)", "cancel"))
 
 	// Show selection menu

cli/pkg/cli/auth/byo_quick_setup.go

@@ -1,13 +1,247 @@
 package auth
 
-import "fmt"
+import (
+	"context"
+	"fmt"
+	"strings"
 
-// QuickAPISetup performs quick provider setup with provider ID and optional API key
-func QuickAPISetup(providerID, apiKey string) error {
-	fmt.Println("Quick BYO API setup is currently stubbed - not yet implemented.")
-	fmt.Printf("Requested provider: %s\n", providerID)
-	if apiKey != "" {
-		fmt.Println("Provided API key:", "<jk redacted>")
+	"github.com/cline/cli/pkg/cli/global"
+	"github.com/cline/cli/pkg/cli/task"
+	"github.com/cline/grpc-go/cline"
+)
+
+// Package-level variables for command-line flags
+var (
+	QuickProvider string // Provider ID (e.g., "openai", "anthropic")
+	QuickAPIKey   string // API key for the provider
+	QuickModelID  string // Model ID to configure
+	QuickBaseURL  string // Base URL (optional, for openai compatible only)
+)
+
+// QuickSetupFromFlags performs quick setup using command-line flags
+// Returns error if validation fails or configuration cannot be applied
+func QuickSetupFromFlags(ctx context.Context, provider, apiKey, modelID, baseURL string) error {
+	// Validate all input parameters
+	providerEnum, err := validateQuickSetupInputs(provider, apiKey, modelID, baseURL)
+	if err != nil {
+		return err
+	}
+
+	// Create task manager for state operations
+	manager, err := createTaskManager(ctx)
+	if err != nil {
+		return fmt.Errorf("failed to create task manager: %w", err)
+	}
+
+	// Validate and fetch model information if needed
+	finalModelID, modelInfo, err := validateAndFetchModel(ctx, manager, providerEnum, modelID, apiKey)
+	if err != nil {
+		return fmt.Errorf("model validation failed: %w", err)
+	}
+
+	// For Ollama, baseURL is stored in the API key field
+	finalAPIKey := apiKey
+	finalBaseURL := baseURL
+	if providerEnum == cline.ApiProvider_OLLAMA {
+		if baseURL != "" {
+			finalAPIKey = baseURL
+			finalBaseURL = ""
+		} else if apiKey != "" {
+			// User provided API key for Ollama - treat it as baseURL
+			finalAPIKey = apiKey
+			finalBaseURL = ""
+		} else {
+			// Use default Ollama baseURL
+			finalAPIKey = "http://localhost:11434"
+			finalBaseURL = ""
+		}
+	}
+
+	// Configure the provider using existing AddProviderPartial function
+	if err := AddProviderPartial(ctx, manager, providerEnum, finalModelID, finalAPIKey, finalBaseURL, modelInfo); err != nil {
+		return fmt.Errorf("failed to configure provider: %w", err)
+	}
+
+	// Set the provider as active for both Plan and Act modes
+	if err := UpdateProviderPartial(ctx, manager, providerEnum, ProviderUpdatesPartial{}, true); err != nil {
+		return fmt.Errorf("failed to set provider as active: %w", err)
+	}
+
+	// Mark welcome view as completed
+	if err := markWelcomeViewCompleted(ctx, manager); err != nil {
+		// Non-fatal error, just log it
+		if global.Config.Verbose {
+			fmt.Printf("[DEBUG] Warning: failed to mark welcome view as completed: %v\n", err)
+		}
+	}
+
+	// Flush pending state changes to disk immediately
+	// This ensures all configuration changes are persisted before the instance terminates
+	if _, err := manager.GetClient().State.FlushPendingState(ctx, &cline.EmptyRequest{}); err != nil {
+		return fmt.Errorf("failed to flush pending state: %w", err)
+	}
+
+	// Success message
+	fmt.Printf("\n✓ Successfully configured %s provider\n", GetProviderDisplayName(providerEnum))
+	fmt.Printf("  Model: %s\n", finalModelID)
+	if providerEnum == cline.ApiProvider_OLLAMA {
+		fmt.Printf("  Base URL: %s\n", finalAPIKey)
+	} else {
+		fmt.Println("  API Key: Configured")
+	}
+	if finalBaseURL != "" {
+		fmt.Printf("  Custom Base URL: %s\n", finalBaseURL)
+	}
+	fmt.Println("\nYou can now use Cline with this provider.")
+	fmt.Println("Run 'cline start' to begin a new task.")
+
+	return nil
+}
+
+// validateQuickSetupInputs validates all input parameters for quick setup
+// Returns the validated provider enum or an error if validation fails
+func validateQuickSetupInputs(provider, apiKey, modelID, baseURL string) (cline.ApiProvider, error) {
+	// Validate required parameters
+	if provider == "" {
+		return cline.ApiProvider_ANTHROPIC, fmt.Errorf("provider is required. Use --provider or -p flag")
+	}
+
+	if strings.TrimSpace(apiKey) == "" && provider != "ollama" {
+		return cline.ApiProvider_ANTHROPIC, fmt.Errorf("API key is required for %s provider. Use --apikey or -k flag", provider)
+	}
+
+	if strings.TrimSpace(modelID) == "" {
+		return cline.ApiProvider_ANTHROPIC, fmt.Errorf("model ID is required. Use --modelid or -m flag")
+	}
+
+	// Validate and map provider string to enum
+	providerEnum, err := validateQuickSetupProvider(provider)
+	if err != nil {
+		return cline.ApiProvider_ANTHROPIC, err
+	}
+
+	// Validate that baseURL is only provided for OpenAI-compatible providers
+	if err := validateBaseURL(baseURL, providerEnum); err != nil {
+		return cline.ApiProvider_ANTHROPIC, err
+	}
+
+	return providerEnum, nil
+}
+
+// validateBaseURL checks if the user's input includes a baseURL for a provider other than OpenAI (compatible)
+// Returns error if baseURL is provided for unsupported providers
+func validateBaseURL(baseURL string, providerEnum cline.ApiProvider) error {
+	if providerEnum != cline.ApiProvider_OPENAI {
+		if baseURL != "" {
+			return fmt.Errorf("base URL is only supported for OpenAI and OpenAI-compatible providers")
+		}
 	}
 	return nil
 }
+
+
+// validateQuickSetupProvider validates the provider ID and returns the enum value
+// Returns error if provider is invalid or not supported for quick setup
+func validateQuickSetupProvider(providerID string) (cline.ApiProvider, error) {
+	// Normalize provider ID (trim whitespace, lowercase)
+	normalizedID := strings.TrimSpace(strings.ToLower(providerID))
+
+	// Explicitly block Bedrock
+	if normalizedID == "bedrock" {
+		return cline.ApiProvider_BEDROCK, fmt.Errorf("bedrock provider is not supported for quick setup due to complex authentication requirements. Please use interactive setup: cline auth")
+	}
+
+	// Map provider string to enum using existing function
+	provider, ok := mapProviderStringToEnum(normalizedID)
+	if !ok {
+		// Provider not found - provide helpful error message
+		supportedProviders := []string{
+			"openai-native", "openai", "anthropic", "gemini",
+			"openrouter", "xai", "cerebras", "ollama",
+		}
+		return cline.ApiProvider_ANTHROPIC, fmt.Errorf(
+			"invalid provider '%s'. Supported providers: %s",
+			providerID,
+			strings.Join(supportedProviders, ", "),
+		)
+	}
+
+	// Validate against supported quick setup providers
+	supportedProviders := map[cline.ApiProvider]bool{
+		cline.ApiProvider_OPENAI_NATIVE: true,
+		cline.ApiProvider_OPENAI:        true,
+		cline.ApiProvider_ANTHROPIC:     true,
+		cline.ApiProvider_GEMINI:        true,
+		cline.ApiProvider_OPENROUTER:    true,
+		cline.ApiProvider_XAI:           true,
+		cline.ApiProvider_CEREBRAS:      true,
+		cline.ApiProvider_OLLAMA:        true,
+		cline.ApiProvider_NOUSRESEARCH:  true,
+	}
+
+	if !supportedProviders[provider] {
+		return provider, fmt.Errorf(
+			"provider '%s' is not supported for quick setup. Please use interactive setup: cline auth",
+			providerID,
+		)
+	}
+
+	return provider, nil
+}
+
+// validateAndFetchModel validates the model ID or fetches from provider if needed
+// Returns the final model ID and optional model info
+// For providers with static models, validates against the list
+// For providers with dynamic models, fetches the list if possible
+func validateAndFetchModel(ctx context.Context, manager *task.Manager, provider cline.ApiProvider, modelID, apiKey string) (string, interface{}, error) {
+	// Normalize model ID
+	modelID = strings.TrimSpace(modelID)
+	if modelID == "" {
+		return "", nil, fmt.Errorf("model ID cannot be empty")
+	}
+
+	// For most providers, we trust the user's input since we can't easily validate without making API calls
+	// The actual validation will happen when the model is used
+	switch provider {
+	case cline.ApiProvider_OPENROUTER:
+		// OpenRouter supports model info fetching, but it requires an API call
+		// For quick setup, we'll trust the user's input and return nil for model info
+		// The actual model info will be fetched when needed
+		if global.Config.Verbose {
+			fmt.Printf("[DEBUG] OpenRouter model ID: %s (will be validated on first use)\n", modelID)
+		}
+		return modelID, nil, nil
+
+	case cline.ApiProvider_OLLAMA:
+		// Ollama models can be validated by fetching the list, but this requires the server to be running
+		// For quick setup, we'll trust the user's input
+		if global.Config.Verbose {
+			fmt.Printf("[DEBUG] Ollama model ID: %s (will be validated when server is accessible)\n", modelID)
+		}
+		return modelID, nil, nil
+
+	default:
+		// For other providers (Anthropic, OpenAI, Gemini, XAI, Cerebras), trust user input
+		// Model validation will occur when the model is actually used
+		if global.Config.Verbose {
+			fmt.Printf("[DEBUG] %s model ID: %s (will be validated on first use)\n", GetProviderDisplayName(provider), modelID)
+		}
+		return modelID, nil, nil
+	}
+}
+
+// markWelcomeViewCompleted marks the welcome view as completed in the state
+// This prevents the welcome view from showing up after quick setup
+func markWelcomeViewCompleted(ctx context.Context, manager *task.Manager) error {
+	// Use the State service to update the welcome view flag
+	_, err := manager.GetClient().State.SetWelcomeViewCompleted(ctx, &cline.BooleanRequest{Value: true})
+	if err != nil {
+		return fmt.Errorf("failed to mark welcome view as completed: %w", err)
+	}
+
+	if global.Config.Verbose {
+		fmt.Println("[DEBUG] Marked welcome view as completed")
+	}
+
+	return nil
+}

cli/pkg/cli/auth/models_byo.go

@@ -1 +0,0 @@
-package auth

cli/pkg/cli/auth/models_list_fetch.go

@@ -14,13 +14,33 @@ import (
 
 // FetchOpenRouterModels fetches available OpenRouter models from Cline Core
 func FetchOpenRouterModels(ctx context.Context, manager *task.Manager) (map[string]*cline.OpenRouterModelInfo, error) {
-	resp, err := manager.GetClient().Models.RefreshOpenRouterModels(ctx, &cline.EmptyRequest{})
+	resp, err := manager.GetClient().Models.RefreshOpenRouterModelsRpc(ctx, &cline.EmptyRequest{})
 	if err != nil {
 		return nil, fmt.Errorf("failed to fetch OpenRouter models: %w", err)
 	}
 	return resp.Models, nil
 }
 
+// FetchOcaModels fetches available Oca models from Cline Core
+func FetchOcaModels(ctx context.Context, manager *task.Manager) (map[string]*cline.OcaModelInfo, error) {
+	resp, err := manager.GetClient().Models.RefreshOcaModels(ctx, &cline.StringRequest{})
+	if err != nil {
+		return nil, fmt.Errorf("failed to fetch Oca models: %w", err)
+	}
+	return resp.Models, nil
+}
+
+// ConvertOpenRouterModelsToInterface converts OpenRouter model map to generic interface map.
+// This allows OpenRouter and Cline models to be used with the generic fetching utilities.
+func ConvertOpenRouterModelsToInterface(models map[string]*cline.OpenRouterModelInfo) map[string]interface{} {
+	result := make(map[string]interface{}, len(models))
+	for k, v := range models {
+		result[k] = v
+	}
+	return result
+}
+
+
 // FetchOpenAiModels fetches available OpenAI models from Cline Core
 // Takes the API key and returns a list of model IDs
 func FetchOpenAiModels(ctx context.Context, manager *task.Manager, baseURL, apiKey string) ([]string, error) {
@@ -100,9 +120,9 @@ func ConvertModelsMapToSlice(models map[string]interface{}) []string {
 	return result
 }
 
-// ConvertOpenRouterModelsToInterface converts OpenRouter model map to generic interface map.
-// This allows OpenRouter and Cline models to be used with the generic fetching utilities.
-func ConvertOpenRouterModelsToInterface(models map[string]*cline.OpenRouterModelInfo) map[string]interface{} {
+// ConvertOcaModelsToInterface converts Oca model map to generic interface map.
+// This allows Oca and Cline models to be used with the generic fetching utilities.
+func ConvertOcaModelsToInterface(models map[string]*cline.OcaModelInfo) map[string]interface{} {
 	result := make(map[string]interface{}, len(models))
 	for k, v := range models {
 		result[k] = v

cli/pkg/cli/auth/providers_byo.go

@@ -18,14 +18,16 @@ type BYOProviderOption struct {
 func GetBYOProviderList() []BYOProviderOption {
 	return []BYOProviderOption{
 		{Name: "Anthropic", Provider: cline.ApiProvider_ANTHROPIC},
-		{Name: "OpenAI", Provider: cline.ApiProvider_OPENAI},
-		{Name: "OpenAI Native", Provider: cline.ApiProvider_OPENAI_NATIVE},
+		{Name: "OpenAI Compatible", Provider: cline.ApiProvider_OPENAI},
+		{Name: "OpenAI (Official)", Provider: cline.ApiProvider_OPENAI_NATIVE},
 		{Name: "OpenRouter", Provider: cline.ApiProvider_OPENROUTER},
 		{Name: "X AI (Grok)", Provider: cline.ApiProvider_XAI},
 		{Name: "AWS Bedrock", Provider: cline.ApiProvider_BEDROCK},
 		{Name: "Google Gemini", Provider: cline.ApiProvider_GEMINI},
 		{Name: "Ollama", Provider: cline.ApiProvider_OLLAMA},
 		{Name: "Cerebras", Provider: cline.ApiProvider_CEREBRAS},
+		{Name: "NousResearch", Provider: cline.ApiProvider_NOUSRESEARCH},
+		{Name: "Oracle Code Assist", Provider: cline.ApiProvider_OCA},
 	}
 }
 
@@ -71,6 +73,8 @@ func SupportsBYOModelFetching(provider cline.ApiProvider) bool {
 		return true
 	case cline.ApiProvider_OLLAMA:
 		return true
+	case cline.ApiProvider_OCA:
+		return true
 	}
 
 	return SupportsStaticModelList(provider)
@@ -82,9 +86,9 @@ func GetBYOProviderPlaceholder(provider cline.ApiProvider) string {
 	case cline.ApiProvider_ANTHROPIC:
 		return "e.g., claude-sonnet-4-5-20250929"
 	case cline.ApiProvider_OPENAI:
-		return "e.g., gpt-5-2025-08-07"
-	case cline.ApiProvider_OPENAI_NATIVE:
 		return "e.g., openai/gpt-oss-120b"
+	case cline.ApiProvider_OPENAI_NATIVE:
+		return "e.g., gpt-5-2025-08-07"
 	case cline.ApiProvider_OPENROUTER:
 		return "e.g., google/gemini-2.0-flash-exp:free"
 	case cline.ApiProvider_XAI:
@@ -97,6 +101,10 @@ func GetBYOProviderPlaceholder(provider cline.ApiProvider) string {
 		return "e.g., qwen3-coder:30b"
 	case cline.ApiProvider_CEREBRAS:
 		return "e.g., gpt-oss-120b"
+	case cline.ApiProvider_NOUSRESEARCH:
+		return "e.g., Hermes-4-405B"
+	case cline.ApiProvider_OCA:
+		return "e.g., oca/llama4"
 	default:
 		return "Enter model ID"
 	}
@@ -127,8 +135,8 @@ func GetBYOAPIKeyFieldConfig(provider cline.ApiProvider) APIKeyFieldConfig {
 }
 
 // PromptForAPIKey prompts the user to enter an API key (or base URL for Ollama).
-// For OpenAI Native provider, also prompts for an optional base URL.
-func PromptForAPIKey(provider cline.ApiProvider) (string, error) {
+// For OpenAI (Compatible) provider, also prompts for an optional base URL.
+func PromptForAPIKey(provider cline.ApiProvider) (string, string, error) {
 	var apiKey string
 	config := GetBYOAPIKeyFieldConfig(provider)
 
@@ -149,11 +157,11 @@ func PromptForAPIKey(provider cline.ApiProvider) (string, error) {
 	form := huh.NewForm(huh.NewGroup(apiKeyField))
 
 	if err := form.Run(); err != nil {
-		return "", fmt.Errorf("failed to get API key: %w", err)
+		return "", "", fmt.Errorf("failed to get API key: %w", err)
 	}
 
-	// For OpenAI Native provider, also prompt for base URL
-	if provider == cline.ApiProvider_OPENAI_NATIVE {
+	// For OpenAI (Compatible) provider, prompt for base URL
+	if provider == cline.ApiProvider_OPENAI {
 		var baseURL string
 		baseURLForm := huh.NewForm(
 			huh.NewGroup(
@@ -166,12 +174,11 @@ func PromptForAPIKey(provider cline.ApiProvider) (string, error) {
 		)
 
 		if err := baseURLForm.Run(); err != nil {
-			return "", fmt.Errorf("failed to get base URL: %w", err)
+			return "", "", fmt.Errorf("failed to get base URL: %w", err)
 		}
 
-		// TODO - connect baseURL
-		_ = baseURL
+		return apiKey, baseURL, nil
 	}
 
-	return apiKey, nil
+	return apiKey, "", nil
 }

cli/pkg/cli/auth/providers_list.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"strings"
+	"time"
 
 	"github.com/cline/cli/pkg/cli/global"
 	"github.com/cline/cli/pkg/cli/task"
@@ -110,6 +111,9 @@ func (r *ProviderListResult) GetAllReadyProviders() []*ProviderDisplay {
 		cline.ApiProvider_GEMINI,
 		cline.ApiProvider_OLLAMA,
 		cline.ApiProvider_CEREBRAS,
+		cline.ApiProvider_NOUSRESEARCH,
+		cline.ApiProvider_OCA,
+		cline.ApiProvider_HICAP,
 	}
 
 	// Check each provider to see if it's ready to use
@@ -120,16 +124,23 @@ func (r *ProviderListResult) GetAllReadyProviders() []*ProviderDisplay {
 			continue
 		}
 
-		// Check if this provider has an API key
-		hasAPIKey := checkAPIKeyExists(r.apiConfig, provider)
-		if !hasAPIKey {
-			continue
-		}
-
 		// Check if this provider has a model configured
 		modelID := getProviderSpecificModelID(r.apiConfig, "plan", provider)
-		if modelID == "" {
-			continue
+
+		// Determine if credentials exist
+		hasCreds := checkAPIKeyExists(r.apiConfig, provider)
+
+		// Determine readiness: OCA uses auth state presence; others need creds and model
+		if provider == cline.ApiProvider_OCA {
+			state, _ := GetLatestOCAState(context.Background(), 2 *time.Second)
+			if state == nil || state.User == nil {
+				continue
+			}
+		} else {
+			// Provider is not ready unless it has credentials AND a model configured
+			if !hasCreds || modelID == "" {
+				continue
+			}
 		}
 
 		// Get base URL for Ollama
@@ -145,7 +156,7 @@ func (r *ProviderListResult) GetAllReadyProviders() []*ProviderDisplay {
 			Mode:      "Ready",
 			Provider:  provider,
 			ModelID:   modelID,
-			HasAPIKey: hasAPIKey,
+			HasAPIKey: checkAPIKeyExists(r.apiConfig, provider),
 			BaseURL:   baseURL,
 		})
 		seenProviders[provider] = true
@@ -203,13 +214,15 @@ func extractProviderFromState(stateData map[string]interface{}, mode string) *Pr
 // mapProviderStringToEnum converts provider string from state to ApiProvider enum
 // Returns (provider, ok) where ok is false if the provider is unknown
 func mapProviderStringToEnum(providerStr string) (cline.ApiProvider, bool) {
+	normalizedStr := strings.ToLower(providerStr)
+	
 	// Map string values to enum values
-	switch providerStr {
+	switch normalizedStr {
 	case "anthropic":
 		return cline.ApiProvider_ANTHROPIC, true
-	case "openai":
+	case "openai", "openai-compatible": // internal name is 'openai', but this is actually the openai-compatible provider
 		return cline.ApiProvider_OPENAI, true
-	case "openai-native":
+	case "openai-native": // This is the native, official Open AI provider
 		return cline.ApiProvider_OPENAI_NATIVE, true
 	case "openrouter":
 		return cline.ApiProvider_OPENROUTER, true
@@ -225,6 +238,12 @@ func mapProviderStringToEnum(providerStr string) (cline.ApiProvider, bool) {
 		return cline.ApiProvider_CEREBRAS, true
 	case "cline":
 		return cline.ApiProvider_CLINE, true
+	case "oca":
+		return cline.ApiProvider_OCA, true
+	case "hicap":
+		return cline.ApiProvider_HICAP, true
+	case "nousResearch":
+		return cline.ApiProvider_NOUSRESEARCH, true
 	default:
 		return cline.ApiProvider_ANTHROPIC, false // Return 0 value with false
 	}
@@ -237,7 +256,7 @@ func GetProviderIDForEnum(provider cline.ApiProvider) string {
 	case cline.ApiProvider_ANTHROPIC:
 		return "anthropic"
 	case cline.ApiProvider_OPENAI:
-		return "openai"
+		return "openai-compatible"
 	case cline.ApiProvider_OPENAI_NATIVE:
 		return "openai-native"
 	case cline.ApiProvider_OPENROUTER:
@@ -254,6 +273,12 @@ func GetProviderIDForEnum(provider cline.ApiProvider) string {
 		return "cerebras"
 	case cline.ApiProvider_CLINE:
 		return "cline"
+	case cline.ApiProvider_OCA:
+		return "oca"
+	case cline.ApiProvider_HICAP:
+		return "hicap"
+	case cline.ApiProvider_NOUSRESEARCH:
+		return "nousResearch"
 	default:
 		return ""
 	}
@@ -312,9 +337,9 @@ func GetProviderDisplayName(provider cline.ApiProvider) string {
 	case cline.ApiProvider_ANTHROPIC:
 		return "Anthropic"
 	case cline.ApiProvider_OPENAI:
-		return "OpenAI"
+		return "OpenAI Compatible"
 	case cline.ApiProvider_OPENAI_NATIVE:
-		return "OpenAI Native"
+		return "OpenAI (Official)"
 	case cline.ApiProvider_OPENROUTER:
 		return "OpenRouter"
 	case cline.ApiProvider_XAI:
@@ -329,6 +354,12 @@ func GetProviderDisplayName(provider cline.ApiProvider) string {
 		return "Cerebras"
 	case cline.ApiProvider_CLINE:
 		return "Cline (Official)"
+	case cline.ApiProvider_OCA:
+		return "Oracle Code Assist"
+	case cline.ApiProvider_HICAP:
+		return "Hicap"
+	case cline.ApiProvider_NOUSRESEARCH:
+		return "NousResearch"
 	default:
 		return "Unknown"
 	}
@@ -378,7 +409,7 @@ func FormatProviderList(result *ProviderListResult) string {
 				} else {
 					output.WriteString("    Base URL: (default)\n")
 				}
-			} else if display.Provider == cline.ApiProvider_CLINE {
+			} else if display.Provider == cline.ApiProvider_CLINE || display.Provider == cline.ApiProvider_OCA {
 				output.WriteString("    Status:   Authenticated\n")
 			} else {
 				output.WriteString("    API Key:  Configured\n")
@@ -430,6 +461,12 @@ func DetectAllConfiguredProviders(ctx context.Context, manager *task.Manager) ([
 		verboseLog("[DEBUG] Cline provider is authenticated")
 	}
 
+	// Check OCA provider via global auth subscription (state presence)
+	if state, _ := GetLatestOCAState(context.Background(), 2*time.Second); state != nil && state.User != nil {
+		configuredProviders = append(configuredProviders, cline.ApiProvider_OCA)
+		verboseLog("[DEBUG] OCA provider has active auth state")
+	}
+
 	// Check each BYO provider for API key presence
 	providersToCheck := []struct {
 		provider cline.ApiProvider
@@ -444,6 +481,8 @@ func DetectAllConfiguredProviders(ctx context.Context, manager *task.Manager) ([
 		{cline.ApiProvider_GEMINI, "geminiApiKey"},
 		{cline.ApiProvider_OLLAMA, "ollamaBaseUrl"}, // Ollama uses baseUrl instead of API key
 		{cline.ApiProvider_CEREBRAS, "cerebrasApiKey"},
+		{cline.ApiProvider_HICAP, "hicapApiKey"},
+		{cline.ApiProvider_NOUSRESEARCH, "nousResearchApiKey"},
 	}
 
 	for _, providerCheck := range providersToCheck {
@@ -459,6 +498,7 @@ func DetectAllConfiguredProviders(ctx context.Context, manager *task.Manager) ([
 		}
 	}
 
+
 	verboseLog("[DEBUG] Total configured providers: %d", len(configuredProviders))
 	for _, p := range configuredProviders {
 		verboseLog("[DEBUG]   - %s", GetProviderDisplayName(p))

cli/pkg/cli/auth/update_api_configurations.go

@@ -12,7 +12,7 @@ import (
 )
 
 // updateApiConfigurationPartial is a helper that calls the gRPC method with optional verbose logging.
-// This replaces the Manager.UpdateApiConfigurationPartial method to keep auth-specific code in the auth package.
+// This replaces the Manager.updateApiConfigurationPartial method to keep auth-specific code in the auth package.
 func updateApiConfigurationPartial(ctx context.Context, manager *task.Manager, request *cline.UpdateApiConfigurationPartialRequest) error {
 	if global.Config.Verbose {
 		fmt.Println("[DEBUG] Updating API configuration (partial)")
@@ -46,6 +46,7 @@ func updateApiConfigurationPartial(ctx context.Context, manager *task.Manager, r
 // ProviderFields defines all the field names associated with a specific provider
 type ProviderFields struct {
 	APIKeyField            string // API key field name (e.g., "apiKey", "openAiApiKey")
+	BaseURLField           string // Base URL field name (optional, empty if not applicable)
 	PlanModeModelIDField   string // Plan mode model ID field (e.g., "planModeApiModelId")
 	ActModeModelIDField    string // Act mode model ID field (e.g., "actModeApiModelId")
 	PlanModeModelInfoField string // Plan mode model info field (optional, empty if not applicable)
@@ -68,6 +69,7 @@ func GetProviderFields(provider cline.ApiProvider) (ProviderFields, error) {
 	case cline.ApiProvider_OPENAI:
 		return ProviderFields{
 			APIKeyField:                          "openAiApiKey",
+			BaseURLField:                         "openAiBaseUrl",
 			PlanModeModelIDField:                 "planModeApiModelId",
 			ActModeModelIDField:                  "actModeApiModelId",
 			PlanModeProviderSpecificModelIDField: "planModeOpenAiModelId",
@@ -142,6 +144,34 @@ func GetProviderFields(provider cline.ApiProvider) (ProviderFields, error) {
 			ActModeProviderSpecificModelIDField:  "actModeOpenRouterModelId",
 		}, nil
 
+	case cline.ApiProvider_OCA:
+		return ProviderFields{
+			APIKeyField:                          "ocaApiKey",
+			PlanModeModelIDField:                 "planModeApiModelId",
+			ActModeModelIDField:                  "actModeApiModelId",
+			PlanModeModelInfoField:               "planModeOcaModelInfo",
+			ActModeModelInfoField:                "actModeOcaModelInfo",
+			PlanModeProviderSpecificModelIDField: "planModeOcaModelId",
+			ActModeProviderSpecificModelIDField:  "actModeOcaModelId",
+		}, nil
+	case cline.ApiProvider_HICAP:
+		return ProviderFields{
+			APIKeyField:                          "hicapApiKey",
+			PlanModeModelInfoField:               "planModeHicapModelInfo",
+			ActModeModelInfoField:                "actModeHicapModelInfo",
+			PlanModeProviderSpecificModelIDField: "planModeHicapModelId",
+			ActModeProviderSpecificModelIDField:  "actModeHicapModelId",
+		}, nil
+
+	case cline.ApiProvider_NOUSRESEARCH:
+		return ProviderFields{
+			APIKeyField:                          "nousResearchApiKey",
+			PlanModeModelIDField:                 "planModeApiModelId",
+			ActModeModelIDField:                  "actModeApiModelId",
+			PlanModeProviderSpecificModelIDField: "planModeNousResearchModelId",
+			ActModeProviderSpecificModelIDField:  "actModeNousResearchModelId",
+		}, nil
+
 	default:
 		return ProviderFields{}, fmt.Errorf("unsupported provider: %v", provider)
 	}
@@ -150,9 +180,12 @@ func GetProviderFields(provider cline.ApiProvider) (ProviderFields, error) {
 // ProviderUpdatesPartial defines optional fields for partial provider updates
 // Uses pointers to distinguish between "not provided" and "set to empty"
 type ProviderUpdatesPartial struct {
-	ModelID   *string     // New model ID (optional)
-	APIKey    *string     // New API key (optional)
-	ModelInfo interface{} // New model info (optional, provider-specific)
+	ModelID      *string     // New model ID (optional)
+	APIKey       *string     // New API key (optional)
+	ModelInfo    interface{} // New model info (optional, provider-specific)
+	BaseURL      *string     // New base URL (optional, e.g., for OCA, Ollama)
+	RefreshToken *string     // New refresh token (optional, e.g., for OCA)
+	Mode         *string     // New mode (optional, e.g., "internal" or "external" for OCA)
 }
 
 // GetModelIDFieldName returns the appropriate model ID field name for a provider and mode.
@@ -182,7 +215,7 @@ func GetModelIDFieldName(provider cline.ApiProvider, mode string) (string, error
 // buildProviderFieldMask builds a list of camelCase field paths for the field mask.
 // When includeProviderEnums is true, the provider enum fields are included (for setting active provider).
 // When false, only the data fields are included (for configuring without activating).
-func buildProviderFieldMask(fields ProviderFields, includeAPIKey bool, includeModelID bool, includeModelInfo bool, includeProviderEnums bool) []string {
+func buildProviderFieldMask(fields ProviderFields, includeAPIKey bool, includeModelID bool, includeModelInfo bool, includeBaseURL bool, includeProviderEnums bool) []string {
 	var fieldPaths []string
 
 	// Include provider enums if requested (used when setting active provider)
@@ -199,6 +232,11 @@ func buildProviderFieldMask(fields ProviderFields, includeAPIKey bool, includeMo
 		}
 	}
 
+	// Add base URL field if requested and applicable
+	if includeBaseURL && fields.BaseURLField != "" {
+		fieldPaths = append(fieldPaths, fields.BaseURLField)
+	}
+
 	// Add model ID fields if requested
 	if includeModelID {
 		// Only include provider-specific fields if they exist, otherwise use generic fields
@@ -245,6 +283,12 @@ func setAPIKeyField(apiConfig *cline.ModelsApiConfiguration, fieldName string, v
 		apiConfig.CerebrasApiKey = value
 	case "clineApiKey":
 		apiConfig.ClineApiKey = value
+	case "ocaApiKey":
+		apiConfig.OcaApiKey = value
+	case "hicapApiKey":
+		apiConfig.HicapApiKey = value
+	case "nousResearchApiKey":
+		apiConfig.NousResearchApiKey = value
 	}
 }
 
@@ -263,11 +307,20 @@ func setProviderSpecificModelID(apiConfig *cline.ModelsApiConfiguration, fieldNa
 	case "planModeAwsBedrockCustomModelBaseId":
 		apiConfig.PlanModeAwsBedrockCustomModelBaseId = value
 		apiConfig.ActModeAwsBedrockCustomModelBaseId = value
+	case "planModeOcaModelId":
+		apiConfig.PlanModeOcaModelId = value
+		apiConfig.ActModeOcaModelId = value
+	case "planModeHicapModelId":
+		apiConfig.PlanModeHicapModelId = value
+		apiConfig.ActModeHicapModelId = value
+	case "planModeNousResearchModelId":
+		apiConfig.PlanModeNousResearchModelId = value
+		apiConfig.ActModeNousResearchModelId = value
 	}
 }
 
 // AddProviderPartial configures a new provider with all necessary fields using partial updates.
-func AddProviderPartial(ctx context.Context, manager *task.Manager, provider cline.ApiProvider, modelID string, apiKey string, modelInfo interface{}) error {
+func AddProviderPartial(ctx context.Context, manager *task.Manager, provider cline.ApiProvider, modelID string, apiKey string, baseURL string, modelInfo interface{}) error {
 	// Get field mapping for this provider
 	fields, err := GetProviderFields(provider)
 	if err != nil {
@@ -282,6 +335,13 @@ func AddProviderPartial(ctx context.Context, manager *task.Manager, provider cli
 		setAPIKeyField(apiConfig, fields.APIKeyField, proto.String(apiKey))
 	}
 
+	// Set base URL field if provided and applicable
+	includeBaseURL := false
+	if baseURL != "" && fields.BaseURLField != "" {
+		setBaseURLField(apiConfig, fields.BaseURLField, proto.String(baseURL))
+		includeBaseURL = true
+	}
+
 	// Set model ID fields
 	apiConfig.PlanModeApiModelId = proto.String(modelID)
 	apiConfig.ActModeApiModelId = proto.String(modelID)
@@ -301,7 +361,7 @@ func AddProviderPartial(ctx context.Context, manager *task.Manager, provider cli
 
 	// Build field mask including all fields we're setting (without provider enums)
 	includeModelInfo := fields.PlanModeModelInfoField != "" && modelInfo != nil
-	fieldPaths := buildProviderFieldMask(fields, true, true, includeModelInfo, false)
+	fieldPaths := buildProviderFieldMask(fields, true, true, includeModelInfo, includeBaseURL, false)
 
 	// Create field mask
 	fieldMask := &fieldmaskpb.FieldMask{Paths: fieldPaths}
@@ -368,7 +428,7 @@ func UpdateProviderPartial(ctx context.Context, manager *task.Manager, provider
 	}
 
 	// Build field mask for only the fields being updated
-	fieldPaths := buildProviderFieldMask(fields, includeAPIKey, includeModelID, includeModelInfo, setAsActive)
+	fieldPaths := buildProviderFieldMask(fields, includeAPIKey, includeModelID, includeModelInfo, false, setAsActive)
 
 	// Create field mask
 	fieldMask := &fieldmaskpb.FieldMask{Paths: fieldPaths}
@@ -421,6 +481,46 @@ func RemoveProviderPartial(ctx context.Context, manager *task.Manager, provider
 	return nil
 }
 
+// setBaseURLField sets the appropriate base URL field in the config based on the field name
+func setBaseURLField(apiConfig *cline.ModelsApiConfiguration, fieldName string, value *string) {
+	switch fieldName {
+	case "ocaBaseUrl":
+		apiConfig.OcaBaseUrl = value
+	case "ollamaBaseUrl":
+		apiConfig.OllamaBaseUrl = value
+	case "openAiBaseUrl":
+		apiConfig.OpenAiBaseUrl = value
+	case "geminiBaseUrl":
+		apiConfig.GeminiBaseUrl = value
+	case "liteLlmBaseUrl":
+		apiConfig.LiteLlmBaseUrl = value
+	case "anthropicBaseUrl":
+		apiConfig.AnthropicBaseUrl = value
+	case "requestyBaseUrl":
+		apiConfig.RequestyBaseUrl = value
+	case "lmStudioBaseUrl":
+		apiConfig.LmStudioBaseUrl = value
+	case "oca":
+		apiConfig.OcaBaseUrl = value
+	}
+}
+
+// setRefreshTokenField sets the appropriate refresh token field in the config
+func setRefreshTokenField(apiConfig *cline.ModelsApiConfiguration, fieldName string, value *string) {
+	switch fieldName {
+	case "ocaRefreshToken":
+		apiConfig.OcaRefreshToken = value
+	}
+}
+
+// setModeField sets the appropriate mode field in the config
+func setModeField(apiConfig *cline.ModelsApiConfiguration, fieldName string, value *string) {
+	switch fieldName {
+	case "ocaMode":
+		apiConfig.OcaMode = value
+	}
+}
+
 // BedrockOptionalFields holds optional configuration fields for AWS Bedrock
 type BedrockOptionalFields struct {
 	SessionToken            *string // Optional: AWS session token for temporary credentials
@@ -434,6 +534,12 @@ type BedrockOptionalFields struct {
 	Endpoint                *string // Optional: Custom endpoint URL
 }
 
+// OcaOptionalFields holds optional configuration fields for Oracle Code Assist
+type OcaOptionalFields struct {
+	BaseURL *string // Optional: Base URL
+	Mode    *string // Optional: Mode ("internal" or "external")
+}
+
 // setBedrockOptionalFields sets optional Bedrock-specific fields in the API configuration
 func setBedrockOptionalFields(apiConfig *cline.ModelsApiConfiguration, fields *BedrockOptionalFields) {
 	if fields == nil {
@@ -469,6 +575,20 @@ func setBedrockOptionalFields(apiConfig *cline.ModelsApiConfiguration, fields *B
 	}
 }
 
+// setOcaOptionalFields sets optional Oca-specific fields in the API configuration
+func setOcaOptionalFields(apiConfig *cline.ModelsApiConfiguration, fields *OcaOptionalFields) {
+	if fields == nil {
+		return
+	}
+
+	if fields.Mode != nil {
+		apiConfig.OcaMode = fields.Mode
+	}
+	if fields.BaseURL != nil {
+		apiConfig.OcaBaseUrl = fields.BaseURL
+	}
+}
+
 // buildBedrockOptionalFieldMask builds field mask paths for Bedrock optional fields that have values
 func buildBedrockOptionalFieldMask(fields *BedrockOptionalFields) []string {
 	if fields == nil {
@@ -507,3 +627,21 @@ func buildBedrockOptionalFieldMask(fields *BedrockOptionalFields) []string {
 
 	return fieldPaths
 }
+
+// buildOcaOptionalFieldMask builds field mask paths for Bedrock optional fields that have values
+func buildOcaOptionalFieldMask(fields *OcaOptionalFields) []string {
+	if fields == nil {
+		return nil
+	}
+
+	var fieldPaths []string
+
+	if fields.Mode != nil {
+		fieldPaths = append(fieldPaths, "ocaMode")
+	}
+	if fields.BaseURL != nil {
+		fieldPaths = append(fieldPaths, "ocaBaseUrl")
+	}
+
+	return fieldPaths
+}

cli/pkg/cli/auth/wizard_byo.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"strings"
+	"time"
 
 	"github.com/charmbracelet/huh"
 	"github.com/cline/cli/pkg/cli/global"
@@ -40,7 +41,7 @@ func (pw *ProviderWizard) showMainMenu() (string, error) {
 			huh.NewSelect[string]().
 				Title("What would you like to do?").
 				Options(
-					huh.NewOption("Configure a new provider", "add"),
+					huh.NewOption("Add or change an API provider", "add"),
 					huh.NewOption("Change model for API provider", "change-model"),
 					huh.NewOption("Remove a provider", "remove"),
 					huh.NewOption("List configured providers", "list"),
@@ -107,8 +108,13 @@ func (pw *ProviderWizard) handleAddProvider() error {
 		return pw.handleAddBedrockProvider()
 	}
 
+	// Step 2b: Special handling for OCA provider
+	if provider == cline.ApiProvider_OCA {
+		return pw.handleAddOcaProvider()
+	}
+
 	// Step 3: Get API key first (for non-Bedrock providers)
-	apiKey, err := PromptForAPIKey(provider)
+	apiKey, baseURL, err := PromptForAPIKey(provider)
 	if err != nil {
 		return fmt.Errorf("failed to get API key: %w", err)
 	}
@@ -120,7 +126,7 @@ func (pw *ProviderWizard) handleAddProvider() error {
 	}
 
 	// Step 5: Apply configuration using AddProviderPartial
-	if err := AddProviderPartial(pw.ctx, pw.manager, provider, modelID, apiKey, modelInfo); err != nil {
+	if err := AddProviderPartial(pw.ctx, pw.manager, provider, modelID, apiKey, baseURL, modelInfo); err != nil {
 		return fmt.Errorf("failed to save configuration: %w", err)
 	}
 
@@ -162,6 +168,51 @@ func (pw *ProviderWizard) handleAddBedrockProvider() error {
 	return nil
 }
 
+// handleAddOcaProvider handles adding Oracle Code Assist provider with optional settings and auth
+func (pw *ProviderWizard) handleAddOcaProvider() error {
+	// Step 1: Get OCA configuration (base URL and mode)
+	config, err := PromptForOcaConfig(pw.ctx, pw.manager)
+	if err != nil {
+		if strings.Contains(err.Error(), "user aborted") || strings.Contains(err.Error(), "cancelled") {
+			return nil
+		}
+		return fmt.Errorf("failed to get OCA configuration: %w", err)
+	}
+
+	// Apply OCA configuration (base URL and mode)
+	if err := ApplyOcaConfig(pw.ctx, pw.manager, config); err != nil {
+		return fmt.Errorf("failed to save OCA configuration: %w", err)
+	}
+
+	// Step 2: Ensure OCA authentication
+	if err := ensureOcaAuthenticated(pw.ctx); err != nil {
+		return fmt.Errorf("failed to authenticate with OCA: %w", err)
+	}
+
+	// Step 3: Select model
+	modelID, _, err := pw.selectModel(cline.ApiProvider_OCA, "")
+	if err != nil {
+		return fmt.Errorf("model selection failed: %w", err)
+	}
+
+	// Step 4: Apply the OCA model configuration and set as active
+	updates := ProviderUpdatesPartial{
+		ModelID:   &modelID,
+		ModelInfo: nil,
+	}
+
+	if err := UpdateProviderPartial(pw.ctx, pw.manager, cline.ApiProvider_OCA, updates, true); err != nil {
+		return fmt.Errorf("failed to save OCA configuration: %w", err)
+	}
+
+	if err := setWelcomeViewCompleted(pw.ctx, pw.manager); err != nil {
+		verboseLog("Warning: Failed to mark welcome view as completed: %v", err)
+	}
+
+	fmt.Println("✓ OCA provider configured successfully!")
+	return nil
+}
+
 // handleListProviders retrieves and displays configured providers
 func (pw *ProviderWizard) handleListProviders() error {
 	result, err := GetProviderConfigurations(pw.ctx, pw.manager)
@@ -259,6 +310,15 @@ func (pw *ProviderWizard) fetchModelsForProvider(provider cline.ApiProvider, api
 		}
 		// Ollama returns just model IDs without additional info, so modelInfo map is nil
 		return modelIDs, nil, nil
+
+	case cline.ApiProvider_OCA:
+		// OCA supports dynamic model fetching
+		models, err := FetchOcaModels(pw.ctx, pw.manager)
+		if err != nil {
+			return nil, nil, err
+		}
+		interfaceMap := ConvertOcaModelsToInterface(models)
+		return ConvertModelsMapToSlice(interfaceMap), interfaceMap, nil
 	}
 
 	// Fall back to static models for providers that don't support dynamic fetching
@@ -525,8 +585,17 @@ func getProviderModelIDFromState(stateData map[string]interface{}, provider clin
 	return ""
 }
 
-// getProviderAPIKeyFromState retrieves the API key for a specific provider from state
+ // getProviderAPIKeyFromState retrieves the API key for a specific provider from state
 func getProviderAPIKeyFromState(stateData map[string]interface{}, provider cline.ApiProvider) string {
+	// OCA uses account authentication, not API keys. Consider it "present" if authenticated.
+	if provider == cline.ApiProvider_OCA {
+		if state, _ := GetLatestOCAState(context.TODO(), 2 * time.Second); state != nil && state.User != nil {
+			// Return a sentinel non-empty string so upstream checks pass.
+			return "OCA_AUTH_VERIFIED"
+		}
+		return ""
+	}
+
 	fields, err := GetProviderFields(provider)
 	if err != nil {
 		return ""
@@ -656,7 +725,16 @@ func (pw *ProviderWizard) handleRemoveProvider() error {
 		return nil
 	}
 
-	// Step 7: Clear the API key for the selected provider
+	// Step 7: If removing OCA, sign out first
+	if selectedProvider.Provider == cline.ApiProvider_OCA {
+		if err := signOutOca(pw.ctx); err != nil {
+			fmt.Printf("Warning: Failed to sign out of OCA: %v\n", err)
+		} else {
+			fmt.Println("Signed out of OCA.")
+		}
+	}
+
+	// Step 8: Clear the API key for the selected provider
 	if err := pw.clearProviderAPIKey(selectedProvider.Provider); err != nil {
 		return fmt.Errorf("failed to remove provider: %w", err)
 	}
@@ -670,6 +748,16 @@ func (pw *ProviderWizard) clearProviderAPIKey(provider cline.ApiProvider) error
 	return RemoveProviderPartial(pw.ctx, pw.manager, provider)
 }
 
+
+func signOutOca(ctx context.Context) error {
+	client, err := global.GetDefaultClient(ctx)
+	if err != nil {
+		return err
+	}
+	_, err = client.Ocaaccount.OcaAccountLogoutClicked(ctx, &cline.EmptyRequest{})
+	return err
+}
+
 func setWelcomeViewCompleted(ctx context.Context, manager *task.Manager) error {
 	_, err := manager.GetClient().State.SetWelcomeViewCompleted(ctx, &cline.BooleanRequest{Value: true})
 	return err

cli/pkg/cli/auth/wizard_byo_oca.go

@@ -0,0 +1,366 @@
+package auth
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/charmbracelet/huh"
+	"github.com/cline/cli/pkg/cli/global"
+	"github.com/cline/cli/pkg/cli/task"
+	"github.com/cline/grpc-go/cline"
+	"google.golang.org/protobuf/proto"
+	"google.golang.org/protobuf/types/known/fieldmaskpb"
+)
+
+// OcaConfig holds Oracle Code Assist (OCA) configuration fields
+type OcaConfig struct {
+	BaseURL string
+	Mode    string
+}
+
+// PromptForOcaConfig displays a form for OCA configuration (base URL and mode)
+func PromptForOcaConfig(ctx context.Context, manager *task.Manager) (*OcaConfig, error) {
+	config := &OcaConfig{}
+	var mode string
+
+	// Collect optional settings
+	configForm := huh.NewForm(
+		huh.NewGroup(
+			huh.NewInput().
+				Title("Base URL").
+				Value(&config.BaseURL).
+				Description("Leave empty to use default Base URL"),
+
+			huh.NewSelect[string]().
+				Title("Choose OCA mode (used for authentication)").
+				Description("Select 'Internal' to use Cline's internal OCA, or 'External' for your own OCA instance").
+				Options(
+					huh.NewOption("Internal", "internal"),
+					huh.NewOption("External", "external"),
+				).
+				Value(&mode),
+		),
+	)
+
+	if err := configForm.Run(); err != nil {
+		return nil, fmt.Errorf("failed to get OCA configuration: %w", err)
+	}
+
+	// Trim whitespace from string fields
+	config.BaseURL = strings.TrimSpace(config.BaseURL)
+	config.Mode = strings.TrimSpace(mode)
+
+	return config, nil
+}
+
+// ApplyOcaConfig applies OCA configuration using partial updates
+func ApplyOcaConfig(ctx context.Context, manager *task.Manager, config *OcaConfig) error {
+	// Build the API configuration with all OCA fields
+	apiConfig := &cline.ModelsApiConfiguration{}
+
+	// Set profile authentication fields (always required)
+	optionalFields := &OcaOptionalFields{}
+
+	// Set profile name (can be empty for default profile)
+	if config.BaseURL != "" {
+		optionalFields.BaseURL = proto.String(config.BaseURL)
+	}
+
+	// Set optional fields if provided
+	if config.Mode != "" {
+		optionalFields.Mode = proto.String(config.Mode)
+	}
+
+	// Apply all fields to the config
+	setOcaOptionalFields(apiConfig, optionalFields)
+
+	// Add profile authentication field paths
+	optionalPaths := buildOcaOptionalFieldMask(optionalFields)
+
+	// Create field mask
+	fieldMask := &fieldmaskpb.FieldMask{Paths: optionalPaths}
+
+	// Apply the partial update
+	request := &cline.UpdateApiConfigurationPartialRequest{
+		ApiConfiguration: apiConfig,
+		UpdateMask:       fieldMask,
+	}
+
+	if err := updateApiConfigurationPartial(ctx, manager, request); err != nil {
+		return fmt.Errorf("failed to apply OCA configuration: %w", err)
+	}
+
+	return nil
+}
+
+// ===========================
+// OCA Auth Listener Singleton
+// ===========================
+
+type ocaAuthStream interface {
+	Recv() (*cline.OcaAuthState, error)
+}
+
+// OcaAuthStatusListener manages subscription to OCA auth status updates
+type OcaAuthStatusListener struct {
+	stream        ocaAuthStream
+	updatesCh     chan *cline.OcaAuthState
+	errCh         chan error
+	ctx           context.Context
+	cancel        context.CancelFunc
+	mu            sync.RWMutex
+	lastState     *cline.OcaAuthState
+	firstEventCh  chan struct{}
+	firstEventOnce sync.Once
+}
+
+// NewOcaAuthStatusListener creates a new OCA auth status listener
+func NewOcaAuthStatusListener(parentCtx context.Context) (*OcaAuthStatusListener, error) {
+	client, err := global.GetDefaultClient(parentCtx)
+	if err != nil {
+		return nil, fmt.Errorf("failed to get client: %w", err)
+	}
+
+	// Keep the listener alive independently of short-lived caller contexts
+	ctx, cancel := context.WithCancel(context.Background())
+
+	// Subscribe to OCA auth status updates
+	stream, err := client.Ocaaccount.OcaSubscribeToAuthStatusUpdate(ctx, &cline.EmptyRequest{})
+	if err != nil {
+		cancel()
+		return nil, fmt.Errorf("failed to subscribe to OCA auth updates: %w", err)
+	}
+
+	return &OcaAuthStatusListener{
+		stream:       stream,
+		updatesCh:    make(chan *cline.OcaAuthState, 10),
+		errCh:        make(chan error, 1),
+		ctx:          ctx,
+		cancel:       cancel,
+		firstEventCh: make(chan struct{}),
+	}, nil
+}
+
+// Start begins listening to the auth status update stream
+func (l *OcaAuthStatusListener) Start() error {
+	go l.readStream()
+	return nil
+}
+
+func (l *OcaAuthStatusListener) readStream() {
+	defer close(l.updatesCh)
+	defer close(l.errCh)
+
+	for {
+		select {
+		case <-l.ctx.Done():
+			return
+		default:
+			state, err := l.stream.Recv()
+			if err != nil {
+				// Propagate error and exit
+				if err == io.EOF {
+					// Treat as error to notify waiters
+					err = fmt.Errorf("OCA auth status stream closed")
+				}
+				select {
+				case l.errCh <- err:
+				case <-l.ctx.Done():
+				}
+				return
+			}
+
+			l.mu.Lock()
+			l.lastState = state
+			l.mu.Unlock()
+
+			// Notify first event waiters
+			l.firstEventOnce.Do(func() { close(l.firstEventCh) })
+
+			select {
+			case l.updatesCh <- state:
+			case <-l.ctx.Done():
+				return
+			}
+		}
+	}
+}
+
+// WaitForFirstEvent blocks until the first event is received or timeout occurs
+func (l *OcaAuthStatusListener) WaitForFirstEvent(timeout time.Duration) error {
+	// Fast-path if already have a state
+	l.mu.RLock()
+	ready := l.lastState != nil
+	l.mu.RUnlock()
+	if ready {
+		return nil
+	}
+
+	timer := time.NewTimer(timeout)
+	defer timer.Stop()
+
+	select {
+	case <-l.firstEventCh:
+		return nil
+	case <-timer.C:
+		return fmt.Errorf("timeout waiting for initial OCA auth event")
+	case <-l.ctx.Done():
+		return fmt.Errorf("OCA auth listener cancelled")
+	}
+}
+
+// IsAuthenticated returns true if the last known OCA auth state is authenticated
+func (l *OcaAuthStatusListener) IsAuthenticated() bool {
+	l.mu.RLock()
+	defer l.mu.RUnlock()
+	return isOCAStateAuthenticated(l.lastState)
+}
+
+// WaitForAuthentication waits until OCA authentication succeeds or timeout occurs
+func (l *OcaAuthStatusListener) WaitForAuthentication(timeout time.Duration) error {
+	timer := time.NewTimer(timeout)
+	defer timer.Stop()
+
+	// If already authenticated, return immediately
+	if l.IsAuthenticated() {
+		return nil
+	}
+
+	for {
+		select {
+		case <-timer.C:
+			return fmt.Errorf("OCA authentication timeout after %v - please try again", timeout)
+		case <-l.ctx.Done():
+			return fmt.Errorf("OCA authentication cancelled")
+		case err := <-l.errCh:
+			return fmt.Errorf("OCA authentication stream error: %w", err)
+		case state := <-l.updatesCh:
+			if isOCAStateAuthenticated(state) {
+				return nil
+			}
+		}
+	}
+}
+
+// Stop closes the stream and cleans up resources
+func (l *OcaAuthStatusListener) Stop() {
+	l.cancel()
+}
+
+func isOCAStateAuthenticated(state *cline.OcaAuthState) bool {
+	return state != nil && state.User != nil
+}
+
+// Singleton holder
+var (
+	ocaListener     *OcaAuthStatusListener
+	ocaListenerOnce sync.Once
+	ocaListenerErr  error
+)
+
+// GetOcaAuthListener returns the OCA auth listener singleton
+func GetOcaAuthListener(ctx context.Context) (*OcaAuthStatusListener, error) {
+	// Allow optional ctx: if nil, use context.TODO(). If already initialized, return singleton.
+	if ctx == nil {
+		ctx = context.TODO()
+	}
+
+	ocaListenerOnce.Do(func() {
+		l, err := NewOcaAuthStatusListener(ctx)
+		if err != nil {
+			ocaListenerErr = err
+			return
+		}
+		if err := l.Start(); err != nil {
+			ocaListenerErr = err
+			return
+		}
+		ocaListener = l
+	})
+	return ocaListener, ocaListenerErr
+}
+
+// IsOCAAuthenticated returns true if the global OCA auth status is authenticated.
+// It attempts a brief wait for the first event to avoid stale reads.
+func IsOCAAuthenticated(ctx context.Context) bool {
+	l, err := GetOcaAuthListener(ctx)
+	if err != nil {
+		return false
+	}
+	_ = l.WaitForFirstEvent(1 * time.Second) // best-effort
+	return l.IsAuthenticated()
+}
+
+ // LatestState returns the last received OCA auth state (may be nil)
+func (l *OcaAuthStatusListener) LatestState() *cline.OcaAuthState {
+	l.mu.RLock()
+	defer l.mu.RUnlock()
+	return l.lastState
+}
+
+// GetLatestOCAState returns the latest known OCA auth state, optionally waiting for the first event
+func GetLatestOCAState(ctx context.Context, timeout time.Duration) (*cline.OcaAuthState, error) {
+	l, err := GetOcaAuthListener(ctx)
+	if err != nil {
+		return nil, err
+	}
+	if timeout > 0 {
+		if err := l.WaitForFirstEvent(timeout); err != nil {
+			return nil, err
+		}
+	}
+	return l.LatestState(), nil
+}
+
+// ensureOcaAuthenticated initiates OCA login (if needed) and waits for success using the singleton listener
+func ensureOcaAuthenticated(ctx context.Context) error {
+	// Ensure listener exists
+	listener, err := GetOcaAuthListener(ctx)
+	if err != nil {
+		return fmt.Errorf("failed to initialize OCA auth listener: %w", err)
+	}
+
+	// Briefly wait for first event to know current state
+	_ = listener.WaitForFirstEvent(1 * time.Second)
+
+	// If already authenticated, nothing to do
+	if listener.IsAuthenticated() {
+		fmt.Println("✓ OCA authentication already active.")
+		return nil
+	}
+
+	// Create gRPC client for initiating login
+	client, err := global.GetDefaultClient(ctx)
+	if err != nil {
+		return fmt.Errorf("failed to obtain client: %w", err)
+	}
+
+	// Start login and wait for authentication
+	waitCtx, cancel := context.WithTimeout(ctx, 5*time.Minute)
+	defer cancel()
+
+	// Initiate login (opens the browser with a callback URL from Cline Core)
+	response, err := client.Ocaaccount.OcaAccountLoginClicked(waitCtx, &cline.EmptyRequest{})
+	if err != nil {
+		return fmt.Errorf("failed to initiate OCA login: %w", err)
+	}
+
+	fmt.Println("\nOpening browser for OCA authentication...")
+	if response != nil && response.Value != "" {
+		fmt.Printf("If the browser doesn't open automatically, visit this URL:\n%s\n\n", response.Value)
+	}
+	fmt.Println("Waiting for you to complete OCA authentication in your browser...")
+	fmt.Println("(This may take a few moments. Timeout: 5 minutes)")
+
+	// Block until authenticated or timeout
+	if err := listener.WaitForAuthentication(5 * time.Minute); err != nil {
+		return err
+	}
+
+	fmt.Println("✓ OCA authentication successful!")
+	return nil
+}

cli/pkg/cli/config.go

@@ -123,7 +123,10 @@ func setCommand() *cobra.Command {
 		Use:     "set <key=value> [key=value...]",
 		Aliases: []string{"s"},
 		Short:   "Set configuration variables",
-		Long:    `Set one or more global configuration variables using key=value format.`,
+		Long:    `Set one or more global configuration variables using key=value format.
+		
+This command merges the provided settings with existing values, preserving
+unspecified fields. Only the fields you explicitly set will be updated.`,
 		Args:    cobra.MinimumNArgs(1),
 		RunE: func(cmd *cobra.Command, args []string) error {
 			ctx := cmd.Context()
@@ -139,7 +142,7 @@ func setCommand() *cobra.Command {
 				return err
 			}
 
-			// Update settings
+			// Update settings (server-side merge handles preserving existing values)
 			return configManager.UpdateSettings(ctx, settings, secrets)
 		},
 	}

cli/pkg/cli/config/settings_renderer.go

@@ -189,7 +189,7 @@ func renderAutoApprovalSettings(value interface{}, censor bool) error {
 				}
 			}
 		} else {
-			// Print other fields normally (enabled, maxRequests, enableNotifications, favorites)
+			// Print other fields normally (enabled, enableNotifications, favorites)
 			fmt.Printf("  %s: %s\n", camelToKebab(key), formatValue(val, key, censor))
 		}
 	}

cli/pkg/cli/display/renderer.go

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"strings"
 
+	"github.com/charmbracelet/lipgloss"
 	"github.com/cline/cli/pkg/cli/global"
 	"github.com/cline/cli/pkg/cli/output"
 	"github.com/cline/cli/pkg/cli/types"
@@ -14,6 +15,16 @@ type Renderer struct {
 	typewriter   *TypewriterPrinter
 	mdRenderer   *MarkdownRenderer
 	outputFormat string
+
+	// Lipgloss styles that respect outputFormat
+	dimStyle     lipgloss.Style
+	greenStyle   lipgloss.Style
+	redStyle     lipgloss.Style
+	yellowStyle  lipgloss.Style
+	blueStyle    lipgloss.Style
+	whiteStyle   lipgloss.Style
+	boldStyle    lipgloss.Style
+	successStyle lipgloss.Style
 }
 
 func NewRenderer(outputFormat string) *Renderer {
@@ -22,11 +33,23 @@ func NewRenderer(outputFormat string) *Renderer {
 		mdRenderer = nil
 	}
 
-	return &Renderer{
+	r := &Renderer{
 		typewriter:   NewTypewriterPrinter(DefaultTypewriterConfig()),
 		mdRenderer:   mdRenderer,
 		outputFormat: outputFormat,
 	}
+
+	// Initialize lipgloss styles (will respect the global color profile)
+	r.dimStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("8"))
+	r.greenStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("2"))
+	r.redStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("1"))
+	r.yellowStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("3"))
+	r.blueStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("39"))
+	r.whiteStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("7"))
+	r.boldStyle = lipgloss.NewStyle().Bold(true)
+	r.successStyle = lipgloss.NewStyle().Foreground(lipgloss.Color("2")).Bold(true)
+
+	return r
 }
 
 func (r *Renderer) RenderMessage(prefix, text string, newline bool) error {
@@ -206,21 +229,76 @@ func (r *Renderer) GetMdRenderer() *MarkdownRenderer {
 
 // RenderMarkdown renders markdown text to terminal format with ANSI codes
 // Falls back to plaintext if markdown rendering is unavailable or fails
-// Respects output format - skips rendering in plain mode
+// Respects output format - skips rendering in plain mode or non-TTY contexts
 func (r *Renderer) RenderMarkdown(markdown string) string {
-	// Skip markdown rendering in plain mode
-	if r.outputFormat == "plain" {
+	// Skip markdown rendering if:
+	// 1. Output format is explicitly "plain"
+	// 2. Not in a TTY (piped output, file redirect, CI, etc.)
+	if r.outputFormat == "plain" || !isTTY() {
 		return markdown
 	}
-	
+
 	if r.mdRenderer == nil {
 		return markdown
 	}
-	
+
 	rendered, err := r.mdRenderer.Render(markdown)
 	if err != nil {
 		return markdown
 	}
-	
+
 	return rendered
 }
+
+// Lipgloss-based color rendering methods
+// These automatically respect the output format via lipgloss color profile
+
+// Dim renders text in dim gray (bright black)
+func (r *Renderer) Dim(text string) string {
+	return r.dimStyle.Render(text)
+}
+
+// Green renders text in green
+func (r *Renderer) Green(text string) string {
+	return r.greenStyle.Render(text)
+}
+
+// Red renders text in red
+func (r *Renderer) Red(text string) string {
+	return r.redStyle.Render(text)
+}
+
+// Yellow renders text in yellow
+func (r *Renderer) Yellow(text string) string {
+	return r.yellowStyle.Render(text)
+}
+
+// Blue renders text in 256-color blue (index 39)
+func (r *Renderer) Blue(text string) string {
+	return r.blueStyle.Render(text)
+}
+
+// White renders text in white
+func (r *Renderer) White(text string) string {
+	return r.whiteStyle.Render(text)
+}
+
+// Bold renders text in bold
+func (r *Renderer) Bold(text string) string {
+	return r.boldStyle.Render(text)
+}
+
+// Success renders text in green with bold
+func (r *Renderer) Success(text string) string {
+	return r.successStyle.Render(text)
+}
+
+// SuccessWithCheckmark renders text in green with bold and a checkmark prefix
+func (r *Renderer) SuccessWithCheckmark(text string) string {
+	return r.Success("✓ " + text)
+}
+
+// ErrorWithX renders text in red with an X prefix
+func (r *Renderer) ErrorWithX(text string) string {
+	return r.Red("✗ " + text)
+}

cli/pkg/cli/display/segment_streamer.go

@@ -36,8 +36,8 @@ func NewStreamingSegment(sayType, prefix string, mdRenderer *MarkdownRenderer, s
 		toolParser:     NewToolResultParser(mdRenderer),
 	}
 
-	// Render rich header immediately when creating segment (if in rich mode)
-	if shouldMarkdown && outputFormat != "plain" {
+	// Render rich header immediately when creating segment (if in rich mode and TTY)
+	if shouldMarkdown && outputFormat != "plain" && isTTY() {
 		header := ss.generateRichHeader()
 		rendered, _ := mdRenderer.Render(header)
 		output.Println("")
@@ -113,8 +113,8 @@ func (ss *StreamingSegment) renderFinal(currentBuffer string) {
 	} else if ss.sayType == string(types.SayTypeCommand) {
 		// Command output
 		bodyContent = "```shell\n" + currentBuffer + "\n```"
-		// Render markdown
-		if ss.shouldMarkdown && ss.outputFormat != "plain" {
+		// Render markdown only in rich mode and TTY
+		if ss.shouldMarkdown && ss.outputFormat != "plain" && isTTY() {
 			rendered, err := ss.mdRenderer.Render(bodyContent)
 			if err == nil {
 				bodyContent = rendered
@@ -122,7 +122,7 @@ func (ss *StreamingSegment) renderFinal(currentBuffer string) {
 		}
 	} else {
 		// For other types (reasoning, text, etc.), render markdown as-is
-		if ss.shouldMarkdown && ss.outputFormat != "plain" {
+		if ss.shouldMarkdown && ss.outputFormat != "plain" && isTTY() {
 			rendered, err := ss.mdRenderer.Render(currentBuffer)
 			if err == nil {
 				bodyContent = rendered

cli/pkg/cli/display/tool_renderer.go

@@ -106,6 +106,14 @@ func (tr *ToolRenderer) generateToolHeader(tool *types.ToolMessage, verbTense st
 		}
 		return fmt.Sprintf("### Cline %s `%s`", action, tool.Path)
 
+	case string(types.ToolTypeFileDeleted):
+		if verbTense == "wants to" {
+			action = "wants to delete"
+		} else {
+			action = "is deleting"
+		}
+		return fmt.Sprintf("### Cline %s `%s`", action, tool.Path)
+
 	case string(types.ToolTypeListFilesTopLevel):
 		if verbTense == "wants to" {
 			action = "wants to list files in"
@@ -199,7 +207,7 @@ func (tr *ToolRenderer) GenerateToolContentPreview(tool *types.ToolMessage) stri
 		previewMd := fmt.Sprintf("```\n%s\n```", preview)
 		return tr.renderMarkdown(previewMd)
 
-	case string(types.ToolTypeReadFile), string(types.ToolTypeWebFetch):
+	case string(types.ToolTypeReadFile), string(types.ToolTypeWebFetch), string(types.ToolTypeFileDeleted):
 		// No preview for read/fetch operations
 		return ""
 
@@ -226,7 +234,8 @@ func (tr *ToolRenderer) GenerateToolContentBody(tool *types.ToolMessage) string
 	toolParser := NewToolResultParser(tr.mdRenderer)
 
 	switch tool.Tool {
-	case string(types.ToolTypeReadFile):
+	case string(types.ToolTypeReadFile),
+		string(types.ToolTypeFileDeleted):
 		// readFile: show header only, no body
 		return ""
 
@@ -339,9 +348,10 @@ func (tr *ToolRenderer) RenderUserResponse(approved bool, feedback string) strin
 	return fmt.Sprintf("%s %s\n", symbol, status)
 }
 
-// renderMarkdown renders markdown if not in plain mode
+// renderMarkdown renders markdown if not in plain mode and in a TTY
 func (tr *ToolRenderer) renderMarkdown(markdown string) string {
-	if tr.outputFormat == "plain" {
+	// Skip markdown rendering if plain mode or not in TTY
+	if tr.outputFormat == "plain" || !isTTY() {
 		return markdown
 	}
 

cli/pkg/cli/doctor.go

@@ -0,0 +1,65 @@
+package cli
+
+import (
+	"fmt"
+
+	"github.com/cline/cli/pkg/cli/display"
+	"github.com/cline/cli/pkg/cli/global"
+	"github.com/cline/cli/pkg/cli/terminal"
+	"github.com/cline/cli/pkg/cli/updater"
+	"github.com/spf13/cobra"
+)
+
+// NewDoctorCommand creates the doctor command
+func NewDoctorCommand() *cobra.Command {
+	cmd := &cobra.Command{
+		Use:     "doctor",
+		Aliases: []string{"d"},
+		Short:   "Check system health and diagnose problems",
+		Long: `Check the health of your Cline CLI installation and diagnose problems.
+
+Currently this command performs the following checks and fixes:
+
+Terminal Configuration:
+  - Detects your terminal emulator (VS Code, Cursor, Ghostty, Kitty, WezTerm, Alacritty)
+  - Configures shift+enter to insert newlines in multiline input
+  - Creates backups before modifying configuration files
+  - Supported terminals: VS Code, Cursor, Ghostty, Kitty, WezTerm, Alacritty
+  - iTerm2 works by default, Terminal.app requires manual setup
+
+CLI Updates:
+  - Checks npm registry for the latest version
+  - Automatically installs updates via npm if available
+  - Respects NO_AUTO_UPDATE environment variable
+  - Skipped in CI environments
+
+Note: Future versions will include additional health checks for Node.js version,
+npm availability, Cline Core connectivity, database integrity, and more.`,
+		RunE: func(cmd *cobra.Command, args []string) error {
+			return runDoctorChecks()
+		},
+	}
+
+	return cmd
+}
+
+// runDoctorChecks performs all doctor diagnostics and configuration
+func runDoctorChecks() error {
+	renderer := display.NewRenderer(global.Config.OutputFormat)
+
+	fmt.Printf("\n%s\n\n", renderer.Bold("Cline Doctor - System Health Check"))
+
+	// Configure terminal keybindings (terminal.go prints its own status)
+	fmt.Printf("%s\n\n", renderer.Dim("━━━ Terminal Configuration ━━━"))
+	terminal.SetupKeyboardSync()
+
+	// Check for updates (updater.go prints its own status)
+	fmt.Printf("\n%s\n\n", renderer.Dim("━━━ CLI Updates ━━━"))
+	updater.CheckAndUpdateSync(global.Config.Verbose, true)
+
+	// Summary
+	fmt.Printf("\n%s\n", renderer.Dim("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"))
+	fmt.Printf("\n%s\n\n", renderer.SuccessWithCheckmark("Health check complete"))
+
+	return nil
+}

cli/pkg/cli/global/global.go

@@ -6,8 +6,10 @@ import (
 	"os"
 	"path/filepath"
 
+	"github.com/charmbracelet/lipgloss"
 	"github.com/cline/cli/pkg/common"
 	"github.com/cline/grpc-go/client"
+	"github.com/muesli/termenv"
 )
 
 type Port uint16
@@ -47,6 +49,12 @@ func InitializeGlobalConfig(cfg *GlobalConfig) error {
 		return fmt.Errorf("failed to create config directory: %w", err)
 	}
 
+	// Configure lipgloss color profile based on output format
+	if cfg.OutputFormat == "plain" {
+		lipgloss.SetColorProfile(termenv.Ascii) // NO COLOR mode
+	}
+	// Otherwise lipgloss auto-detects terminal capabilities (default behavior)
+
 	Config = cfg
 	Clients = NewClineClients(cfg.ConfigPath)
 

cli/pkg/cli/handlers/ask_handlers.go

@@ -52,8 +52,6 @@ func (h *AskHandler) Handle(msg *types.ClineMessage, dc *DisplayContext) error {
 		return h.handleResumeCompletedTask(msg, dc)
 	case string(types.AskTypeMistakeLimitReached):
 		return h.handleMistakeLimitReached(msg, dc)
-	case string(types.AskTypeAutoApprovalMaxReached):
-		return h.handleAutoApprovalMaxReached(msg, dc)
 	case string(types.AskTypeBrowserActionLaunch):
 		return h.handleBrowserActionLaunch(msg, dc)
 	case string(types.AskTypeUseMcpServer):
@@ -71,22 +69,25 @@ func (h *AskHandler) Handle(msg *types.ClineMessage, dc *DisplayContext) error {
 
 // handleFollowup handles followup questions
 func (h *AskHandler) handleFollowup(msg *types.ClineMessage, dc *DisplayContext) error {
-	// Use ToolRenderer for unified rendering
-	header := dc.ToolRenderer.GenerateAskFollowupHeader()
 	body := dc.ToolRenderer.GenerateAskFollowupBody(msg.Text)
 
 	if body == "" {
 		return nil
 	}
 
-	// Render header
-	rendered := dc.Renderer.RenderMarkdown(header)
-	output.Print("\n")
-	output.Print(rendered)
-	output.Print("\n")
-
-	// Render body
-	output.Print(body)
+	if dc.IsStreamingMode {
+		// In streaming mode, header was already shown by partial stream
+		// Just render the body content
+		output.Print(body)
+	} else {
+		// Non-streaming mode: render header + body together
+		header := dc.ToolRenderer.GenerateAskFollowupHeader()
+		rendered := dc.Renderer.RenderMarkdown(header)
+		output.Print("\n")
+		output.Print(rendered)
+		output.Print("\n")
+		output.Print(body)
+	}
 
 	return nil
 }
@@ -125,8 +126,8 @@ func (h *AskHandler) handlePlanModeRespond(msg *types.ClineMessage, dc *DisplayC
 // showApprovalHint displays a hint in non-interactive mode about how to approve/deny
 func (h *AskHandler) showApprovalHint(dc *DisplayContext) {
 	if !dc.IsInteractive {
-		output.Printf("\n\033[90mCline is requesting approval to use this tool\033[0m\n")
-		output.Printf("\033[90mUse \033[0mcline task send --approve\033[90m or \033[0m--deny\033[90m to respond\033[0m\n")
+		output.Printf("\n%s\n", dc.Renderer.Dim("Cline is requesting approval to use this tool"))
+		output.Printf("%s\n", dc.Renderer.Dim("Use cline task send --approve or --deny to respond"))
 	}
 }
 
@@ -177,9 +178,19 @@ func (h *AskHandler) handleTool(msg *types.ClineMessage, dc *DisplayContext) err
 		return dc.Renderer.RenderMessage("TOOL", msg.Text, true)
 	}
 
-	// Use unified ToolRenderer
-	rendered := dc.ToolRenderer.RenderToolApprovalRequest(&tool)
-	output.Print(rendered)
+	if dc.IsStreamingMode {
+		// In streaming mode, header was already shown by partial stream
+		// Just render the content preview
+		contentPreview := dc.ToolRenderer.GenerateToolContentPreview(&tool)
+		if contentPreview != "" {
+			output.Print("\n")
+			output.Print(contentPreview)
+		}
+	} else {
+		// Non-streaming mode: render full approval (header + preview)
+		rendered := dc.ToolRenderer.RenderToolApprovalRequest(&tool)
+		output.Print(rendered)
+	}
 
 	h.showApprovalHint(dc)
 	return nil
@@ -242,25 +253,6 @@ func (h *AskHandler) handleMistakeLimitReached(msg *types.ClineMessage, dc *Disp
 	return dc.Renderer.RenderMessage("ERROR", fmt.Sprintf("Mistake Limit Reached: %s. Approval required.", msg.Text), true)
 }
 
-// handleAutoApprovalMaxReached handles auto-approval max reached
-func (h *AskHandler) handleAutoApprovalMaxReached(msg *types.ClineMessage, dc *DisplayContext) error {
-	if dc.SystemRenderer != nil {
-		details := make(map[string]string)
-		if msg.Text != "" {
-			details["reason"] = msg.Text
-		}
-		dc.SystemRenderer.RenderError(
-			"warning",
-			"Auto-Approval Limit Reached",
-			"The maximum number of auto-approved requests has been reached. Manual approval is now required.",
-			details,
-		)
-		fmt.Printf("\n**Approval required to continue.**\n")
-		return nil
-	}
-	return dc.Renderer.RenderMessage("WARNING", fmt.Sprintf("Auto-approval limit reached: %s. Approval required.", msg.Text), true)
-}
-
 // handleBrowserActionLaunch handles browser action launch requests
 func (h *AskHandler) handleBrowserActionLaunch(msg *types.ClineMessage, dc *DisplayContext) error {
 	url := strings.TrimSpace(msg.Text)

cli/pkg/cli/instances.go

@@ -389,20 +389,21 @@ func newInstanceListCommand() *cobra.Command {
 				}
 
 				// Render the markdown table with terminal width for nice table layout
-				renderer, err := display.NewMarkdownRendererForTerminal()
+				mdRenderer, err := display.NewMarkdownRendererForTerminal()
 				if err != nil {
 					// Fallback to plain table if markdown renderer fails
 					fmt.Println(markdown.String())
 				} else {
-					rendered, err := renderer.Render(markdown.String())
+					rendered, err := mdRenderer.Render(markdown.String())
 					if err != nil {
 						fmt.Println(markdown.String())
 					} else {
 						// Post-process to colorize status values
-						rendered = strings.ReplaceAll(rendered, "SERVING", "\033[32mSERVING\033[0m")         // Green
-						rendered = strings.ReplaceAll(rendered, "✓", "\033[32m✓\033[0m")                     // Green
-						rendered = strings.ReplaceAll(rendered, "NOT_SERVING", "\033[31mNOT_SERVING\033[0m") // Red
-						rendered = strings.ReplaceAll(rendered, "UNKNOWN", "\033[33mUNKNOWN\033[0m")         // Yellow
+						colorRenderer := display.NewRenderer(global.Config.OutputFormat)
+						rendered = strings.ReplaceAll(rendered, "SERVING", colorRenderer.Green("SERVING"))
+						rendered = strings.ReplaceAll(rendered, "✓", colorRenderer.Green("✓"))
+						rendered = strings.ReplaceAll(rendered, "NOT_SERVING", colorRenderer.Red("NOT_SERVING"))
+						rendered = strings.ReplaceAll(rendered, "UNKNOWN", colorRenderer.Yellow("UNKNOWN"))
 
 						fmt.Print(strings.TrimLeft(rendered, "\n"))
 					}

cli/pkg/cli/logs.go

@@ -208,9 +208,9 @@ func listLogFiles(logsDir string) ([]logFileInfo, error) {
 		})
 	}
 
-	// Sort by created time (newest first)
+	// Sort by created time (oldest first)
 	sort.Slice(logs, func(i, j int) bool {
-		return logs[i].created.After(logs[j].created)
+		return logs[i].created.Before(logs[j].created)
 	})
 
 	return logs, nil
@@ -340,6 +340,7 @@ func renderLogsTable(logs []logFileInfo, markForDeletion bool) error {
 	}
 
 	// Use markdown table for rich output
+	colorRenderer := display.NewRenderer(global.Config.OutputFormat)
 	var markdown strings.Builder
 	markdown.WriteString("| **FILENAME** | **SIZE** | **CREATED** | **AGE** |\n")
 	markdown.WriteString("|--------------|----------|-------------|---------|")
@@ -352,9 +353,9 @@ func renderLogsTable(logs []logFileInfo, markForDeletion bool) error {
 			row.age,
 		)
 
-		// If marking for deletion, wrap in red ANSI codes
+		// If marking for deletion, wrap in red
 		if markForDeletion {
-			line = "\033[31m" + line + "\033[0m"
+			line = colorRenderer.Red(line)
 		}
 
 		markdown.WriteString(line)
@@ -378,4 +379,4 @@ func renderLogsTable(logs []logFileInfo, markForDeletion bool) error {
 	fmt.Println()
 
 	return nil
-}
+}

cli/pkg/cli/output/input_model.go

@@ -24,10 +24,11 @@ const (
 
 // InputSubmitMsg is sent when the user submits input
 type InputSubmitMsg struct {
-	Value      string
-	InputType  InputType
-	Approved   bool   // For approval type
-	NeedsFeedback bool // For approval type
+	Value          string
+	InputType      InputType
+	Approved       bool // For approval type
+	NeedsFeedback  bool // For approval type
+	NoAskAgain     bool // For approval type - indicates "don't ask again" was selected
 }
 
 // InputCancelMsg is sent when the user cancels input (Ctrl+C)
@@ -159,8 +160,7 @@ func NewInputModel(inputType InputType, title, placeholder, currentMode string)
 	if inputType == InputTypeApproval {
 		m.approvalOptions = []string{
 			"Yes",
-			"Yes, with feedback",
-			"No",
+			"Yes, and don't ask again for this task",
 			"No, with feedback",
 		}
 		m.selectedOption = 0
@@ -210,8 +210,7 @@ func (m *InputModel) Update(msg tea.Msg) (tea.Model, tea.Cmd) {
 		if msg.InputType == InputTypeApproval {
 			m.approvalOptions = []string{
 				"Yes",
-				"Yes, with feedback",
-				"No",
+				"Yes, and don't ask again for this task",
 				"No, with feedback",
 			}
 			m.selectedOption = 0
@@ -298,6 +297,7 @@ func (m *InputModel) handleSubmit() (tea.Model, tea.Cmd) {
 		selected := m.approvalOptions[m.selectedOption]
 		approved := strings.HasPrefix(selected, "Yes")
 		needsFeedback := strings.Contains(selected, "feedback")
+		noAskAgain := strings.Contains(selected, "don't ask again")
 
 		if needsFeedback {
 			// Store the approval decision before switching to feedback input
@@ -318,6 +318,7 @@ func (m *InputModel) handleSubmit() (tea.Model, tea.Cmd) {
 				InputType:     InputTypeApproval,
 				Approved:      approved,
 				NeedsFeedback: false,
+				NoAskAgain:    noAskAgain,
 			}
 		}
 

cli/pkg/cli/task.go

@@ -14,6 +14,7 @@ import (
 	"github.com/cline/cli/pkg/cli/global"
 	"github.com/cline/cli/pkg/cli/task"
 	"github.com/cline/cli/pkg/cli/updater"
+	"github.com/cline/grpc-go/cline"
 	"github.com/spf13/cobra"
 )
 
@@ -476,15 +477,34 @@ func newTaskOpenCommand() *cobra.Command {
 					return fmt.Errorf("failed to parse settings: %w", err)
 				}
 
-				// Create config manager to apply settings
-				configManager, err := config.NewManager(ctx, taskManager.GetCurrentInstance())
-				if err != nil {
-					return fmt.Errorf("failed to create config manager: %w", err)
+				// Apply task-specific settings using UpdateTaskSettings RPC
+				if parsedSettings != nil {
+					_, err = taskManager.GetClient().State.UpdateTaskSettings(ctx, &cline.UpdateTaskSettingsRequest{
+						Settings: parsedSettings,
+						TaskId:   &taskID,
+					})
+					if err != nil {
+						return fmt.Errorf("failed to apply task settings: %w", err)
+					}
+					if global.Config.Verbose {
+						fmt.Println("Task-specific settings applied successfully")
+					}
 				}
 
-				// Apply the settings to the instance
-				if err := configManager.UpdateSettings(ctx, parsedSettings, secrets); err != nil {
-					return fmt.Errorf("failed to apply settings: %w", err)
+				// Handle secrets separately if provided (they must go to global config)
+				if secrets != nil {
+					// Secrets are always global, not task-specific
+					configManager, err := config.NewManager(ctx, taskManager.GetCurrentInstance())
+					if err != nil {
+						return fmt.Errorf("failed to create config manager: %w", err)
+					}
+
+					if err := configManager.UpdateSettings(ctx, nil, secrets); err != nil {
+						return fmt.Errorf("failed to apply secrets: %w", err)
+					}
+					if global.Config.Verbose {
+						fmt.Println("Global secrets applied successfully")
+					}
 				}
 			}
 
@@ -572,17 +592,20 @@ func getContentFromStdinAndArgs(args []string) (string, error) {
 
 	// Check if data is being piped to stdin
 	if (stat.Mode() & os.ModeCharDevice) == 0 {
-		stdinBytes, err := io.ReadAll(os.Stdin)
-		if err != nil {
-			return "", fmt.Errorf("failed to read from stdin: %w", err)
-		}
-
-		stdinContent := strings.TrimSpace(string(stdinBytes))
-		if stdinContent != "" {
-			if content.Len() > 0 {
-				content.WriteString(" ")
+		// Only try to read if there's actually data available
+		if stat.Size() > 0 {
+			stdinBytes, err := io.ReadAll(os.Stdin)
+			if err != nil {
+				return "", fmt.Errorf("failed to read from stdin: %w", err)
+			}
+
+			stdinContent := strings.TrimSpace(string(stdinBytes))
+			if stdinContent != "" {
+				if content.Len() > 0 {
+					content.WriteString(" ")
+				}
+				content.WriteString(stdinContent)
 			}
-			content.WriteString(stdinContent)
 		}
 	}
 
@@ -649,4 +672,4 @@ func CreateAndFollowTask(ctx context.Context, prompt string, opts TaskOptions) e
 	} else {
 		return taskManager.FollowConversation(ctx, taskManager.GetCurrentInstance(), true)
 	}
-}
+}

cli/pkg/cli/task/input_handler.go

@@ -2,6 +2,7 @@ package task
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"strings"
@@ -9,6 +10,7 @@ import (
 	"time"
 
 	tea "github.com/charmbracelet/bubbletea"
+	"github.com/charmbracelet/lipgloss"
 	"github.com/cline/cli/pkg/cli/global"
 	"github.com/cline/cli/pkg/cli/output"
 	"github.com/cline/cli/pkg/cli/types"
@@ -16,20 +18,21 @@ import (
 
 // InputHandler manages interactive user input during follow mode
 type InputHandler struct {
-	manager         *Manager
-	coordinator     *StreamCoordinator
-	cancelFunc      context.CancelFunc
-	mu              sync.RWMutex
-	isRunning       bool
-	pollTicker      *time.Ticker
-	program         *tea.Program
-	programRunning  bool
-	programDoneChan chan struct{} // Signals when program actually exits
-	resultChan      chan output.InputSubmitMsg
-	cancelChan      chan struct{}
-	feedbackApproval bool // Track if we're in feedback after approval
-	feedbackApproved bool // Track the approval decision
-	ctx             context.Context // Context for restart callback
+	manager          *Manager
+	coordinator      *StreamCoordinator
+	cancelFunc       context.CancelFunc
+	mu               sync.RWMutex
+	isRunning        bool
+	pollTicker       *time.Ticker
+	program          *tea.Program
+	programRunning   bool
+	programDoneChan  chan struct{} // Signals when program actually exits
+	resultChan       chan output.InputSubmitMsg
+	cancelChan       chan struct{}
+	feedbackApproval bool                // Track if we're in feedback after approval
+	feedbackApproved bool                // Track the approval decision
+	approvalMessage  *types.ClineMessage // Store the approval message for determining action
+	ctx              context.Context     // Context for restart callback
 }
 
 // NewInputHandler creates a new input handler
@@ -162,6 +165,10 @@ func (ih *InputHandler) Start(ctx context.Context, errChan chan error) {
 				// Check for mode switch commands first
 				newMode, remainingMessage, isModeSwitch := ih.parseModeSwitch(message)
 				if isModeSwitch {
+					// Create styles for mode switch messages (respect global color profile)
+					actStyle := lipgloss.NewStyle().Foreground(lipgloss.Color("39")).Bold(true)
+					planStyle := lipgloss.NewStyle().Foreground(lipgloss.Color("3")).Bold(true)
+
 					if remainingMessage != "" {
 						// Switching with a message - behavior differs by mode
 						if newMode == "act" {
@@ -170,16 +177,14 @@ func (ih *InputHandler) Start(ctx context.Context, errChan chan error) {
 								output.Printf("\nError switching to act mode with message: %v\n", err)
 								continue
 							}
-							// 256-color index 39 for act mode (matches lipgloss color "39" in input form)
-							output.Printf("\n\033[38;5;39m\033[1mSwitched to act mode\033[0m\n")
+							output.Printf("\n%s\n", actStyle.Render("Switched to act mode"))
 						} else {
 							// Plan mode: must switch first, then send message separately
 							if err := ih.manager.SetMode(ctx, newMode, nil, nil, nil); err != nil {
 								output.Printf("\nError switching to plan mode: %v\n", err)
 								continue
 							}
-							// Yellow color for plan mode (ANSI color 3)
-							output.Printf("\n\033[33m\033[1mSwitched to plan mode\033[0m\n")
+							output.Printf("\n%s\n", planStyle.Render("Switched to plan mode"))
 
 							// Now send the message separately
 							time.Sleep(500 * time.Millisecond) // Give mode switch time to process
@@ -196,9 +201,9 @@ func (ih *InputHandler) Start(ctx context.Context, errChan chan error) {
 						}
 						// Color based on mode
 						if newMode == "act" {
-							output.Printf("\n\033[38;5;39m\033[1mSwitched to act mode\033[0m\n")
+							output.Printf("\n%s\n", actStyle.Render("Switched to act mode"))
 						} else {
-							output.Printf("\n\033[33m\033[1mSwitched to plan mode\033[0m\n")
+							output.Printf("\n%s\n", planStyle.Render("Switched to plan mode"))
 						}
 					}
 
@@ -229,6 +234,48 @@ func (ih *InputHandler) Start(ctx context.Context, errChan chan error) {
 	}
 }
 
+// determineAutoApprovalAction determines which auto-approval action to enable based on the ask type
+func determineAutoApprovalAction(msg *types.ClineMessage) (string, error) {
+	switch types.AskType(msg.Ask) {
+	case types.AskTypeTool:
+		// Parse tool message to determine if it's a read or edit operation
+		var toolMsg types.ToolMessage
+		if err := json.Unmarshal([]byte(msg.Text), &toolMsg); err != nil {
+			return "", fmt.Errorf("failed to parse tool message: %w", err)
+		}
+
+		// Determine action based on tool type
+		switch types.ToolType(toolMsg.Tool) {
+		case types.ToolTypeReadFile,
+			types.ToolTypeListFilesTopLevel,
+			types.ToolTypeListFilesRecursive,
+			types.ToolTypeListCodeDefinitionNames,
+			types.ToolTypeSearchFiles,
+			types.ToolTypeWebFetch:
+			return "read_files", nil
+		case types.ToolTypeEditedExistingFile,
+			types.ToolTypeNewFileCreated:
+			return "edit_files", nil
+		case types.ToolTypeFileDeleted:
+			return "apply_patch", nil
+		default:
+			return "", fmt.Errorf("unsupported tool type: %s", toolMsg.Tool)
+		}
+
+	case types.AskTypeCommand:
+		return "execute_all_commands", nil
+
+	case types.AskTypeBrowserActionLaunch:
+		return "use_browser", nil
+
+	case types.AskTypeUseMcpServer:
+		return "use_mcp", nil
+
+	default:
+		return "", fmt.Errorf("unsupported ask type: %s", msg.Ask)
+	}
+}
+
 // promptForInput displays an interactive prompt and waits for user input
 func (ih *InputHandler) promptForInput(ctx context.Context) (string, bool, error) {
 	currentMode := ih.manager.GetCurrentMode()
@@ -245,6 +292,9 @@ func (ih *InputHandler) promptForInput(ctx context.Context) (string, bool, error
 
 // promptForApproval displays an approval prompt for tool/command requests
 func (ih *InputHandler) promptForApproval(ctx context.Context, msg *types.ClineMessage) (bool, string, error) {
+	// Store the approval message for later use in determining auto-approval action
+	ih.approvalMessage = msg
+	
 	model := output.NewInputModel(
 		output.InputTypeApproval,
 		"Let Cline use this tool?",
@@ -344,6 +394,23 @@ func (ih *InputHandler) runInputProgram(ctx context.Context, model output.InputM
 				// Need to collect feedback - will be handled by model state change
 				return "", false, nil
 			}
+			
+			// Check if NoAskAgain was selected
+			if result.NoAskAgain && result.Approved && ih.approvalMessage != nil {
+				// Determine which auto-approval action to enable
+				action, err := determineAutoApprovalAction(ih.approvalMessage)
+				if err != nil {
+					output.Printf("\nWarning: Could not determine auto-approval action: %v\n", err)
+				} else {
+					// Enable the auto-approval action
+					if err := ih.manager.UpdateTaskAutoApprovalAction(ctx, action); err != nil {
+						output.Printf("\nWarning: Could not update auto-approval: %v\n", err)
+					} else {
+						output.Printf("\nAuto-approval enabled for %s\n", action)
+					}
+				}
+			}
+			
 			// Store approval state for when feedback comes back
 			ih.feedbackApproval = false
 			ih.feedbackApproved = result.Approved

cli/pkg/cli/task/manager.go

@@ -282,7 +282,6 @@ func (m *Manager) CheckSendEnabled(ctx context.Context) error {
 	errorTypes := []string{
 		string(types.AskTypeAPIReqFailed),           // "api_req_failed"
 		string(types.AskTypeMistakeLimitReached),    // "mistake_limit_reached"
-		string(types.AskTypeAutoApprovalMaxReached), // "auto_approval_max_req_reached"
 	}
 
 	isError := false
@@ -1004,26 +1003,18 @@ func (m *Manager) processStateUpdate(stateUpdate *cline.State, coordinator *Stre
 
 		case msg.Ask == string(types.AskTypePlanModeRespond):
 			msgKey := fmt.Sprintf("%d", msg.Timestamp)
-			// In streaming mode, partial stream handles this message
-			// State stream should skip to avoid duplication
-			if m.isStreamingMode {
-				// Skip - partial stream already handled this
-			} else {
-				// Non-streaming mode: render normally when message is complete
-				if !msg.Partial && !coordinator.IsProcessedInCurrentTurn(msgKey) {
-					m.displayMessage(msg, false, false, i)
+			// Non-streaming mode: render normally when message is complete
+			if !msg.Partial && !coordinator.IsProcessedInCurrentTurn(msgKey) {
+				m.displayMessage(msg, false, false, i)
 
-					coordinator.MarkProcessedInCurrentTurn(msgKey)
-				}
+				coordinator.MarkProcessedInCurrentTurn(msgKey)
 			}
 
 		case msg.Type == types.MessageTypeAsk:
 			msgKey := fmt.Sprintf("%d", msg.Timestamp)
 			// Only render if not already handled by partial stream
-			if !coordinator.IsProcessedInCurrentTurn(msgKey) {
-				fmt.Println()
+			if !msg.Partial && !coordinator.IsProcessedInCurrentTurn(msgKey) {
 				m.displayMessage(msg, false, false, i)
-
 				coordinator.MarkProcessedInCurrentTurn(msgKey)
 			}
 		}
@@ -1245,10 +1236,48 @@ func (m *Manager) updateMode(stateJson string) {
 	m.mu.Unlock()
 }
 
+// UpdateTaskAutoApprovalAction enables a specific auto-approval action for the current task
+func (m *Manager) UpdateTaskAutoApprovalAction(ctx context.Context, actionKey string) error {
+	boolPtr := func(b bool) *bool { return &b }
+	
+	settings := &cline.Settings{
+		AutoApprovalSettings: &cline.AutoApprovalSettings{
+			Actions: &cline.AutoApprovalActions{},
+		},
+	}
+
+	// Set the specific action to true based on actionKey
+	truePtr := boolPtr(true)
+	
+	switch actionKey {
+	case "read_files":
+		settings.AutoApprovalSettings.Actions.ReadFiles = truePtr
+	case "edit_files":
+		settings.AutoApprovalSettings.Actions.EditFiles = truePtr
+	case "execute_all_commands":
+		settings.AutoApprovalSettings.Actions.ExecuteAllCommands = truePtr
+	case "use_browser":
+		settings.AutoApprovalSettings.Actions.UseBrowser = truePtr
+	case "use_mcp":
+		settings.AutoApprovalSettings.Actions.UseMcp = truePtr
+	default:
+		return fmt.Errorf("unknown auto-approval action: %s", actionKey)
+	}
+
+	_, err := m.client.State.UpdateTaskSettings(ctx, &cline.UpdateTaskSettingsRequest{
+		Settings: settings,
+	})
+	if err != nil {
+		return fmt.Errorf("failed to update task settings: %w", err)
+	}
+
+	return nil
+}
+
 // Cleanup cleans up resources
 func (m *Manager) Cleanup() {
 	// Clean up streaming display resources if needed
 	if m.streamingDisplay != nil {
 		m.streamingDisplay.Cleanup()
 	}
-}
+}

cli/pkg/cli/task/settings_parser.go

@@ -180,8 +180,6 @@ func setSimpleField(settings *cline.Settings, key, value string) error {
 		settings.PlanModeHuaweiCloudMaasModelId = strPtr(value)
 	case "plan_mode_oca_model_id":
 		settings.PlanModeOcaModelId = strPtr(value)
-	case "plan_mode_vercel_ai_gateway_model_id":
-		settings.PlanModeVercelAiGatewayModelId = strPtr(value)
 	case "act_mode_api_model_id":
 		settings.ActModeApiModelId = strPtr(value)
 	case "act_mode_reasoning_effort":
@@ -218,8 +216,6 @@ func setSimpleField(settings *cline.Settings, key, value string) error {
 		settings.ActModeHuaweiCloudMaasModelId = strPtr(value)
 	case "act_mode_oca_model_id":
 		settings.ActModeOcaModelId = strPtr(value)
-	case "act_mode_vercel_ai_gateway_model_id":
-		settings.ActModeVercelAiGatewayModelId = strPtr(value)
 
 	// Boolean fields
 	case "aws_use_cross_region_inference":
@@ -416,24 +412,12 @@ func setNestedField(settings *cline.Settings, parentField string, childFields ma
 func setAutoApprovalSettings(settings *cline.AutoApprovalSettings, fields map[string]string) error {
 	for key, value := range fields {
 		switch key {
-		case "enabled":
-			val, err := parseBool(value)
-			if err != nil {
-				return err
-			}
-			settings.Enabled = val
-		case "max_requests":
-			val, err := parseInt32(value)
-			if err != nil {
-				return err
-			}
-			settings.MaxRequests = val
 		case "enable_notifications":
 			val, err := parseBool(value)
 			if err != nil {
 				return err
 			}
-			settings.EnableNotifications = val
+			settings.EnableNotifications = boolPtr(val)
 		case "actions":
 			return fmt.Errorf("auto_approval_settings.actions requires nested dot notation (e.g., auto-approval-settings.actions.read-files=true)")
 		default:
@@ -464,21 +448,21 @@ func setAutoApprovalAction(actions *cline.AutoApprovalActions, key, value string
 
 	switch key {
 	case "read_files":
-		actions.ReadFiles = val
+		actions.ReadFiles = boolPtr(val)
 	case "read_files_externally":
-		actions.ReadFilesExternally = val
+		actions.ReadFilesExternally = boolPtr(val)
 	case "edit_files":
-		actions.EditFiles = val
+		actions.EditFiles = boolPtr(val)
 	case "edit_files_externally":
-		actions.EditFilesExternally = val
+		actions.EditFilesExternally = boolPtr(val)
 	case "execute_safe_commands":
-		actions.ExecuteSafeCommands = val
+		actions.ExecuteSafeCommands = boolPtr(val)
 	case "execute_all_commands":
-		actions.ExecuteAllCommands = val
+		actions.ExecuteAllCommands = boolPtr(val)
 	case "use_browser":
-		actions.UseBrowser = val
+		actions.UseBrowser = boolPtr(val)
 	case "use_mcp":
-		actions.UseMcp = val
+		actions.UseMcp = boolPtr(val)
 	default:
 		return fmt.Errorf("unsupported auto_approval_actions field '%s'", key)
 	}
@@ -672,6 +656,8 @@ func parseApiProvider(value string) (cline.ApiProvider, error) {
 		return cline.ApiProvider_DIFY, nil
 	case "oca":
 		return cline.ApiProvider_OCA, nil
+	case "minimax":
+		return cline.ApiProvider_MINIMAX, nil
 	default:
 		return cline.ApiProvider_ANTHROPIC, fmt.Errorf("invalid api_provider '%s'", value)
 	}
@@ -746,14 +732,14 @@ func setSecretField(secrets *cline.Secrets, key, value string) error {
 		secrets.HuaweiCloudMaasApiKey = strPtr(value)
 	case "baseten_api_key":
 		secrets.BasetenApiKey = strPtr(value)
-	case "vercel_ai_gateway_api_key":
-		secrets.VercelAiGatewayApiKey = strPtr(value)
 	case "dify_api_key":
 		secrets.DifyApiKey = strPtr(value)
 	case "oca_api_key":
 		secrets.OcaApiKey = strPtr(value)
 	case "oca_refresh_token":
 		secrets.OcaRefreshToken = strPtr(value)
+	case "hicap_api_key":
+		secrets.HicapApiKey = strPtr(value)
 	default:
 		return fmt.Errorf("unsupported secret field '%s'", key)
 	}

cli/pkg/cli/terminal/keyboard.go

@@ -0,0 +1,695 @@
+package terminal
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"sync"
+
+	"github.com/cline/cli/pkg/cli/display"
+	"github.com/cline/cli/pkg/cli/global"
+)
+
+// KeyboardProtocol manages enhanced keyboard protocol support for detecting
+// modified keys like shift+enter across all major terminals.
+type KeyboardProtocol struct {
+	enabled bool
+	mu      sync.Mutex
+}
+
+var globalProtocol = &KeyboardProtocol{}
+
+// EnableEnhancedKeyboard enables enhanced keyboard protocols to support
+// shift+enter and other modified keys across all major terminals:
+// - VS Code integrated terminal
+// - iTerm2
+// - Terminal.app
+// - Ghostty
+// - Kitty
+// - WezTerm
+// - Alacritty
+// - foot
+// - xterm
+//
+// This function is safe to call multiple times and handles cleanup automatically.
+// It enables both modifyOtherKeys (xterm protocol) and Kitty keyboard protocol
+// for maximum compatibility.
+func EnableEnhancedKeyboard() {
+	globalProtocol.mu.Lock()
+	defer globalProtocol.mu.Unlock()
+
+	if globalProtocol.enabled {
+		return // Already enabled
+	}
+
+	// Check if we're in a TTY (not piped/redirected)
+	if !isatty(os.Stdin.Fd()) {
+		return
+	}
+
+	// Enable modifyOtherKeys mode 2
+	// This tells xterm-compatible terminals (VS Code, iTerm2, Terminal.app, etc.)
+	// to send escape sequences for modified keys including shift+enter
+	// Format: CSI > 4 ; 2 m
+	// - Mode 2 enables for ALL keys including well-known ones
+	fmt.Print("\x1b[>4;2m")
+
+	// Also enable Kitty keyboard protocol for terminals that support it
+	// This is a more modern protocol supported by Kitty, Ghostty, WezTerm, foot, etc.
+	// Format: CSI = <flags> u where flags=1 means "disambiguate escape codes"
+	// This makes shift+enter distinguishable from plain enter
+	fmt.Print("\x1b[=1u")
+
+	globalProtocol.enabled = true
+}
+
+// DisableEnhancedKeyboard restores the terminal to its default keyboard mode.
+// This should be called on program exit to be a good citizen.
+func DisableEnhancedKeyboard() {
+	globalProtocol.mu.Lock()
+	defer globalProtocol.mu.Unlock()
+
+	if !globalProtocol.enabled {
+		return
+	}
+
+	// Disable modifyOtherKeys (restore to mode 0)
+	fmt.Print("\x1b[>4;0m")
+
+	// Disable Kitty keyboard protocol
+	fmt.Print("\x1b[<u")
+
+	globalProtocol.enabled = false
+}
+
+// isatty checks if a file descriptor is a terminal
+func isatty(fd uintptr) bool {
+	// Use the standard library's terminal package
+	// This works across all platforms (Unix, Windows, etc.)
+	fileInfo, err := os.Stdin.Stat()
+	if err != nil {
+		return false
+	}
+	return (fileInfo.Mode() & os.ModeCharDevice) != 0
+}
+
+// SetupKeyboard detects the current terminal and configures keybindings if needed.
+// Runs in background and doesn't block. Prints status when configs are modified.
+func SetupKeyboard() {
+	go func() {
+		renderer := display.NewRenderer(global.Config.OutputFormat)
+		setupKeyboardInternal(renderer)
+	}()
+}
+
+// SetupKeyboardSync is the synchronous version used by doctor command.
+// Blocks until complete and prints status for all terminals.
+func SetupKeyboardSync() {
+	renderer := display.NewRenderer(global.Config.OutputFormat)
+	setupKeyboardInternal(renderer)
+}
+
+func setupKeyboardInternal(renderer *display.Renderer) {
+	terminalName := DetectTerminal()
+
+	switch terminalName {
+	case "vscode":
+		// VS Code and Cursor use the same TERM_PROGRAM value
+		modified, path := SetupVSCodeKeybindings()
+		if modified {
+			fmt.Printf("%s VS Code %s\n", renderer.Dim("Configured shift+enter for"), renderer.Dim("terminal"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		} else if path != "" {
+			fmt.Printf("%s\n", renderer.Dim("✓ VS Code shift+enter already configured"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		}
+
+		modified, path = SetupCursorKeybindings()
+		if modified {
+			fmt.Printf("%s Cursor %s\n", renderer.Dim("Configured shift+enter for"), renderer.Dim("terminal"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		} else if path != "" {
+			fmt.Printf("%s\n", renderer.Dim("✓ Cursor shift+enter already configured"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		}
+
+	case "ghostty":
+		modified, path := SetupGhosttyKeybindings()
+		if modified {
+			fmt.Printf("%s Ghostty %s\n", renderer.Dim("Configured shift+enter for"), renderer.Dim("terminal"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+			fmt.Printf("%s\n", renderer.Dim("  Fully restart Ghostty (quit all windows) for changes to take effect"))
+		} else if path != "" {
+			fmt.Printf("%s\n", renderer.Dim("✓ Ghostty shift+enter already configured"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		}
+
+	case "wezterm":
+		modified, path := SetupWezTermKeybindings()
+		if modified {
+			fmt.Printf("%s WezTerm %s\n", renderer.Dim("Configured shift+enter for"), renderer.Dim("terminal"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		} else if path != "" {
+			fmt.Printf("%s\n", renderer.Dim("✓ WezTerm shift+enter already configured"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		}
+
+	case "alacritty":
+		modified, path := SetupAlacrittyKeybindings()
+		if modified {
+			fmt.Printf("%s Alacritty %s\n", renderer.Dim("Configured shift+enter for"), renderer.Dim("terminal"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		} else if path != "" {
+			fmt.Printf("%s\n", renderer.Dim("✓ Alacritty shift+enter already configured"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		}
+
+	case "kitty":
+		modified, path := SetupKittyKeybindings()
+		if modified {
+			fmt.Printf("%s Kitty %s\n", renderer.Dim("Configured shift+enter for"), renderer.Dim("terminal"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		} else if path != "" {
+			fmt.Printf("%s\n", renderer.Dim("✓ Kitty shift+enter already configured"))
+			fmt.Printf("%s %s\n", renderer.Dim("  →"), path)
+		}
+
+	case "iterm2":
+		fmt.Printf("%s\n", renderer.Dim("✓ iTerm2 shift+enter works by default (maps to alt+enter)"))
+
+	case "terminal.app":
+		fmt.Printf("%s\n", renderer.Dim("⚠ Terminal.app requires manual configuration"))
+		fmt.Printf("%s\n", renderer.Dim("  See: Terminal → Preferences → Profiles → Keyboard"))
+
+	case "unknown":
+		fmt.Printf("%s\n", renderer.Dim("ℹ Terminal not detected - use alt+enter or ctrl+j for newlines"))
+	}
+}
+
+// getVSCodeConfigPath returns the platform-specific path to VS Code's User directory
+func getVSCodeConfigPath() (string, error) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return "", err
+	}
+
+	switch runtime.GOOS {
+	case "darwin":
+		return filepath.Join(home, "Library", "Application Support", "Code", "User"), nil
+	case "windows":
+		appData := os.Getenv("APPDATA")
+		if appData == "" {
+			appData = filepath.Join(home, "AppData", "Roaming")
+		}
+		return filepath.Join(appData, "Code", "User"), nil
+	default: // linux, freebsd, etc.
+		return filepath.Join(home, ".config", "Code", "User"), nil
+	}
+}
+
+// getCursorConfigPath returns the platform-specific path to Cursor's User directory
+func getCursorConfigPath() (string, error) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return "", err
+	}
+
+	switch runtime.GOOS {
+	case "darwin":
+		return filepath.Join(home, "Library", "Application Support", "Cursor", "User"), nil
+	case "windows":
+		appData := os.Getenv("APPDATA")
+		if appData == "" {
+			appData = filepath.Join(home, "AppData", "Roaming")
+		}
+		return filepath.Join(appData, "Cursor", "User"), nil
+	default: // linux, freebsd, etc.
+		return filepath.Join(home, ".config", "Cursor", "User"), nil
+	}
+}
+
+// DetectTerminal identifies which terminal emulator is currently running
+func DetectTerminal() string {
+	// Check TERM_PROGRAM (works for most terminals)
+	termProgram := os.Getenv("TERM_PROGRAM")
+	switch termProgram {
+	case "vscode":
+		return "vscode" // Also covers Cursor (uses same value)
+	case "WezTerm":
+		return "wezterm"
+	case "ghostty":
+		return "ghostty"
+	case "iTerm.app":
+		return "iterm2"
+	case "Apple_Terminal":
+		return "terminal.app"
+	}
+
+	// Kitty doesn't set TERM_PROGRAM, check KITTY_WINDOW_ID
+	if os.Getenv("KITTY_WINDOW_ID") != "" {
+		return "kitty"
+	}
+
+	// Alacritty doesn't set TERM_PROGRAM, check ALACRITTY_SOCKET
+	if os.Getenv("ALACRITTY_SOCKET") != "" {
+		return "alacritty"
+	}
+
+	// Ghostty fallback (cross-platform - more reliable than TERM_PROGRAM)
+	if os.Getenv("GHOSTTY_RESOURCES_DIR") != "" {
+		return "ghostty"
+	}
+
+	// Alacritty fallback
+	if os.Getenv("ALACRITTY_LOG") != "" {
+		return "alacritty"
+	}
+
+	// Check TERM variable as last resort
+	term := os.Getenv("TERM")
+	if strings.Contains(term, "kitty") {
+		return "kitty"
+	}
+	if term == "alacritty" {
+		return "alacritty"
+	}
+	if term == "xterm-ghostty" {
+		return "ghostty"
+	}
+
+	return "unknown"
+}
+
+// VSCodeKeybinding represents a VS Code keyboard shortcut
+type VSCodeKeybinding struct {
+	Key     string                 `json:"key"`
+	Command string                 `json:"command"`
+	Args    map[string]interface{} `json:"args,omitempty"`
+	When    string                 `json:"when,omitempty"`
+}
+
+// SetupVSCodeKeybindings adds shift+enter support to VS Code's integrated terminal
+// by modifying the user's keybindings.json file.
+// Returns (wasModified, configPath) to allow caller to log the change.
+func SetupVSCodeKeybindings() (bool, string) {
+	// Get platform-specific VS Code config path
+	configDir, err := getVSCodeConfigPath()
+	if err != nil {
+		return false, ""
+	}
+
+	keybindingsPath := filepath.Join(configDir, "keybindings.json")
+
+	// Check if VS Code is installed (keybindings file or parent dir exists)
+	if _, err := os.Stat(filepath.Dir(keybindingsPath)); os.IsNotExist(err) {
+		// VS Code not installed, skip silently
+		return false, ""
+	}
+
+	// Read existing keybindings
+	var keybindings []VSCodeKeybinding
+
+	data, err := os.ReadFile(keybindingsPath)
+	if err != nil {
+		if !os.IsNotExist(err) {
+			return false, ""
+		}
+		// File doesn't exist, start with empty array
+		keybindings = []VSCodeKeybinding{}
+	} else {
+		// Parse existing keybindings
+		if err := json.Unmarshal(data, &keybindings); err != nil {
+			// If parse fails, don't modify the file
+			return false, ""
+		}
+	}
+
+	// Check if shift+enter binding already exists
+	for _, kb := range keybindings {
+		if kb.Key == "shift+enter" && kb.Command == "workbench.action.terminal.sendSequence" {
+			// Already configured
+			return false, keybindingsPath
+		}
+	}
+
+	// Add shift+enter keybinding
+	newBinding := VSCodeKeybinding{
+		Key:     "shift+enter",
+		Command: "workbench.action.terminal.sendSequence",
+		Args: map[string]interface{}{
+			"text": "\u001b\n", // ESC + newline (alt+enter sequence)
+		},
+		When: "terminalFocus",
+	}
+
+	keybindings = append(keybindings, newBinding)
+
+	// Create backup
+	if data != nil {
+		backupPath := keybindingsPath + ".backup"
+		_ = os.WriteFile(backupPath, data, 0644)
+	}
+
+	// Write updated keybindings
+	updatedData, err := json.MarshalIndent(keybindings, "", "  ")
+	if err != nil {
+		return false, ""
+	}
+
+	// Ensure parent directory exists
+	if err := os.MkdirAll(filepath.Dir(keybindingsPath), 0755); err != nil {
+		return false, ""
+	}
+
+	if err := os.WriteFile(keybindingsPath, updatedData, 0644); err != nil {
+		return false, ""
+	}
+
+	return true, keybindingsPath
+}
+
+// SetupCursorKeybindings adds shift+enter support to Cursor's integrated terminal
+// by modifying the user's keybindings.json file.
+// Cursor is a fork of VS Code, so it uses the same keybinding format.
+// Returns (wasModified, configPath) to allow caller to log the change.
+func SetupCursorKeybindings() (bool, string) {
+	// Get platform-specific Cursor config path
+	configDir, err := getCursorConfigPath()
+	if err != nil {
+		return false, ""
+	}
+
+	keybindingsPath := filepath.Join(configDir, "keybindings.json")
+
+	// Check if Cursor is installed (keybindings file or parent dir exists)
+	if _, err := os.Stat(filepath.Dir(keybindingsPath)); os.IsNotExist(err) {
+		// Cursor not installed, skip silently
+		return false, ""
+	}
+
+	// Read existing keybindings
+	var keybindings []VSCodeKeybinding
+
+	data, err := os.ReadFile(keybindingsPath)
+	if err != nil {
+		if !os.IsNotExist(err) {
+			return false, ""
+		}
+		// File doesn't exist, start with empty array
+		keybindings = []VSCodeKeybinding{}
+	} else {
+		// Parse existing keybindings
+		if err := json.Unmarshal(data, &keybindings); err != nil {
+			// If parse fails, don't modify the file
+			return false, ""
+		}
+	}
+
+	// Check if shift+enter binding already exists
+	for _, kb := range keybindings {
+		if kb.Key == "shift+enter" && kb.Command == "workbench.action.terminal.sendSequence" {
+			// Already configured
+			return false, keybindingsPath
+		}
+	}
+
+	// Add shift+enter keybinding
+	newBinding := VSCodeKeybinding{
+		Key:     "shift+enter",
+		Command: "workbench.action.terminal.sendSequence",
+		Args: map[string]interface{}{
+			"text": "\u001b\n", // ESC + newline (alt+enter sequence)
+		},
+		When: "terminalFocus",
+	}
+
+	keybindings = append(keybindings, newBinding)
+
+	// Create backup
+	if data != nil {
+		backupPath := keybindingsPath + ".backup"
+		_ = os.WriteFile(backupPath, data, 0644)
+	}
+
+	// Write updated keybindings
+	updatedData, err := json.MarshalIndent(keybindings, "", "  ")
+	if err != nil {
+		return false, ""
+	}
+
+	// Ensure parent directory exists
+	if err := os.MkdirAll(filepath.Dir(keybindingsPath), 0755); err != nil {
+		return false, ""
+	}
+
+	if err := os.WriteFile(keybindingsPath, updatedData, 0644); err != nil {
+		return false, ""
+	}
+
+	return true, keybindingsPath
+}
+
+// SetupGhosttyKeybindings adds shift+enter support to Ghostty terminal
+// by appending to the user's config file.
+// Returns (wasModified, configPath) to allow caller to log the change.
+func SetupGhosttyKeybindings() (bool, string) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return false, ""
+	}
+
+	// Ghostty config location: ~/.config/ghostty/config
+	configPath := filepath.Join(home, ".config", "ghostty", "config")
+
+	// Check if config directory exists
+	configDir := filepath.Dir(configPath)
+	if _, err := os.Stat(configDir); os.IsNotExist(err) {
+		// Ghostty not installed, skip silently
+		return false, ""
+	}
+
+	// Read existing config if it exists
+	var existingContent []byte
+	if data, err := os.ReadFile(configPath); err == nil {
+		existingContent = data
+		// Check if shift+enter already configured
+		if strings.Contains(string(data), "keybind = shift+enter") {
+			return false, configPath
+		}
+	}
+
+	// Keybinding to add - send newline character (0x0a)
+	// Ghostty requires \x0a hex escape syntax, verified working
+	keybinding := "keybind = shift+enter=text:\\x0a\n"
+
+	// Append to config
+	newContent := append(existingContent, []byte(keybinding)...)
+
+	// Ensure directory exists
+	if err := os.MkdirAll(configDir, 0755); err != nil {
+		return false, ""
+	}
+
+	// Create backup if file exists
+	if existingContent != nil {
+		backupPath := configPath + ".backup"
+		_ = os.WriteFile(backupPath, existingContent, 0644)
+	}
+
+	// Write updated config
+	if err := os.WriteFile(configPath, newContent, 0644); err != nil {
+		return false, ""
+	}
+
+	return true, configPath
+}
+
+// SetupWezTermKeybindings adds shift+enter support to WezTerm
+// by appending to the user's .wezterm.lua file.
+// Returns (wasModified, configPath)
+func SetupWezTermKeybindings() (bool, string) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return false, ""
+	}
+
+	configPath := filepath.Join(home, ".wezterm.lua")
+
+	// Check if WezTerm config exists
+	if _, err := os.Stat(configPath); os.IsNotExist(err) {
+		// WezTerm not configured, skip silently
+		return false, ""
+	}
+
+	// Read existing config
+	data, err := os.ReadFile(configPath)
+	if err != nil {
+		return false, ""
+	}
+
+	// Check if shift+enter already configured
+	if strings.Contains(string(data), "key = 'Enter'") && strings.Contains(string(data), "mods = 'SHIFT'") {
+		return false, configPath
+	}
+
+	// Create backup
+	backupPath := configPath + ".backup"
+	_ = os.WriteFile(backupPath, data, 0644)
+
+	// Keybinding to add (insert before final return statement)
+	keybinding := `
+-- Shift+Enter for newlines (added by Cline CLI)
+config.keys = config.keys or {}
+table.insert(config.keys, {
+  key = 'Enter',
+  mods = 'SHIFT',
+  action = wezterm.action.SendString '\x1b\n',
+})
+`
+
+	content := string(data)
+	// Try to insert before the final return statement
+	if strings.Contains(content, "return config") {
+		content = strings.Replace(content, "return config", keybinding+"\nreturn config", 1)
+	} else {
+		// No return statement, append at end
+		content += keybinding
+	}
+
+	// Write updated config
+	if err := os.WriteFile(configPath, []byte(content), 0644); err != nil {
+		return false, ""
+	}
+
+	return true, configPath
+}
+
+// SetupAlacrittyKeybindings adds shift+enter support to Alacritty
+// by appending to the user's alacritty.yml file.
+// Returns (wasModified, configPath)
+func SetupAlacrittyKeybindings() (bool, string) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return false, ""
+	}
+
+	// Try both possible locations
+	configPaths := []string{
+		filepath.Join(home, ".config", "alacritty", "alacritty.yml"),
+		filepath.Join(home, ".config", "alacritty", "alacritty.toml"),
+		filepath.Join(home, ".alacritty.yml"),
+	}
+
+	var configPath string
+	for _, path := range configPaths {
+		if _, err := os.Stat(path); err == nil {
+			configPath = path
+			break
+		}
+	}
+
+	if configPath == "" {
+		// Alacritty not configured, skip silently
+		return false, ""
+	}
+
+	// Read existing config
+	data, err := os.ReadFile(configPath)
+	if err != nil {
+		return false, ""
+	}
+
+	// Check if shift+enter already configured
+	if strings.Contains(string(data), "key: Return") && strings.Contains(string(data), "mods: Shift") {
+		return false, configPath
+	}
+
+	// Create backup
+	backupPath := configPath + ".backup"
+	_ = os.WriteFile(backupPath, data, 0644)
+
+	// Keybinding to add
+	var keybinding string
+	if strings.HasSuffix(configPath, ".yml") || strings.HasSuffix(configPath, ".yaml") {
+		keybinding = `
+# Shift+Enter for newlines (added by Cline CLI)
+key_bindings:
+  - { key: Return, mods: Shift, chars: "\x1b\n" }
+`
+	} else {
+		// TOML format
+		keybinding = `
+# Shift+Enter for newlines (added by Cline CLI)
+[[keyboard.bindings]]
+key = "Return"
+mods = "Shift"
+chars = "\x1b\n"
+`
+	}
+
+	// Append to config
+	newContent := append(data, []byte(keybinding)...)
+
+	// Write updated config
+	if err := os.WriteFile(configPath, newContent, 0644); err != nil {
+		return false, ""
+	}
+
+	return true, configPath
+}
+
+// SetupKittyKeybindings adds shift+enter support to Kitty terminal
+// by appending to the user's kitty.conf file.
+// Returns (wasModified, configPath)
+func SetupKittyKeybindings() (bool, string) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return false, ""
+	}
+
+	configPath := filepath.Join(home, ".config", "kitty", "kitty.conf")
+
+	// Check if config directory exists
+	configDir := filepath.Dir(configPath)
+	if _, err := os.Stat(configDir); os.IsNotExist(err) {
+		// Kitty not installed, skip silently
+		return false, ""
+	}
+
+	// Read existing config if it exists
+	var existingContent []byte
+	if data, err := os.ReadFile(configPath); err == nil {
+		existingContent = data
+		// Check if shift+enter already configured
+		if strings.Contains(string(data), "map shift+enter") {
+			return false, configPath
+		}
+	}
+
+	// Keybinding to add
+	keybinding := "# Shift+Enter for newlines (added by Cline CLI)\nmap shift+enter send_text all \\x1b\\n\n"
+
+	// Append to config
+	newContent := append(existingContent, []byte(keybinding)...)
+
+	// Ensure directory exists
+	if err := os.MkdirAll(configDir, 0755); err != nil {
+		return false, ""
+	}
+
+	// Create backup if file exists
+	if existingContent != nil {
+		backupPath := configPath + ".backup"
+		_ = os.WriteFile(backupPath, existingContent, 0644)
+	}
+
+	// Write updated config
+	if err := os.WriteFile(configPath, newContent, 0644); err != nil {
+		return false, ""
+	}
+
+	return true, configPath
+}

cli/pkg/cli/types/messages.go

@@ -37,17 +37,16 @@ const (
 type AskType string
 
 const (
-	AskTypeFollowup               AskType = "followup"
-	AskTypePlanModeRespond        AskType = "plan_mode_respond"
-	AskTypeCommand                AskType = "command"
-	AskTypeCommandOutput          AskType = "command_output"
-	AskTypeCompletionResult       AskType = "completion_result"
-	AskTypeTool                   AskType = "tool"
-	AskTypeAPIReqFailed           AskType = "api_req_failed"
-	AskTypeResumeTask             AskType = "resume_task"
-	AskTypeResumeCompletedTask    AskType = "resume_completed_task"
-	AskTypeMistakeLimitReached    AskType = "mistake_limit_reached"
-	AskTypeAutoApprovalMaxReached AskType = "auto_approval_max_req_reached"
+	AskTypeFollowup            AskType = "followup"
+	AskTypePlanModeRespond     AskType = "plan_mode_respond"
+	AskTypeCommand             AskType = "command"
+	AskTypeCommandOutput       AskType = "command_output"
+	AskTypeCompletionResult    AskType = "completion_result"
+	AskTypeTool                AskType = "tool"
+	AskTypeAPIReqFailed        AskType = "api_req_failed"
+	AskTypeResumeTask          AskType = "resume_task"
+	AskTypeResumeCompletedTask AskType = "resume_completed_task"
+	AskTypeMistakeLimitReached AskType = "mistake_limit_reached"
 	AskTypeBrowserActionLaunch    AskType = "browser_action_launch"
 	AskTypeUseMcpServer           AskType = "use_mcp_server"
 	AskTypeNewTask                AskType = "new_task"
@@ -108,6 +107,7 @@ const (
 	ToolTypeEditedExistingFile      ToolType = "editedExistingFile"
 	ToolTypeNewFileCreated          ToolType = "newFileCreated"
 	ToolTypeReadFile                ToolType = "readFile"
+	ToolTypeFileDeleted             ToolType = "fileDeleted"
 	ToolTypeListFilesTopLevel       ToolType = "listFilesTopLevel"
 	ToolTypeListFilesRecursive      ToolType = "listFilesRecursive"
 	ToolTypeListCodeDefinitionNames ToolType = "listCodeDefinitionNames"
@@ -247,8 +247,6 @@ func convertProtoAskType(askType cline.ClineAsk) string {
 		return string(AskTypeResumeCompletedTask)
 	case cline.ClineAsk_MISTAKE_LIMIT_REACHED:
 		return string(AskTypeMistakeLimitReached)
-	case cline.ClineAsk_AUTO_APPROVAL_MAX_REQ_REACHED:
-		return string(AskTypeAutoApprovalMaxReached)
 	case cline.ClineAsk_BROWSER_ACTION_LAUNCH:
 		return string(AskTypeBrowserActionLaunch)
 	case cline.ClineAsk_USE_MCP_SERVER:

cli/pkg/cli/updater/updater.go

@@ -68,7 +68,7 @@ func CheckAndUpdate(isVerbose bool) {
 
 	// Run in background so we don't block CLI startup
 	go func() {
-		if err := checkAndUpdateSync(); err != nil {
+		if err := checkAndUpdateInternal(false); err != nil {
 			if verbose {
 				output.Printf("[updater] Update check failed: %v\n", err)
 			}
@@ -76,15 +76,49 @@ func CheckAndUpdate(isVerbose bool) {
 	}()
 }
 
-func checkAndUpdateSync() error {
+// CheckAndUpdateSync performs a synchronous update check (blocks until complete).
+// If bypassCache is true, ignores the 24-hour cache and always checks npm registry.
+// This is used by the doctor command.
+func CheckAndUpdateSync(isVerbose bool, bypassCache bool) {
+	verbose = isVerbose
+
+	// Skip in CI environments
+	if os.Getenv("CI") != "" {
+		if verbose {
+			output.Printf("[updater] Skipping update check (CI environment)\n")
+		}
+		return
+	}
+
+	// Skip if user disabled auto-updates
+	if os.Getenv("NO_AUTO_UPDATE") != "" {
+		if verbose {
+			output.Printf("[updater] Skipping update check (NO_AUTO_UPDATE set)\n")
+		}
+		return
+	}
+
+	if verbose {
+		output.Printf("[updater] Starting update check...\n")
+	}
+
+	// Run synchronously
+	if err := checkAndUpdateInternal(bypassCache); err != nil {
+		if verbose {
+			output.Printf("[updater] Update check failed: %v\n", err)
+		}
+	}
+}
+
+func checkAndUpdateInternal(bypassCache bool) error {
 	if verbose {
 		output.Printf("[updater] Loading update cache...\n")
 	}
 
 	// Load cache
 	cache, err := loadCache()
-	if err == nil && time.Since(cache.LastCheck) < checkInterval {
-		// Checked recently, skip
+	if !bypassCache && err == nil && time.Since(cache.LastCheck) < checkInterval {
+		// Checked recently, skip (unless cache is bypassed)
 		if verbose {
 			output.Printf("[updater] Cache is fresh (last checked %v ago), skipping\n", time.Since(cache.LastCheck))
 		}
@@ -341,7 +375,7 @@ func showFailureMessage(channel string) {
 
 func getCacheFilePath() string {
 	configDir := filepath.Join(os.Getenv("HOME"), ".cline", "data")
-	return filepath.Join(configDir, ".update-cache")
+	return filepath.Join(configDir, "cli-update-cache")
 }
 
 func loadCache() (cacheData, error) {
@@ -372,4 +406,4 @@ func saveCache(cache cacheData) error {
 	}
 
 	return os.WriteFile(cacheFile, data, 0644)
-}
+}

cli/pkg/common/utils.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"fmt"
 	"net"
+	"os/exec"
 	"strconv"
+	"strings"
 	"time"
 
 	"google.golang.org/grpc"
@@ -124,6 +126,16 @@ func NormalizeAddressForGRPC(address string) (string, error) {
 	return address, nil
 }
 
+// GetNodeVersion returns the current Node.js version, or "unknown" if unable to detect
+func GetNodeVersion() string {
+	cmd := exec.Command("node", "--version")
+	output, err := cmd.Output()
+	if err != nil {
+		return "unknown"
+	}
+	return strings.TrimSpace(string(output))
+}
+
 // RetryOperation performs an operation with retry logic
 func RetryOperation(maxRetries int, timeoutPerAttempt time.Duration, operation func() error) error {
 	var lastErr error
@@ -155,5 +167,19 @@ func RetryOperation(maxRetries int, timeoutPerAttempt time.Duration, operation f
 		}
 	}
 
-	return fmt.Errorf("operation failed after %d attempts: %w", maxRetries, lastErr)
+	return fmt.Errorf(`operation failed to after %d attempts: %w
+
+This is usually caused by an incompatible Node.js version
+
+REQUIREMENTS:
+• Node.js version 20+ is required
+• Current Node.js version: %s
+
+DEBUGGING STEPS:
+1. View recent logs: cline log list
+2. Logs are available in: ~/.cline/logs/
+3. The most recent cline-core log file is usually valuable
+
+For additional help, visit: https://github.com/cline/cline/issues
+`, maxRetries, lastErr, GetNodeVersion())
 }

cli/pkg/generated/providers.go

@@ -144,6 +144,8 @@ const (
 	OPENAI_NATIVE = "openai-native"
 	XAI = "xai"
 	CEREBRAS = "cerebras"
+	OCA = "oca"
+	NOUSRESEARCH = "nousResearch"
 )
 
 // AllProviders returns a slice of enabled provider IDs for the CLI build.
@@ -159,6 +161,8 @@ var AllProviders = []string{
 	"openai-native",
 	"xai",
 	"cerebras",
+	"oca",
+	"nousResearch",
 }
 
 // ConfigField represents a configuration field requirement
@@ -316,6 +320,15 @@ var rawConfigFields = `	[
 	    "fieldType": "password",
 	    "placeholder": "Enter your API key"
 	  },
+	  {
+	    "name": "nousResearchApiKey",
+	    "type": "string",
+	    "comment": "",
+	    "category": "nousResearch",
+	    "required": true,
+	    "fieldType": "password",
+	    "placeholder": "Enter your API key"
+	  },
 	  {
 	    "name": "ulid",
 	    "type": "string",
@@ -433,6 +446,15 @@ var rawConfigFields = `	[
 	    "fieldType": "url",
 	    "placeholder": "https://api.example.com"
 	  },
+	  {
+	    "name": "minimaxApiLine",
+	    "type": "string",
+	    "comment": "",
+	    "category": "general",
+	    "required": false,
+	    "fieldType": "string",
+	    "placeholder": ""
+	  },
 	  {
 	    "name": "ocaMode",
 	    "type": "string",
@@ -441,7 +463,16 @@ var rawConfigFields = `	[
 	    "required": false,
 	    "fieldType": "string",
 	    "placeholder": ""
-	  }
+	  },
+	  {
+	    "name": "hicapApiKey",
+	    "type": "string",
+	    "comment": "",
+	    "category": "general",
+	    "required": true,
+	    "fieldType": "password",
+	    "placeholder": "Enter your API key"
+	  },
 	]`
 
 // Raw model definitions data (parsed from TypeScript)
@@ -467,6 +498,16 @@ var rawModelDefinitions = `	{
 	      "supportsImages": true,
 	      "supportsPromptCache": true
 	    },
+	    "claude-haiku-4-5-20251001": {
+	      "maxTokens": 8192,
+	      "contextWindow": 200000,
+	      "inputPrice": 1,
+	      "outputPrice": 5,
+	      "cacheWritesPrice": 1,
+	      "cacheReadsPrice": 0,
+	      "supportsImages": true,
+	      "supportsPromptCache": true
+	    },
 	    "claude-sonnet-4-20250514": {
 	      "maxTokens": 8192,
 	      "contextWindow": 200000,
@@ -579,6 +620,16 @@ var rawModelDefinitions = `	{
 	      "supportsImages": true,
 	      "supportsPromptCache": true
 	    },
+	    "anthropic.claude-haiku-4-5-20251001-v1:0": {
+	      "maxTokens": 8192,
+	      "contextWindow": 200000,
+	      "inputPrice": 1,
+	      "outputPrice": 5,
+	      "cacheWritesPrice": 1,
+	      "cacheReadsPrice": 0,
+	      "supportsImages": true,
+	      "supportsPromptCache": true
+	    },
 	    "anthropic.claude-sonnet-4-20250514-v1:0": {
 	      "maxTokens": 8192,
 	      "contextWindow": 200000,
@@ -744,6 +795,24 @@ var rawModelDefinitions = `	{
 	      "supportsImages": false,
 	      "supportsPromptCache": false,
 	      "description": "A compact 20B open-weight Mixture-of-Experts language model designed for strong reasoning and tool use, ideal for edge devices and local inference."
+	    },
+	    "qwen.qwen3-coder-30b-a3b-v1:0": {
+	      "maxTokens": 8192,
+	      "contextWindow": 262144,
+	      "inputPrice": 0,
+	      "outputPrice": 0,
+	      "supportsImages": false,
+	      "supportsPromptCache": false,
+	      "description": "Qwen3 Coder 30B MoE model with 3.3B activated parameters, optimized for code generation and analysis with 256K context window."
+	    },
+	    "qwen.qwen3-coder-480b-a35b-v1:0": {
+	      "maxTokens": 8192,
+	      "contextWindow": 262144,
+	      "inputPrice": 0,
+	      "outputPrice": 1,
+	      "supportsImages": false,
+	      "supportsPromptCache": false,
+	      "description": "Qwen3 Coder 480B flagship MoE model with 35B activated parameters, designed for complex coding tasks with advanced reasoning capabilities and 256K context window."
 	    }
 	  },
 	  "gemini": {
@@ -1232,6 +1301,26 @@ var rawModelDefinitions = `	{
 	      "supportsPromptCache": false,
 	      "description": "SOTA performance with ~1500 tokens/s"
 	    }
+	  },
+	  "nousResearch": {
+	    "Hermes-4-405B": {
+	      "maxTokens": 8192,
+	      "contextWindow": 128000,
+	      "inputPrice": 0,
+	      "outputPrice": 0,
+	      "supportsImages": false,
+	      "supportsPromptCache": false,
+	      "description": "This is the largest model in the Hermes 4 family, and it is the fullest expression of our design, focused on advanced reasoning and creative depth rather than optimizing inference speed or cost."
+	    },
+	    "Hermes-4-70B": {
+	      "maxTokens": 8192,
+	      "contextWindow": 128000,
+	      "inputPrice": 0,
+	      "outputPrice": 0,
+	      "supportsImages": false,
+	      "supportsPromptCache": false,
+	      "description": "This incarnation of Hermes 4 balances scale and size. It handles complex reasoning tasks, while staying fast and cost effective. A versatile choice for many use cases."
+	    }
 	  }
 	}`
 
@@ -1389,6 +1478,30 @@ func GetProviderDefinitions() (map[string]ProviderDefinition, error) {
 		HasDynamicModels: false,
 		SetupInstructions: `Get your API key from https://cloud.cerebras.ai/`,
 	}
+
+	// Oca
+	definitions["oca"] = ProviderDefinition{
+		ID:              "oca",
+		Name:            "Oca",
+		RequiredFields:  getFieldsByProvider("oca", configFields, true),
+		OptionalFields:  getFieldsByProvider("oca", configFields, false),
+		Models:          modelDefinitions["oca"],
+		DefaultModelID:  "",
+		HasDynamicModels: false,
+		SetupInstructions: `Configure Oca API credentials`,
+	}
+
+	// NousResearch
+	definitions["nousResearch"] = ProviderDefinition{
+		ID:              "nousResearch",
+		Name:            "NousResearch",
+		RequiredFields:  getFieldsByProvider("nousResearch", configFields, true),
+		OptionalFields:  getFieldsByProvider("nousResearch", configFields, false),
+		Models:          modelDefinitions["nousResearch"],
+		DefaultModelID:  "Hermes-4-405B",
+		HasDynamicModels: false,
+		SetupInstructions: `Configure NousResearch API credentials`,
+	}
 	
 	return definitions, nil
 }
@@ -1415,6 +1528,8 @@ func GetProviderDisplayName(providerID string) string {
 		"openai-native": "OpenAI",
 		"xai": "X AI (Grok)",
 		"cerebras": "Cerebras",
+		"oca": "Oca",
+		"nousResearch": "NousResearch",
 	}
 	
 	if name, exists := displayNames[providerID]; exists {

docker/.dockerignore

@@ -0,0 +1,48 @@
+# Git
+.git
+.gitignore
+.gitattributes
+
+# Node modules
+node_modules
+npm-debug.log
+
+# Build artifacts
+dist
+dist-standalone
+build
+*.log
+
+# Generated code
+src/generated
+
+# CLI build artifacts
+cli/bin
+cli/dist
+
+# Webview build artifacts
+webview-ui/dist
+webview-ui/build
+
+# IDE
+.vscode
+.idea
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Documentation
+*.md
+!README.md
+
+# Tests
+tests
+*.test.js
+*.spec.js
+
+# CI/CD
+.github
+.gitlab-ci.yml

docker/Dockerfile

@@ -0,0 +1,49 @@
+FROM node:22-slim
+
+# TARGETARCH enables multi-architecture support without emulation warnings:
+# - Docker automatically sets TARGETARCH to the build platform's architecture
+# - On arm64 machines (Apple Silicon): TARGETARCH=arm64, uses linux-arm64 binaries
+# - On amd64 machines (Intel/AMD): TARGETARCH=amd64, uses linux-x64 binaries
+# The corresponding platform-specific binaries and native modules (better-sqlite3)
+# are pre-built by scripts/package-standalone.mjs during the build process.
+ARG TARGETARCH
+
+# Install only runtime dependencies
+RUN apt-get update && apt-get install -y \
+    git curl ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /opt/cline
+
+# Copy the entire pre-built distribution
+COPY dist-standalone/ ./
+
+# Create symlink for Linux native modules
+# Map Docker's TARGETARCH (arm64/amd64) to Node's platform naming (x64 for amd64)
+RUN if [ "$TARGETARCH" = "amd64" ]; then \
+        ln -sf /opt/cline/binaries/linux-x64/node_modules/better-sqlite3 /opt/cline/node_modules/better-sqlite3; \
+    else \
+        ln -sf /opt/cline/binaries/linux-$TARGETARCH/node_modules/better-sqlite3 /opt/cline/node_modules/better-sqlite3; \
+    fi
+
+# Set up CLI binaries
+# The Linux binaries are already in /opt/cline/bin/ from dist-standalone
+# Just need to create symlinks to the platform-specific ones
+RUN cd /opt/cline/bin && \
+    ln -sf cline-linux-$TARGETARCH cline && \
+    ln -sf cline-host-linux-$TARGETARCH cline-host && \
+    chmod +x cline-linux-$TARGETARCH cline-host-linux-$TARGETARCH cline cline-host
+
+# Add binaries to PATH
+ENV PATH="/opt/cline/bin:${PATH}"
+ENV NODE_ENV=production
+ENV CLINE_HOME=/root/.cline
+
+RUN mkdir -p $CLINE_HOME
+
+WORKDIR /workspace
+
+EXPOSE 8000
+
+ENTRYPOINT ["/opt/cline/bin/cline"]
+CMD ["--help"]

docs/cline-cli/installation.mdx

@@ -3,19 +3,21 @@ title: "Installation"
 description: "Install Cline CLI and authenticate with your account"
 ---
 
-<Tabs>
-  <Tab title="NPM">
-    ```bash
-    npm install -g cline
-    ```
-  </Tab>
+## Prerequisites
 
-  <Tab title="CURL">
-    ```bash
-    curl -fsSL https://raw.githubusercontent.com/cline/cline/main/scripts/install.sh | bash
-    ```
-  </Tab>
-</Tabs>
+Cline CLI requires Node.js version 20 or higher. We recommend using Node.js 22 for the best experience.
+
+To check your Node.js version:
+
+```bash
+node --version
+```
+
+## Installation
+
+```bash
+npm install -g cline
+```
 
 After installation, authenticate with your Cline account:
 

docs/cline-cli/overview.mdx

@@ -19,6 +19,22 @@ The CLI tracks instances across your system and outputs in formats designed for
 Ready to get started? Check out the [installation guide](/cline-cli/installation) to install Cline CLI and run your first task.
 </Tip>
 
+## Supported Model Providers
+
+Cline CLI supports multiple AI model providers, giving you flexibility in choosing the best model for your needs:
+
+- **Anthropic**
+- **OpenAI**
+- **OpenAI Compatible**
+- **OpenRouter**
+- **X AI (Grok)**
+- **AWS Bedrock**
+- **Google Gemini**
+- **Ollama**
+- **Cerebras**
+
+During installation, you'll authenticate and configure your preferred provider using the `cline auth` command.
+
 ## What you can build with this
 
 **Automated code maintenance**

docs/cline-cli/samples/github-integration.mdx

@@ -0,0 +1,324 @@
+---
+title: "GitHub Actions Integration"
+description: "Automatically respond to GitHub issues by mentioning @cline in comments using Cline CLI in GitHub Actions."
+---
+
+# GitHub Integration Sample
+
+Automate GitHub issue analysis with AI. Mention `@cline` in any issue comment to trigger an autonomous investigation that reads files, analyzes code, and provides actionable insights - all running automatically in GitHub Actions.
+
+
+<Note>
+**New to Cline CLI?** This sample assumes you understand Cline CLI basics and have completed the [Installation Guide](https://docs.cline.bot/cline-cli/installation). If you're new to Cline CLI, we recommend starting with the [GitHub RCA sample](../github-issue-rca) first, as it's simpler and will help you understand the fundamentals before setting up GitHub Actions.
+</Note>
+
+## The Workflow
+
+Trigger Cline by mentioning `@cline` in any issue comment:
+
+<Frame>
+  <img src="https://storage.googleapis.com/cline_public_images/ss0a-comment.png" alt="Issue comment with @cline mention" width="600" />
+</Frame>
+
+Cline's automated analysis appears as a new comment, with insights drawn from your actual codebase:
+
+<Frame>
+  <img src="https://storage.googleapis.com/cline_public_images/ss0b-final.png" alt="Automated analysis response from Cline" width="600" />
+</Frame>
+
+The entire investigation runs autonomously in GitHub Actions - from file exploration to posting results.
+
+Let's configure your repository.
+
+## Prerequisites
+
+Before you begin, you'll need:
+
+- **Cline CLI knowledge** - Completed the [Installation Guide](https://docs.cline.bot/cline-cli/installation) and understand basic usage
+- **GitHub repository** - With admin access to configure Actions and secrets
+- **GitHub Actions familiarity** - Basic understanding of workflows and CI/CD
+- **API provider account** - OpenRouter, Anthropic, or similar with API key
+
+## Setup
+
+### 1. Copy the Workflow File
+
+
+
+Copy the workflow file from this sample to your repository. The workflow file must be placed in the `.github/workflows/` directory in your repository root for GitHub Actions to detect and run it. In this case, we'll name it `cline-responder.yml`.
+
+```bash
+# In your repository root
+mkdir -p .github/workflows
+curl -o .github/workflows/cline-responder.yml https://raw.githubusercontent.com/cline/cline/main/src/samples/cli/github-integration/cline-responder.yml
+```
+
+Alternatively, you can copy the full workflow file directly into `.github/workflows/cline-responder.yml`:
+
+<Accordion title="Click to view the complete cline-responder.yml workflow">
+```yaml
+name: Cline Issue Assistant
+
+on:
+  issue_comment:
+    types: [created, edited]
+
+permissions:
+  issues: write
+
+jobs:
+  respond:
+    runs-on: ubuntu-latest
+    environment: cline-actions
+    steps:
+      - name: Check for @cline mention
+        id: detect
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const body = context.payload.comment?.body || "";
+            const isPR = !!context.payload.issue?.pull_request;
+            const hit = body.toLowerCase().includes("@cline");
+            core.setOutput("hit", (!isPR && hit) ? "true" : "false");
+            core.setOutput("issue_number", String(context.payload.issue?.number || ""));
+            core.setOutput("issue_url", context.payload.issue?.html_url || "");
+            core.setOutput("comment_body", body);
+
+      - name: Checkout repository
+        if: steps.detect.outputs.hit == 'true'
+        uses: actions/checkout@v4
+
+      # Node v20 is needed for Cline CLI on GitHub Actions Linux
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: Setup Cline CLI
+        if: steps.detect.outputs.hit == 'true'
+        run: |
+          # Install the Cline CLI
+          sudo npm install -g cline
+
+      - name: Create Cline Instance
+        if: steps.detect.outputs.hit == 'true'
+        env:
+          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
+          CLINE_DIR: ${{ runner.temp }}/cline
+        run: |
+          # Create instance and capture output
+          INSTANCE_OUTPUT=$(cline instance new 2>&1)
+          
+          # Parse address from output (format: "  Address: 127.0.0.1:36733")
+          CLINE_ADDRESS=$(echo "$INSTANCE_OUTPUT" | grep "Address:" | grep -oE '([0-9]{1,3}\.){3}[0-9]{1,3}:[0-9]+')
+          echo "CLINE_ADDRESS=$CLINE_ADDRESS" >> $GITHUB_ENV
+          
+          # Configure API key
+          cline config set open-router-api-key=$OPENROUTER_API_KEY --address $CLINE_ADDRESS -v
+
+      - name: Download analyze script
+        if: steps.detect.outputs.hit == 'true'
+        run: |
+          export GITORG="YOUR-GITHUB-ORG"
+          export GITREPO="YOUR-GITHUB-REPO"
+
+          curl -L https://raw.githubusercontent.com/${GITORG}/${GITREPO}/refs/heads/main/git-scripts/analyze-issue.sh -o analyze-issue.sh
+          chmod +x analyze-issue.sh
+
+      - name: Run analysis
+        if: steps.detect.outputs.hit == 'true'
+        id: analyze
+        env:
+          ISSUE_URL: ${{ steps.detect.outputs.issue_url }}
+          COMMENT: ${{ steps.detect.outputs.comment_body }}
+          CLINE_ADDRESS: ${{ env.CLINE_ADDRESS }}
+        run: |
+          set -euo pipefail
+          
+          RESULT=$(./analyze-issue.sh "${ISSUE_URL}" "Analyze this issue. The user asked: ${COMMENT}" "$CLINE_ADDRESS")
+          
+          {
+            echo 'result<<EOF'
+            printf "%s\n" "$RESULT"
+            echo 'EOF'
+          } >> "$GITHUB_OUTPUT"
+
+      - name: Post response
+        if: steps.detect.outputs.hit == 'true'
+        uses: actions/github-script@v7
+        env:
+          ISSUE_NUMBER: ${{ steps.detect.outputs.issue_number }}
+          RESULT: ${{ steps.analyze.outputs.result }}
+        with:
+          script: |
+            await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: Number(process.env.ISSUE_NUMBER),
+              body: process.env.RESULT || "(no output)"
+            });
+```
+</Accordion>
+
+<Warning>
+**You MUST edit the workflow file before committing!**
+
+Open `.github/workflows/cline-responder.yml` and update the "Download analyze script" step within the workflow to specify your GitHub organization and repository where the analysis script is stored:
+
+```yaml
+export GITORG="YOUR-GITHUB-ORG"      # Change this!
+export GITREPO="YOUR-GITHUB-REPO"    # Change this!
+```
+
+**Example:** If your repository is `github.com/acme/myproject`, set:
+```yaml
+export GITORG="acme"
+export GITREPO="myproject"
+```
+
+This tells the workflow where to download the analysis script from your repository after you commit it in step 3.
+</Warning>
+
+The workflow will look for new or updated issues, check for `@cline` mentions, and then
+start up an instance of the Cline CLI to dig into the issue, providing feedback
+as a reply to the issue.
+
+### 2. Configure API Keys
+
+Add your AI provider API keys as repository secrets:
+
+1. Go to your GitHub repository
+2. Navigate to **Settings** → **Environment** and Add a new environment.
+
+   <Frame>
+     <img src="https://storage.googleapis.com/cline_public_images/ss01-environment.png" alt="Navigate to Actions secrets" width="600" />
+   </Frame>
+
+   Make sure to name it "cline-actions" so that it matches the `environment`
+   value at the top of the `cline-responder.yml` file.
+
+3. Click **New repository secret**
+4. Add a secret for the `OPENROUTER_API_KEY` with a value of an API key from
+   [openrouter.com](https://openrouter.com).
+
+   <Frame>
+     <img src="https://storage.googleapis.com/cline_public_images/ss02-api-key.png" alt="Add API key secret" width="600" />
+   </Frame>
+
+5. Verify your secret is configured:
+
+   <Frame>
+     <img src="https://storage.googleapis.com/cline_public_images/ss03-ready.png" alt="API key configured" width="600" />
+   </Frame>
+
+Now you're ready to supply Cline with the credentials it needs in a GitHub Action.
+
+### 3. Add Analysis Script
+
+Add the analysis script from the `github-issue-rca` sample to your repository. **First, you'll need to create a `git-scripts` directory in your repository root where the script will be located.** Choose one of these options:
+
+**Option A: Download directly (Recommended)**
+
+```bash
+# In your repository root, create the directory and download the script
+mkdir -p git-scripts
+curl -o git-scripts/analyze-issue.sh https://raw.githubusercontent.com/cline/cline/main/src/samples/cli/github-issue-rca/analyze-issue.sh
+chmod +x git-scripts/analyze-issue.sh
+```
+
+**Option B: Manual copy-paste**
+
+Create the directory and file manually, then paste the script content:
+
+```bash
+# In your repository root
+mkdir -p git-scripts
+# Create and edit the file with your preferred editor
+nano git-scripts/analyze-issue.sh  # or use vim, code, etc.
+```
+
+<Accordion title="Click to view the complete analyze-issue.sh script">
+```bash
+#!/bin/bash
+# Analyze a GitHub issue using Cline CLI
+
+if [ -z "$1" ]; then
+    echo "Usage: $0 <github-issue-url> [prompt] [address]"
+    echo "Example: $0 https://github.com/owner/repo/issues/123"
+    echo "Example: $0 https://github.com/owner/repo/issues/123 'What is the root cause of this issue?'"
+    echo "Example: $0 https://github.com/owner/repo/issues/123 'What is the root cause of this issue?' 127.0.0.1:46529"
+    exit 1
+fi
+
+# Gather the args
+ISSUE_URL="$1"
+PROMPT="${2:-What is the root cause of this issue?}"
+if [ -n "$3" ]; then
+    ADDRESS="--address $3"
+fi
+
+# Ask Cline for its analysis, showing only the summary
+cline -y "$PROMPT: $ISSUE_URL" --mode act $ADDRESS -F json | \
+    sed -n '/^{/,$p' | \
+    jq -r 'select(.say == "completion_result") | .text' | \
+    sed 's/\\n/\n/g'
+```
+
+After pasting the script content, make it executable:
+```bash
+chmod +x git-scripts/analyze-issue.sh
+```
+</Accordion>
+
+This analysis script calls Cline to execute a prompt on a GitHub issue,
+summarizing the output to populate the reply to the issue.
+
+### 4. Commit and Push
+
+```bash
+git add .github/workflows/cline-responder.yml
+git add git-scripts/analyze-issue.sh
+git commit -m "Add Cline issue assistant workflow"
+git push
+```
+
+## Usage
+
+Once set up, simply mention `@cline` in any issue comment:
+
+```
+@cline what's causing this error?
+
+@cline analyze the root cause
+
+@cline what are the security implications?
+```
+
+GitHub Actions will:
+1. Detect the `@cline` mention
+2. Start a Cline CLI instance
+3. Download the analysis script
+4. Analyze the issue using act mode with yolo (fully autonomous)
+5. Post Cline's analysis as a new comment
+
+**Note**: The workflow only triggers on issue comments, not pull request
+comments.
+
+## How It Works
+
+The workflow (`cline-responder.yml`):
+
+1. **Triggers** on issue comments (created or edited)
+2. **Detects** `@cline` mentions (case-insensitive)
+3. **Installs** Cline CLI globally using npm
+4. **Creates** a Cline instance using `cline instance new`
+5. **Configures** authentication using `cline config set open-router-api-key=...
+   --address ...`
+6. **Downloads** the reusable `analyze-issue.sh` script from the
+   `github-issue-rca` sample
+7. **Runs** analysis with the instance address
+8. **Posts** the analysis result as a comment
+
+## Related Samples
+
+- **[github-issue-rca](./github-issue-rca)**: The reusable script that powers this integration

docs/cline-cli/samples/github-issue-rca.mdx

@@ -0,0 +1,383 @@
+---
+title: "GitHub Issue RCA Sample"
+description: "Automated GitHub issue analysis using Cline CLI to identify root causes."
+---
+
+# GitHub Root Cause Analysis
+
+Automated GitHub issue analysis using Cline CLI. This script uses Cline's autonomous AI capabilities to fetch, analyze, and identify root causes of GitHub issues, outputting clean, parseable results that can be easily integrated into your development workflows.
+
+<Note>
+**New to Cline CLI?** This sample assumes you have already completed the [Installation Guide](https://docs.cline.bot/cline-cli/installation) and authenticated with `cline auth`. If you haven't set up Cline CLI yet, please start there first.
+</Note>
+
+<Frame>
+  <img src="https://storage.googleapis.com/cline_public_images/cli-rca.gif" alt="CLI Root Cause Analysis Demo" width="600" />
+</Frame>
+
+## Prerequisites
+
+This sample assumes you have already:
+
+- **Cline CLI** installed and authenticated ([Installation Guide](https://docs.cline.bot/cline-cli/installation))
+- **At least one AI model provider** configured (e.g., OpenRouter, Anthropic, OpenAI)
+- **Basic familiarity** with Cline CLI commands
+
+Additionally, you'll need:
+
+- **GitHub CLI** (`gh`) installed and authenticated
+- **jq** installed for JSON parsing
+- **bash** shell (or compatible shell)
+
+### Installation Instructions
+
+#### macOS
+
+<Note>
+These instructions require [Homebrew](https://brew.sh/) to be installed. If you don't have Homebrew, install it first by running:
+```bash
+/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
+```
+</Note>
+
+```bash
+# Install GitHub CLI
+brew install gh
+
+# Install jq
+brew install jq
+
+# Authenticate with GitHub
+gh auth login
+```
+
+#### Linux
+
+```bash
+# Install GitHub CLI (Debian/Ubuntu)
+sudo apt install gh
+
+# Or for other Linux distributions, see: https://cli.github.com/manual/installation
+
+# Install jq (Debian/Ubuntu)
+sudo apt install jq
+
+# Authenticate with GitHub
+gh auth login
+```
+
+## Getting the Script
+
+**Option 1: Download directly with curl**
+```bash
+curl -O https://raw.githubusercontent.com/cline/cline/main/src/samples/cli/github-issue-rca/analyze-issue.sh
+```
+
+**Option 2: Copy the full script**
+
+<Accordion title="Click to view the complete analyze-issue.sh script">
+
+```bash
+#!/bin/bash
+# Analyze a GitHub issue using Cline CLI
+
+if [ -z "$1" ]; then
+    echo "Usage: $0 <github-issue-url> [prompt] [address]"
+    echo "Example: $0 https://github.com/owner/repo/issues/123"
+    echo "Example: $0 https://github.com/owner/repo/issues/123 'What is the root cause of this issue?'"
+    echo "Example: $0 https://github.com/owner/repo/issues/123 'What is the root cause of this issue?' 127.0.0.1:46529"
+    exit 1
+fi
+
+# Gather the args
+ISSUE_URL="$1"
+PROMPT="${2:-What is the root cause of this issue?}"
+if [ -n "$3" ]; then
+    ADDRESS="--address $3"
+fi
+
+# Ask Cline for its analysis, showing only the summary
+cline -y "$PROMPT: $ISSUE_URL" --mode act $ADDRESS -F json | \
+    sed -n '/^{/,$p' | \
+    jq -r 'select(.say == "completion_result") | .text' | \
+    sed 's/\\n/\n/g'
+```
+
+</Accordion>
+
+<Note>
+**After downloading or creating the script**, make it executable by running:
+```bash
+chmod +x analyze-issue.sh
+```
+</Note>
+
+## Quick Usage Examples
+
+### Basic Usage
+
+Run this command in your terminal from the directory where you saved the script to analyze an issue with the default root cause prompt:
+
+```bash
+./analyze-issue.sh https://github.com/owner/repo/issues/123
+```
+
+This will:
+- Fetch issue #123 from the repository
+- Analyze the issue to identify root causes
+- Provide detailed analysis with recommendations
+
+### Custom Analysis Prompt
+
+Ask specific questions about the issue:
+
+```bash
+./analyze-issue.sh https://github.com/owner/repo/issues/456 "What is the security impact?"
+```
+
+### Using Specific Cline Instance
+
+Target a particular Cline instance by address:
+
+```bash
+./analyze-issue.sh https://github.com/owner/repo/issues/123 \
+    "What is the root cause of this issue?" \
+    127.0.0.1:46529
+```
+
+<Warning>
+This is useful when:
+- Running multiple Cline instances
+- Using a remote Cline server
+- Testing with specific configurations
+</Warning>
+
+<Note>
+The script will automatically handle everything: fetching the issue, analyzing it with Cline, and displaying the results. The analysis typically takes 30-60 seconds depending on the issue complexity.
+</Note>
+
+## How It Works
+
+Let's analyze each component of the script to understand how it works.
+
+### Argument Validation
+
+The script validates input and provides usage instructions:
+
+```bash
+if [ -z "$1" ]; then
+    echo "Usage: $0 <github-issue-url> [prompt] [address]"
+    echo "Example: $0 https://github.com/owner/repo/issues/123"
+    echo "Example: $0 https://github.com/owner/repo/issues/123 'What is the root cause?'"
+    echo "Example: $0 https://github.com/owner/repo/issues/123 'Analyze security impact' 127.0.0.1:46529"
+    exit 1
+fi
+```
+
+**Key Points:**
+- Validates required GitHub issue URL
+- Shows clear usage examples
+- Supports optional custom prompt
+- Supports optional Cline instance address
+
+### Argument Parsing
+
+The script extracts and sets up the arguments:
+
+```bash
+# Gather the args
+ISSUE_URL="$1"
+PROMPT="${2:-What is the root cause of this issue?}"
+if [ -n "$3" ]; then
+    ADDRESS="--address $3"
+fi
+```
+
+**Explanation:**
+- `ISSUE_URL="$1"` - First argument is always the issue URL
+- `PROMPT="${2:-...}"` - Second argument is optional, defaults to root cause analysis
+- `ADDRESS` - Third argument is optional, only set if provided
+
+### The Core Analysis Pipeline
+
+This is where the magic happens:
+
+```bash
+# Ask Cline for his analysis, showing only the summary
+cline -y "$PROMPT: $ISSUE_URL" --mode act $ADDRESS -F json | \
+    sed -n '/^{/,$p' | \
+    jq -r 'select(.say == "completion_result") | .text' | \
+    sed 's/\\n/\n/g'
+```
+
+<Accordion title="Pipeline Breakdown: Understanding Each Component">
+
+**1. `cline -y "$PROMPT: $ISSUE_URL"`**
+   - `-y` enables yolo mode (no user interaction)
+   - Constructs prompt with issue URL
+
+**2. `--mode act`**
+   - Enables act mode for active investigation
+   - Allows Cline to use tools (read files, run commands, etc.)
+
+**3. `$ADDRESS`**
+   - Optional address flag for specific instance
+   - Expands to `--address <ip:port>` if set
+
+**4. `-F json`**
+   - Outputs in JSON format for parsing
+
+**5. `sed -n '/^{/,$p'`**
+   - Extracts JSON from output
+   - Skips any non-JSON prefix lines
+
+**6. `jq -r 'select(.say == "completion_result") | .text'`**
+   - Filters for completion result messages
+   - Extracts the text field
+   - `-r` outputs raw strings (no JSON quotes)
+
+**7. `sed 's/\\n/\n/g'`**
+   - Converts escaped newlines to actual newlines
+   - Makes output readable
+
+</Accordion>
+
+## Sample Output
+
+Here's an example analyzing a real Flutter issue:
+
+```bash
+$ ./analyze-issue.sh https://github.com/csells/flutter_counter/issues/2
+```
+
+**Output:**
+
+```markdown
+**Root Cause Analysis of Issue #2: "setState isn't cutting it"**
+
+After examining the GitHub issue and analyzing the Flutter counter codebase, 
+I've identified the root cause of why setState() is insufficient for this 
+project's needs:
+
+## Current Implementation Problems
+
+The current Flutter counter app uses setState() for state management, which 
+has several limitations:
+
+1. **Local State Only**: setState() only works within a single widget, making 
+   it difficult to share state across the app
+2. **Rebuild Overhead**: Every setState() call rebuilds the entire widget tree, 
+   causing performance issues with complex UIs
+3. **No State Persistence**: State is lost when the widget is disposed
+4. **Testing Challenges**: setState-based logic is tightly coupled to the UI, 
+   making unit testing difficult
+
+## Why This Matters
+
+As the app grows beyond a simple counter, these limitations become critical:
+- Multiple screens need to access the count
+- State needs to persist across navigation
+- Business logic should be testable independently
+- UI should only rebuild when necessary
+
+## Recommended Solutions
+
+The issue mentions "Provider or Bloc" - both are excellent alternatives:
+
+1. **Provider**: Simple, lightweight state management using InheritedWidget
+   - Easy migration path from setState
+   - Good for small to medium apps
+   - Official Flutter recommendation
+
+2. **Bloc**: More structured approach with clear separation between events, 
+   states, and business logic
+   - Better for complex apps
+   - Excellent testability
+   - Clear architectural patterns
+
+3. **Riverpod**: Modern alternative to Provider with better performance and 
+   developer experience
+   - Compile-time safety
+   - Better testing support
+   - More flexible than Provider
+
+4. **GetX**: Full-featured solution with state management, routing, and 
+   dependency injection
+   - Minimal boilerplate
+   - Fast and lightweight
+   - All-in-one solution
+
+## Next Steps
+
+The current codebase needs refactoring to implement proper state management 
+architecture to handle more complex state scenarios effectively. Provider 
+would be the easiest migration path while Bloc provides better long-term 
+scalability.
+```
+
+## When to Use This Pattern
+
+This script pattern is ideal for various development scenarios where automated GitHub issue analysis can accelerate your workflow.
+
+### Bug Investigation
+
+Quickly analyze bug reports and identify root causes without manual code exploration:
+
+```bash
+./analyze-issue.sh https://github.com/project/repo/issues/123 \
+    "What is the root cause of this bug?"
+```
+
+### Feature Request Analysis
+
+Understand context and implications of feature requests:
+
+```bash
+./analyze-issue.sh https://github.com/project/repo/issues/456 \
+    "What are the implementation challenges?"
+```
+
+### Security Audits
+
+Assess security implications of reported issues:
+
+```bash
+./analyze-issue.sh https://github.com/project/repo/issues/789 \
+    "What are the security implications?"
+```
+
+### Documentation Generation
+
+Generate detailed technical documentation from issues:
+
+```bash
+./analyze-issue.sh https://github.com/project/repo/issues/654 \
+    "Provide detailed technical documentation for this issue"
+```
+
+### Code Review Assistance
+
+Get second opinions on proposed changes:
+
+```bash
+./analyze-issue.sh https://github.com/project/repo/issues/987 \
+    "Review the proposed solution approach"
+```
+
+## Conclusion
+
+This sample demonstrates how to build an autonomous GitHub issue analysis tool using Cline CLI:
+
+1. **Building autonomous CLI tools** using Cline's capabilities
+2. **Parsing structured JSON output** from Cline CLI
+3. **Creating flexible automation scripts** with custom prompting
+4. **Integrating with GitHub** for issue analysis
+5. **Handling command-line arguments** effectively
+
+This pattern can be adapted for many other automation scenarios, from pull request reviews to documentation generation to code quality analysis.
+
+## Related Resources
+
+- [CLI Installation Guide](https://docs.cline.bot/cline-cli/installation)
+- [CLI Reference Documentation](https://docs.cline.bot/cline-cli/cli-reference)
+- [Three Core Flows](https://docs.cline.bot/cline-cli/three-core-flows)

docs/cline-cli/samples/overview.mdx

@@ -0,0 +1,32 @@
+---
+title: "Samples Overview"
+description: Example implementations demonstrating Cline CLI capabilities
+---
+
+This section provides sample implementations that demonstrate various Cline CLI features and capabilities. Each sample includes complete code, detailed explanations, and real-world usage examples.
+
+## Available Samples
+
+<CardGroup cols={1}>
+  <Card 
+    title="GitHub Root Cause Analysis" 
+    icon="magnifying-glass-chart" 
+    href="/cline-cli/samples/github-issue-rca"
+  >
+    A command-line script that uses Cline's autonomous AI capabilities to fetch, analyze, and identify root causes of GitHub issues. Features JSON output parsing and non-interactive execution.
+  </Card>
+
+  <Card 
+    title="GitHub Integration (Actions)" 
+    icon="github" 
+    href="/cline-cli/samples/github-integration"
+  >
+    Automatically respond to GitHub issues by mentioning @cline in comments. Uses Cline CLI in GitHub Actions to create an AI-powered issue assistant that analyzes and responds autonomously.
+  </Card>
+</CardGroup>
+
+## Additional Resources
+
+- [CLI Installation Guide](/cline-cli/installation)
+- [CLI Reference Documentation](/cline-cli/cli-reference)
+- [Three Core Flows](/cline-cli/three-core-flows)

docs/docs.json

@@ -88,6 +88,14 @@
 							"cline-cli/overview",
 							"cline-cli/installation",
 							"cline-cli/three-core-flows",
+							{
+								"group": "CLI Samples",
+								"pages": [
+									"cline-cli/samples/overview",
+									"cline-cli/samples/github-issue-rca",
+									"cline-cli/samples/github-integration"
+								]
+							},
 							"cline-cli/cli-reference"
 						]
 					},
@@ -130,6 +138,7 @@
 							"features/drag-and-drop",
 							"features/editing-messages",
 							"features/focus-chain",
+							"features/hooks",
 							"features/multiroot-workspace",
 							"features/plan-and-act",
 							{
@@ -315,6 +324,10 @@
 		{
 			"source": "/getting-started/your-first-task",
 			"destination": "/getting-started/your-first-project"
+		},
+		{
+			"source": "/cline-cli/samples",
+			"destination": "/cline-cli/samples/overview"
 		}
 	],
 	"search": {

docs/features/cline-rules.mdx

@@ -81,6 +81,20 @@ your-project/
 
 Cline's system prompt, on the other hand, is not user-editable ([here's where you can find it](https://github.com/cline/cline/blob/main/src/core/prompts/system.ts)). For a broader look at prompt engineering best practices, check out [this resource](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview).
 
+### AGENTS.md Standard Support
+
+Cline also supports the [AGENTS.md](https://agents.md/) standard as a fallback 
+(in addition to Cline Rules) by automatically detecting `AGENTS.md` files in 
+your workspace root. This allows you to use the same rules file across different AI 
+coding tools.
+
+```
+your-project/
+├── AGENTS.md
+├── src/
+└── ...
+```
+
 ### Tips for Writing Effective Cline Rules
 
 -   Be Clear and Concise: Use simple language and avoid ambiguity.

docs/features/customization/opening-cline-in-sidebar.mdx

@@ -42,17 +42,17 @@ To open Cline in the right sidebar:
     4. Set the value to `vertical`
     5. Restart Cursor for the changes to take effect
   </Step>
-  <Step title="Open Agent Panel">
-    Click the Cursor cube icon button that opens Cursor's agent (right side view panel)
+  <Step title="Open the AI Pane">
+    Click the Cursor cube icon button (AI Pane) that opens Cursor's agent (right side view panel)
   </Step>
-  <Step title="Drag to Three Dots">
-    Drag the Cline icon directly onto the three dots button - it doesn't work if you just drag it to the top, it has to be the three dots
+  <Step title="Drag Cline to the AI Pane Sidebar">
+    Drag the Cline icon directly into the AI Pane sidebar.
   </Step>
 </Steps>
 
 <Frame>
 	<img
-		src="https://storage.googleapis.com/cline_public_images/cursor-side-bar.gif"
+		src="https://storage.googleapis.com/cline_public_images/Cursor-sidebar.gif"
 		alt="Cursor Right Sidebar Setup"
 	/>
 </Frame>

docs/features/dictation.mdx

@@ -3,7 +3,7 @@ title: "Dictation"
 description: "Communicate with Cline using your voice for faster, more natural AI collaboration"
 ---
 
-Dictation transforms how you work with AI. Instead of typing out complex thoughts, you speak naturally and share your complete intent. This isn't just about speed - though voice is faster - it's about unlocking the kind of fluid collaboration that typing can't match.
+Dictation transforms how you work with AI. Instead of typing out complex thoughts, you speak naturally and share your complete intent. This isn't just about speed - though voice is faster - it's about enabling fluid collaboration that typing can't match.
 
 ## Why Voice Changes Everything
 
@@ -35,11 +35,14 @@ Dictation works with any AI model you've configured. The transcription happens t
 
 ## System Requirements
 
+<Note>
+Dictation is currently not available on Windows. Support for Windows is planned for a future release.
+</Note>
+
 Dictation uses FFmpeg to capture your voice across all platforms:
 
 - **macOS**: FFmpeg (via Homebrew: `brew install ffmpeg`)
 - **Linux**: FFmpeg (via apt: `sudo apt-get install ffmpeg`)
-- **Windows**: FFmpeg (via winget: `winget install Gyan.FFmpeg`)
 
 If you don't have FFmpeg installed, Cline will automatically detect this and prompt you to install it with a single click.
 

docs/features/hooks.mdx

@@ -0,0 +1,419 @@
+---
+title: "Hooks"
+sidebarTitle: "Hooks"
+description: "Inject custom logic into Cline's workflow to validate operations, monitor tool usage, and shape AI decisions"
+---
+
+Hooks let you inject custom logic into Cline's workflow at key moments. Think of them as automated checkpoints where you can validate operations before they execute, monitor tool usage as it happens, and shape how Cline makes decisions.
+
+Hooks run automatically when specific events happen during development. They receive detailed information about each operation, can block problematic actions before they cause issues, and can inject context that guides future AI decisions.
+
+The real power comes from combining these capabilities. You can:
+
+- Stop operations before they cause problems (like creating `.js` files in a TypeScript project)
+- Learn from what's happening and build up project knowledge over time
+- Monitor performance and catch issues as they emerge
+- Track everything for analytics or compliance
+- Trigger external tools or services at the right moments
+
+<Warning>
+Hooks are currently supported on macOS and Linux only. Windows support is not available.
+</Warning>
+
+## Getting Started
+
+<Frame>
+	<img src="https://storage.googleapis.com/cline_public_images/hooks.gif" alt="Hooks in action" />
+</Frame>
+
+Enabling hooks in Cline is straightforward. Here's what you need to do:
+
+<Steps>
+<Step title="Enable Hooks in Settings">
+Open Cline settings and check the **"Enable Hooks"** checkbox.
+
+You can find this setting by:
+1. Opening Cline
+2. Click the "Settings" button on the top right corner
+3. Click the "Feature" section in the left side navigation menu.
+4. Scroll down until you see the "Enable Hooks" checkbox and check it. 
+</Step>
+
+<Step title="Choose Your Hook Location">
+Decide where to place your hooks:
+
+**For personal or organization-wide hooks:**
+- Create hooks in `~/Documents/Cline/Rules/Hooks/`
+- These apply to all workspaces automatically
+
+**For project-specific hooks:**
+- Create hooks in `.clinerules/hooks/` in your project root
+- These only apply to the specific workspace
+- Commit them to version control so your team can use them too
+</Step>
+
+<Step title="Create Your First Hook">
+Hook files must have exact names with no file extensions. For example, to create a TaskStart hook:
+
+```bash
+# Create the hook file
+vim .clinerules/hooks/TaskStart
+```
+
+Add your script (must start with shebang)
+``` bash
+#!/usr/bin/env bash
+
+# Store piped input into a variable
+input=$(cat)
+
+# Dump the entire JSON payload
+echo "$input" | jq .
+
+# Get the type of a field
+echo "$input" | jq -r '.timestamp | type'
+```
+
+This example script demonstrates the key mechanics of hook input/output: reading the JSON payload from stdin with `input=$(cat)`, and using `jq` to inspect the data structure and field types that your hook receives. This helps you understand what data is available before building more complex hook logic.
+
+**Make it executable**
+
+```bash
+chmod +x .clinerules/hooks/TaskStart
+```
+</Step>
+
+<Step title="Test Your Hook">
+Start a task in Cline and verify your hook executes.
+</Step>
+</Steps>
+
+<Tip>
+Start with a simple hook that just logs information before building complex validation logic. This helps you understand the data structure and timing.
+</Tip>
+
+
+## What You Can Build
+
+Once you understand the basics, hooks open up creative possibilities:
+
+<CardGroup cols={2}>
+  <Card title="Intelligent Code Review" icon="code-branch">
+    Run linters or custom validators before files get saved. Block commits that don't pass checks. Track code quality metrics over time.
+  </Card>
+  
+  <Card title="Security Enforcement" icon="shield-halved">
+    Prevent operations that violate security policies. Detect when sensitive data might be exposed. Audit all file access for compliance.
+  </Card>
+  
+  <Card title="Development Analytics" icon="chart-line">
+    Measure how long different operations take. Identify patterns in how the AI works. Generate productivity reports from hook data.
+  </Card>
+  
+  <Card title="Integration Hub" icon="plug">
+    Connect to issue trackers when certain keywords appear. Update project management tools. Sync with external APIs at the right moments.
+  </Card>
+</CardGroup>
+
+The key is combining hooks with external tools. A hook can be the glue between Cline's workflow and the rest of your development ecosystem.
+
+
+## Hook Types
+
+Cline provides multiple hook types that let you tap into different stages of the AI workflow. They're organized into categories based on their trigger points and use cases.
+
+<Note>
+The hook names below are the exact file names you need to create. For example, to use the TaskStart hook, create a file named `TaskStart` (no file extension) in your hooks directory.
+</Note>
+
+Each hook receives base fields in addition to its specific data: `clineVersion`, `hookName`, `timestamp`, `taskId`, `workspaceRoots`, `userId`.
+
+### Tool Execution
+
+These hooks intercept and validate tool operations before and after they execute. Use them to enforce policies, track changes, and learn from operations.
+
+#### PreToolUse
+
+Runs before any tool executes. Use it to block invalid operations, validate parameters, and enforce project policies before changes happen.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "PreToolUse",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "preToolUse": {
+    "toolName": "string",
+    "parameters": {}
+  }
+}
+```
+
+#### PostToolUse
+
+Runs after a tool completes. Use it to learn from results, track performance metrics, and build project knowledge based on operations performed.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "PostToolUse",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "postToolUse": {
+    "toolName": "string",
+    "parameters": {},
+    "result": "string",
+    "success": boolean,
+    "executionTimeMs": number
+  }
+}
+```
+
+### User Interaction
+
+These hooks monitor and enhance user communication with Cline. Use them to validate input, inject context, and track interaction patterns.
+
+#### UserPromptSubmit
+
+Runs when a user sends a message to Cline. Use it to validate input, inject context based on the prompt, and track interaction patterns.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "UserPromptSubmit",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "userPromptSubmit": {
+    "prompt": "string",
+    "attachments": ["string"]
+  }
+}
+```
+
+### Task Lifecycle
+
+These hooks monitor and respond to task state changes from start to finish. Use them to track progress, restore state, and trigger workflows.
+
+#### TaskStart
+
+Runs when a new task begins. Use it to detect project type, initialize tracking, and inject initial context that shapes how Cline approaches the work.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "TaskStart",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "taskStart": {
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string",
+      "initialTask": "string"
+    }
+  }
+}
+```
+
+#### TaskResume
+
+Runs when a task resumes after interruption. Use it to restore state, refresh context, and log resumption for analytics or external system notifications.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "TaskResume",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "taskResume": {
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string"
+    },
+    "previousState": {
+      "lastMessageTs": "string",
+      "messageCount": "string",
+      "conversationHistoryDeleted": "string"
+    }
+  }
+}
+```
+
+#### TaskCancel
+
+Runs when a task is cancelled. Use it to cleanup resources, log cancellation details, and notify external systems about interrupted work.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "TaskCancel",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "taskCancel": {
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string",
+      "completionStatus": "string"
+    }
+  }
+}
+```
+
+{/*
+#### TaskComplete
+
+Runs when a task finishes successfully. Use it for final cleanup, tracking metrics, generating reports, and triggering post-task workflows.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "TaskComplete",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "taskComplete": {
+    "taskMetadata": {
+      "taskId": "string",
+      "ulid": "string"
+    }
+  }
+}
+```
+*/}
+
+### System Events
+
+These hooks monitor internal Cline operations and system-level events. Use them to track context usage, log system behavior, and analyze performance patterns.
+
+{/*
+#### PreCompact
+
+Runs before conversation context is truncated to fit token limits. Use it to monitor compaction frequency, log events, and track context usage patterns.
+
+**Input Fields:**
+```json
+{
+  "clineVersion": "string",
+  "hookName": "PreCompact",
+  "timestamp": "string",
+  "taskId": "string",
+  "workspaceRoots": ["string"],
+  "userId": "string",
+  "preCompact": {
+    "contextSize": number,
+    "messagesToCompact": number,
+    "compactionStrategy": "string"
+  }
+}
+```
+*/}
+
+### JSON Communication
+
+Hooks receive JSON via stdin and return JSON via stdout.
+
+**Output structure:**
+```json
+{
+  "cancel": false,
+  "contextModification": "WORKSPACE_RULES: Use TypeScript",
+  "errorMessage": "Error details if blocking"
+}
+```
+
+Your hook script can output logging or diagnostic information to stdout during execution, as long as the JSON response is the last thing written. Cline will parse only the final JSON object from stdout.
+
+For example:
+```bash
+#!/usr/bin/env bash
+echo "Processing hook..."  # This is fine
+echo "Tool: $tool_name"    # This is also fine
+# The JSON must be last:
+echo '{"cancel": false}'
+```
+
+The `cancel` field controls whether execution continues. Set it to `true` to block an action, `false` to allow it.
+
+The `contextModification` field injects text into the conversation. This affects future AI decisions, not the current one. Use prefixes like `WORKSPACE_RULES:` or `PERFORMANCE:` to help categorize the context.
+
+### Understanding Context Timing
+
+Context injection affects future decisions, not current ones. When a hook runs:
+
+1. The AI has already decided what to do
+2. The hook can block or allow it
+3. Any context gets added to the conversation
+4. The next AI request sees that context
+
+This means PreToolUse hooks are for blocking bad actions, while PostToolUse hooks are for learning from completed ones.
+
+
+## Troubleshooting
+
+### Hook Not Running
+- Ensure the "Enable Hooks" setting is checked
+- Verify the hook file is executable (`chmod +x hookname`)
+- Check the hook file has no syntax errors
+- Look for errors in VSCode's Output panel (Cline channel)
+
+### Hook Timing Out
+- Reduce complexity of the hook script
+- Avoid expensive operations (network calls, heavy computations)
+- Consider moving complex logic to a background process
+
+### Context Not Affecting Behavior
+Remember that context modifications affect future AI decisions, not the current operation. The AI's current behavior is based on the previous "API Request..." block, and your `contextModification` gets injected into the next "API Request..." block. This means if you need immediate effect, you should use PreToolUse hooks for validation and return `cancel: true` in your hook's JSON response to block Cline from continuing.
+
+When adding context, ensure your modifications are clear and actionable so the AI can understand and apply them effectively. Also check that your context isn't being truncated due to the 50KB limit, as this could prevent important information from reaching the AI.
+
+### Handling Strings with Quotes in JSON Payloads
+When your hook needs to include strings containing unescaped quote characters (`"`) in JSON output, use jq's `--arg` flag for proper escaping:
+
+```bash
+#!/usr/bin/env bash
+
+# When $output contains unescaped quote characters (")...
+output='{"foo":"bar"}'
+
+# Use the --arg flag for automatic string escaping
+jq -n --arg ctx "$output" '{cancel: false, contextModification: $ctx}'
+
+# This will result in:
+# {
+#     "cancel": false,
+#     "contextModification": "{\"foo\":\"bar\"}"
+# }
+```
+
+The `--arg` flag automatically escapes special characters, preventing JSON parsing errors when your context modification includes complex strings or nested JSON structures.
+
+<Warning>
+Hooks run with the same permissions as VS Code. They can access all workspace files and environment variables. Review hooks from untrusted sources before enabling them.
+</Warning>
+
+## Related Features
+
+Hooks complement other Cline features:
+
+- [Cline Rules](/features/cline-rules) define high-level guidance that hooks can enforce
+- [Checkpoints](/features/checkpoints) let you roll back changes if a hook didn't catch an issue
+- [Auto-Approve](/features/auto-approve) works well with hooks as safety nets for automated operations

docs/getting-started/your-first-project.mdx

@@ -35,7 +35,7 @@ Create a simple website in a single HTML file. It should have:
 ```
 
 <Frame>
-  <img src="/assets/installation/chat-prompt.png" alt="Cline Chat Prompt"/>
+  <img src="https://storage.googleapis.com/cline_public_images/chat-prompt.png" alt="Cline Chat Prompt"/>
 </Frame>
 
 Press Enter and watch Cline work!

docs/mcp/connecting-to-a-remote-server.mdx

@@ -29,11 +29,33 @@ The "Remote Servers" tab allows you to connect to any MCP server that's accessib
 2. Fill in the required information:
     - **Server Name**: Provide a unique, descriptive name for the server
     - **Server URL**: Enter the complete URL endpoint of the MCP server (e.g., `https://example.com/mcp-sse`)
+    - **Transport Type**: Select the connection protocol (Streamable HTTP is recommended for modern servers)
 3. Click "Add Server" to initiate the connection
 4. Cline will attempt to connect to the server and display the connection status
 
 > **Note**: When connecting to a remote server, ensure you trust the source, as MCP servers can execute code in your environment.
 
+#### Transport Types
+
+Cline supports two transport protocols for remote MCP servers:
+
+-   **Streamable HTTP (Recommended)**: The modern MCP transport protocol with better performance, reliability, and full OAuth 2.1 authentication support. Use this for most remote servers.
+-   **SSE (Legacy)**: Server-Sent Events transport. Use this only if the server specifically requires SSE or doesn't support Streamable HTTP.
+
+#### OAuth Authentication
+
+Some MCP servers (like Vercel's MCP) require OAuth authentication to access your data securely. When connecting to an OAuth-enabled server:
+
+1. Add the server as usual with its URL
+2. If the server requires authentication, you'll see an error message asking to authenticate.
+3. Click the **"Authenticate"** button that appears
+4. Your browser will open to the server's authorization page
+5. Sign in and grant permission
+6. You'll be redirected back to Cline automatically
+7. The server will connect and show a green status dot
+
+Once authenticated, your credentials are securely stored and the server will reconnect automatically when you reload Cline. You won't need to authenticate again unless you delete the server or your credentials expire.
+
 ### Remote Server Discovery
 
 If you're looking for MCP servers to connect to, several third-party marketplaces provide directories of available servers with various capabilities.
@@ -90,9 +112,20 @@ Toggle the switch next to each server to enable or disable it:
 If a server fails to connect:
 
 1. An error message will be displayed with details about the failure
-2. Check that the server URL is correct and the server is running
-3. Use the "Restart Server" button to attempt reconnection
-4. If problems persist, you can delete the server and try adding it again
+2. **For OAuth errors**: Click the "Authenticate" button to complete the authorization flow
+3. Check that the server URL is correct and the server is running
+4. Try selecting a different transport type (Streamable HTTP vs SSE)
+5. Use the "Restart Server" button to attempt reconnection
+6. If problems persist, you can delete the server and try adding it again
+
+#### OAuth-Specific Issues
+
+If you're having trouble authenticating with an OAuth-enabled server:
+
+-   **"Authentication required" persists**: Make sure you completed the authorization flow in your browser and didn't cancel it
+-   **Browser doesn't open**: Check your system's default browser settings and ensure external URLs can be opened
+-   **Redirect errors**: Verify you're using the latest version of Cline - older versions may not support OAuth
+-   **Reset authentication**: Delete the server and re-add it to start fresh with a new OAuth flow
 
 ### Advanced Configuration
 
@@ -105,10 +138,11 @@ For advanced users, Cline stores MCP server configurations in a JSON file that c
 {
 	"mcpServers": {
 		"exampleServer": {
-			"url": "https://example.com/mcp-sse",
+			"url": "https://example.com/mcp-server",
+			"type": "streamableHttp",
 			"disabled": false,
 			"autoApprove": ["tool1", "tool2"],
-			"timeout": 30
+			"timeout": 60
 		}
 	}
 }
@@ -117,9 +151,10 @@ For advanced users, Cline stores MCP server configurations in a JSON file that c
 Key configuration options:
 
 -   **url**: The endpoint URL (for remote servers)
+-   **type**: Transport protocol - `"streamableHttp"` (recommended) or `"sse"` (legacy)
 -   **disabled**: Whether the server is currently enabled (true/false)
 -   **autoApprove**: List of tool names that don't require confirmation
--   **timeout**: Maximum time in seconds to wait for server responses
+-   **timeout**: Maximum time in seconds to wait for server responses (default: 60)
 
 For additional MCP settings, click the "Advanced MCP Settings" link to access VSCode settings.
 
@@ -130,3 +165,20 @@ Once connected, Cline can use the tools and resources provided by the MCP server
 1. A tool approval prompt will appear (unless auto-approved)
 2. Review the tool details and parameters before approving
 3. The tool will execute and return results to Cline
+
+### Example: Connecting to Vercel MCP
+
+[Vercel MCP](https://vercel.com/docs/mcp/vercel-mcp) is an OAuth-enabled server that provides tools for managing your Vercel projects and deployments:
+
+1. Click "Remote Servers" tab
+2. Enter:
+    - **Server Name**: `vercel`
+    - **Server URL**: `https://mcp.vercel.com`
+    - **Transport Type**: Streamable HTTP (pre-selected)
+3. Click "Add Server"
+4. You'll see "Authentication required" - click the **"Authenticate"** button
+5. Sign in to Vercel in your browser and authorize Cline
+6. Return to Cline - the server will automatically connect
+7. Vercel's tools (deploy, logs, projects) are now available to Cline!
+
+Your Vercel authentication persists across sessions, so you won't need to re-authenticate each time you use Cline.

docs/provider-config/baseten.mdx

@@ -21,20 +21,16 @@ For the most updated pricing, please visit: https://www.baseten.co/products/mode
 Note: Kimi K2 0711, Llama 4 Maverick, and Llama 4 Scout Model APIs have been deprecated at 5pm PT on October 8th.
 https://www.baseten.co/resources/changelog/model-api-deprecation-notice-kimi-k2-0711-scout-maverick/
 
-**Reasoning Models:**
+-   `zai-org/GLM-4.6` (Z AI) - Frontier open model with advanced agentic, reasoning and coding capabilities by Z AI (200k context) \$0.60/\$2.20 per 1M tokens
+-   `moonshotai/Kimi-K2-Instruct-0905` (Moonshot AI) - September update with enhanced capabilities (262K context) - \$0.60/\$2.50 per 1M tokens
+-   `openai/gpt-oss-120b` (OpenAI) - 120B MoE with strong reasoning capabilities (128K context) - \$0.10/\$0.50 per 1M tokens
+-   `Qwen/Qwen3-Coder-480B-A35B-Instruct`- Advanced coding and reasoning (262K context) - \$0.38/\$1.53 per 1M tokens
+-   `Qwen/Qwen3-235B-A22B-Instruct-2507` - Math and reasoning expert (262K context) - \$0.22/\$0.80 per 1M tokens
 -   `deepseek-ai/DeepSeek-R1` - DeepSeek's first-generation reasoning model (163K context) - \$2.55/\$5.95 per 1M tokens
 -   `deepseek-ai/DeepSeek-R1-0528` - Latest revision of DeepSeek's reasoning model (163K context) - \$2.55/\$5.95 per 1M tokens
 -   `deepseek-ai/DeepSeek-V3.1` - Hybrid reasoning with advanced tool calling (163K context) - \$0.50/\$1.50 per 1M tokens
 -   `deepseek-ai/DeepSeek-V3-0324` - Fast general-purpose with enhanced reasoning (163K context) - \$0.77/\$0.77 per 1M tokens
 
-**Flagship Models:**
--   `openai/gpt-oss-120b` (OpenAI) - 120B MoE with strong reasoning capabilities (128K context) - \$0.10/\$0.50 per 1M tokens
--   `moonshotai/Kimi-K2-Instruct-0905` (Moonshot AI) - September update with enhanced capabilities (262K context) - \$0.60/\$2.50 per 1M tokens
-
-**Coding Specialists:**
--   `Qwen/Qwen3-Coder-480B-A35B-Instruct`- Advanced coding and reasoning (262K context) - \$0.38/\$1.53 per 1M tokens
--   `Qwen/Qwen3-235B-A22B-Instruct-2507` - Math and reasoning expert (262K context) - \$0.22/\$0.80 per 1M tokens
-
 ### Configuration in Cline
 
 1.  **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.

docs/provider-config/cerebras.mdx

@@ -18,8 +18,7 @@ Cerebras delivers the world's fastest AI inference through their revolutionary w
 
 Cline supports the following Cerebras models:
 
--   `qwen-3-coder-480b-free` (Free tier) - High-performance coding model at no cost
--   `qwen-3-coder-480b` - Flagship 480B parameter coding model
+-   `zai-glm-4.6` - Intelligent general purpose model with 1,500 tokens/s
 -   `qwen-3-235b-a22b-instruct-2507` - Advanced instruction-following model
 -   `qwen-3-235b-a22b-thinking-2507` - Reasoning model with step-by-step thinking
 -   `llama-3.3-70b` - Meta's Llama 3.3 model optimized for speed

docs/provider-config/claude-code.mdx

@@ -34,18 +34,10 @@ First, you'll need to install and authenticate Claude Code on your system:
 
 <br />
 
-<Accordion title="Windows Setup">
-	Anthropic introduced full support for Claude Code on Windows. Follow the [instructions on how to set up Claude Code
-	normally](#setup) and make sure you have the latest Claude Code and Cline versions.
-</Accordion>
-
 ### Finding your Claude Code path
 
-If you're not sure where Claude Code is installed:
-
--   **macOS / Linux**: Run `which claude` in your terminal
--   **Windows (Command Prompt)**: Run `where claude`
--   **Windows (PowerShell)**: Run `Get-Command claude`
+-   **macOS / Linux / WSL / Git Bash**: `which claude`
+-   **Windows Command Prompt**: `where claude`
 
 ## Supported Models
 

docs/styles.css

@@ -42,7 +42,8 @@ h5,
 h6,
 img {
 	opacity: 1 !important;
-	font-family: "Geist Sans", -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Oxygen, Ubuntu, Cantarell, sans-serif !important;
+	font-family:
+		"Geist Sans", -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Oxygen, Ubuntu, Cantarell, sans-serif !important;
 }
 
 /* Also apply to any h1 elements within content areas */

esbuild.mjs

@@ -123,7 +123,11 @@ const copyWasmFiles = {
 	},
 }
 
-const buildEnvVars = { "import.meta.url": "_importMetaUrl" }
+const buildEnvVars = {
+	"import.meta.url": "_importMetaUrl",
+	"process.env.IS_STANDALONE": JSON.stringify(standalone),
+}
+
 if (production) {
 	// IS_DEV is always disable in production builds.
 	buildEnvVars["process.env.IS_DEV"] = "false"

evals/.gitignore

@@ -1,6 +1,6 @@
 repositories
-
-results/evals.db
+temp-files
+results
 
 diff-edits/cases/
 diff-edits/results/
@@ -21,4 +21,4 @@ diff_editing/test_outputs/
 # Python bytecode cache
 *__pycache__/
 
-diff-edits/cases.zip
+diff-edits/cases.zip

evals/README.md

@@ -15,48 +15,32 @@ The Cline Evaluation System allows you to:
 
 The evaluation system consists of two main components:
 
-1. **Test Server**: Enhanced HTTP server in `src/services/test/TestServer.ts` that provides detailed task results
-2. **CLI Tool**: Command-line interface in `evals/cli/` for orchestrating evaluations
-3. **Diff Edit Benchmark**: Separate command using the CLI tool that runs a comprehensive diff editing benchmark suite on real world cases, along with a streamlit dashboard displaying the results. For more details, see the [Diff Edit Benchmark README](./diff-edits/README.md). Make sure you add a `evals/diff-edits/cases` folder with all the conversation jsons. 
+1. **CLI Tool**: Command-line interface in `evals/cli/` for orchestrating evaluations
+2. **Diff Edit Benchmark**: Separate command using the CLI tool that runs a comprehensive diff editing benchmark suite on real world cases, along with a streamlit dashboard displaying the results. For more details, see the Diff Edit Benchmark [README](./diff-edits/README.md). Make sure you add a `evals/diff-edits/cases` folder with all the conversation jsons.
 
 ## Directory Structure
 
 ```
-cline-repo/
-├── src/
-│   ├── services/
-│   │   ├── test/
-│   │   │   ├── TestServer.ts         # Enhanced HTTP server for task execution
-│   │   │   ├── GitHelper.ts          # Git utilities for file tracking
-│   │   │   └── ...
-│   │   └── ...
-│   └── ...
-├── evals/                            # Main directory for evaluation system
-│   ├── cli/                          # CLI tool for orchestrating evaluations
-│   │   ├── src/
-│   │   │   ├── index.ts              # CLI entry point
-│   │   │   ├── commands/             # CLI commands (setup, run, report)
-│   │   │   ├── adapters/             # Benchmark adapters
-│   │   │   ├── db/                   # Database management
-│   │   │   └── utils/                # Utility functions
-│   │   ├── package.json
-│   │   └── tsconfig.json
-│   ├── diff-edits/                   # Diff editing evaluation suite
-│   │   ├── cases/                    # Test case JSON files
-│   │   ├── results/                  # Evaluation results
-│   │   ├── diff-apply/               # Diff application logic
-│   │   ├── parsing/                  # Assistant message parsing
-│   │   └── prompts/                  # System prompts
-│   ├── repositories/                 # Cloned benchmark repositories
-│   │   ├── exercism/                 # Modified Exercism (from pashpashpash/evals)
-│   │   ├── swe-bench/                # SWE-Bench repository
-│   │   ├── swelancer/                # SWELancer repository
-│   │   └── multi-swe/                # Multi-SWE-Bench repository
-│   ├── results/                      # Evaluation results storage
-│   │   ├── runs/                     # Individual run results
-│   │   └── reports/                  # Generated reports
-│   └── README.md                     # This file
-└── ...
+evals/                            # Main directory for evaluation system
+├── cli/                          # CLI tool for orchestrating evaluations
+│   └── src/
+│       ├── index.ts              # CLI entry point
+│       ├── commands/             # CLI commands (setup, run, report)
+│       ├── adapters/             # Benchmark adapters
+│       ├── db/                   # Database management
+│       └── utils/                # Utility functions
+├── diff-edits/                   # Diff editing evaluation suite
+│   ├── cases/                    # Test case JSON files
+│   ├── results/                  # Evaluation results
+│   ├── diff-apply/               # Diff application logic
+│   ├── parsing/                  # Assistant message parsing
+│   └── prompts/                  # System prompts
+├── repositories/                 # Cloned benchmark repositories
+│   └── exercism/                 # Exercism (Aider Polyglot)
+├── results/                      # Evaluation results storage
+│   ├── runs/                     # Individual run results
+│   └── reports/                  # Generated reports
+└── README.md                     # This file
 ```
 
 ## Getting Started
@@ -67,25 +51,14 @@ cline-repo/
 - VSCode with Cline extension installed
 - Git
 
-### Activation Mechanism
-
-The evaluation system uses an `evals.env` file approach to activate test mode in the Cline extension. When an evaluation is run:
-
-1. The CLI creates an `evals.env` file in the workspace directory
-2. The Cline extension activates due to the `workspaceContains:evals.env` activation event
-3. The extension detects this file and automatically enters test mode
-4. After evaluation completes, the file is automatically removed
-
-This approach eliminates the need for environment variables during the build process and allows for targeted activation only when needed for evaluations. The extension remains dormant during normal use, only activating when an evals.env file is present. For more details, see [Evals Env Activation](./docs/evals-env-activation.md).
-
 ### Installation
 
 1. Build the CLI tool:
 
 ```bash
-cd evals/cli
+cd evals
 npm install
-npm run build
+npm run build:cli
 ```
 
 ### Usage
@@ -106,13 +79,14 @@ node dist/index.js setup --benchmarks exercism
 #### Running Evaluations
 
 ```bash
-node dist/index.js run --model claude-3-opus-20240229 --benchmark exercism
+node dist/index.js run --benchmark exercism --count 10
 ```
 
 Options:
-- `--model`: The model to evaluate (default: claude-3-opus-20240229)
-- `--benchmark`: Specific benchmark to run (default: all)
-- `--count`: Number of tasks to run (default: all)
+- `--benchmark`: Specific benchmark to run (default: exercism)
+- `--count`: Number of tasks to run (default: all available tasks)
+
+**Note:** Model selection is currently configured through the Cline CLI itself, not through evaluation flags.
 
 #### Generating Reports
 
@@ -124,24 +98,11 @@ Options:
 - `--format`: Report format (json, markdown) (default: markdown)
 - `--output`: Output path for the report
 
-#### Managing Test Mode Activation
-
-The CLI provides a command to manually manage the evals.env file for test mode activation:
-
-```bash
-node dist/index.js evals-env create  # Create evals.env file in current directory
-node dist/index.js evals-env remove  # Remove evals.env file from current directory
-node dist/index.js evals-env check   # Check if evals.env file exists in current directory
-```
-
-Options:
-- `--directory`: Specify a directory other than the current one
-
 ## Benchmarks
 
 ### Exercism
 
-Modified Exercism exercises from the [pashpashpash/evals](https://github.com/pashpashpash/evals) repository. These are small, focused programming exercises in various languages.
+Modified Exercism exercises from the [polyglot-benchmark](https://github.com/Aider-AI/polyglot-benchmark) repository. These are small, focused programming exercises in various languages.
 
 ### SWE-Bench (Coming Soon)
 
@@ -350,7 +311,8 @@ The evaluation system collects the following metrics:
 - **Duration**: Time taken to complete tasks
 - **Tool Usage**: Number of tool calls and failures
 - **Success Rate**: Percentage of tasks completed successfully
-- **Functional Correctness**: Percentage of tests passed
+- **Test Success Rate**: Percentage of tests passed
+- **Functional Correctness**: Ratio of tests passed to total tests
 
 ## Reports
 

evals/cli/src/adapters/exercism.ts

@@ -1,6 +1,7 @@
-import * as path from "path"
-import * as fs from "fs"
+import chalk from "chalk"
 import execa from "execa"
+import * as fs from "fs"
+import * as path from "path"
 import { BenchmarkAdapter, Task, VerificationResult } from "./types"
 
 const EVALS_DIR = path.resolve(__dirname, "../../../")
@@ -20,8 +21,12 @@ export class ExercismAdapter implements BenchmarkAdapter {
 
 		if (!fs.existsSync(exercismDir)) {
 			console.log(`Cloning Exercism repository to ${exercismDir}...`)
-			await execa("git", ["clone", "https://github.com/pashpashpash/evals.git", exercismDir])
+			await execa("git", ["clone", "https://github.com/Aider-AI/polyglot-benchmark.git", exercismDir])
 			console.log("Exercism repository cloned successfully")
+
+			// Unskip all JavaScript and Java tests after cloning
+			this.unskipAllJavaScriptTests(exercismDir)
+			this.unskipAllJavaTests(exercismDir)
 		} else {
 			console.log(`Exercism repository already exists at ${exercismDir}`)
 
@@ -29,6 +34,10 @@ export class ExercismAdapter implements BenchmarkAdapter {
 			console.log("Pulling latest changes...")
 			await execa("git", ["pull"], { cwd: exercismDir })
 			console.log("Repository updated successfully")
+
+			// Unskip tests again after pulling
+			this.unskipAllJavaScriptTests(exercismDir)
+			this.unskipAllJavaTests(exercismDir)
 		}
 	}
 
@@ -51,7 +60,7 @@ export class ExercismAdapter implements BenchmarkAdapter {
 			.filter((dir) => !dir.startsWith(".") && !["node_modules", ".git"].includes(dir))
 
 		for (const language of languages) {
-			const languageDir = path.join(exercisesDir, language)
+			const languageDir = path.join(exercisesDir, language, "exercises", "practice")
 
 			// Read exercise directories
 			const exercises = fs.readdirSync(languageDir).filter((dir) => fs.statSync(path.join(languageDir, dir)).isDirectory())
@@ -61,7 +70,7 @@ export class ExercismAdapter implements BenchmarkAdapter {
 
 				// Read instructions
 				let description = ""
-				const instructionsPath = path.join(exerciseDir, "docs", "instructions.md")
+				const instructionsPath = path.join(exerciseDir, ".docs", "instructions.md")
 				if (fs.existsSync(instructionsPath)) {
 					description = fs.readFileSync(instructionsPath, "utf-8")
 				}
@@ -69,20 +78,23 @@ export class ExercismAdapter implements BenchmarkAdapter {
 				// Determine test commands based on language
 				let testCommands: string[] = []
 				switch (language) {
+					case "cpp":
+						testCommands = ["cmake -DEXERCISM_RUN_ALL_TESTS=1 .", "make"]
+						break
 					case "javascript":
-						testCommands = ["npm install", "npm test"]
+						testCommands = ["npm install", "npm test -- --testNamePattern=."]
 						break
 					case "python":
-						testCommands = ["python -m pytest -o markers=task *_test.py"]
+						testCommands = ["python3 -m pytest -o markers=task *_test.py"]
 						break
 					case "go":
-						testCommands = ["go test"]
+						testCommands = ["GOWORK=off go test -v"]
 						break
 					case "java":
 						testCommands = ["./gradlew test"]
 						break
 					case "rust":
-						testCommands = ["cargo test"]
+						testCommands = ["cargo test -- --include-ignored"]
 						break
 					default:
 						testCommands = []
@@ -118,53 +130,117 @@ export class ExercismAdapter implements BenchmarkAdapter {
 			throw new Error(`Task ${taskId} not found`)
 		}
 
-		// Check if Git repository is already initialized
-		const gitDirExists = fs.existsSync(path.join(task.workspacePath, ".git"))
+		// Create temp directory outside workspace for hiding files
+		const tempDir = path.join(EVALS_DIR, "temp-files", task.id)
+		fs.mkdirSync(tempDir, { recursive: true })
 
-		try {
-			// Initialize Git repository if needed
-			if (!gitDirExists) {
-				await execa("git", ["init"], { cwd: task.workspacePath })
-			}
+		// Read config.json to get solution and test files
+		const configPath = path.join(task.workspacePath, ".meta", "config.json")
+		let config: any = { files: { solution: [], test: [] } }
 
-			// Create a dummy file to ensure there's something to commit
-			const dummyFilePath = path.join(task.workspacePath, ".eval-timestamp")
-			fs.writeFileSync(dummyFilePath, new Date().toISOString())
-
-			// Add all files and commit
-			await execa("git", ["add", "."], { cwd: task.workspacePath })
-
-			try {
-				await execa("git", ["commit", "-m", "Initial commit"], { cwd: task.workspacePath })
-			} catch (error: any) {
-				// If commit fails because there are no changes, that's okay
-				if (!error.stderr?.includes("nothing to commit")) {
-					throw error
-				}
-			}
-		} catch (error: any) {
-			console.warn(`Warning: Git operations failed: ${error.message}`)
-			console.warn("Continuing without Git initialization")
+		if (fs.existsSync(configPath)) {
+			config = JSON.parse(fs.readFileSync(configPath, "utf-8"))
 		}
 
-		return task
+		// Build enhanced description with instructions
+		let description = ""
+		const instructionsPath = path.join(task.workspacePath, ".docs", "instructions.md")
+		const appendPath = path.join(task.workspacePath, ".docs", "instructions.append.md")
+
+		if (fs.existsSync(instructionsPath)) {
+			description = fs.readFileSync(instructionsPath, "utf-8")
+		}
+
+		if (fs.existsSync(appendPath)) {
+			description += "\n\n" + fs.readFileSync(appendPath, "utf-8")
+		}
+
+		// Add solution files constraint to description
+		const solutionFiles = config.files.solution || []
+		const fileList = solutionFiles.join(", ")
+		description += `\n\nUse the above instructions to modify the supplied files: ${fileList}. Don't change the names of existing functions or classes, as they may be referenced from other code like unit tests, etc. Only use standard libraries, don't suggest installing any packages.`
+		description +=
+			" You should ignore all test or test related files in this directory. The final test file has been removed and will be used to evaluate your work after your implementation is complete. Think deeply about the problem prior to working on the implementation. Consider all edge cases and test your solution prior to finalizing."
+
+		// Move test files to temp directory
+		if (config.files.test) {
+			config.files.test.forEach((testFile: string) => {
+				const src = path.join(task.workspacePath, testFile)
+				if (fs.existsSync(src)) {
+					const dest = path.join(tempDir, testFile)
+					fs.mkdirSync(path.dirname(dest), { recursive: true })
+					fs.renameSync(src, dest)
+				}
+			})
+		}
+
+		// Move all dot directories (except .git) to temp directory
+		const items = fs.readdirSync(task.workspacePath)
+		items.forEach((item) => {
+			if (item.startsWith(".") && item !== ".git") {
+				const src = path.join(task.workspacePath, item)
+				const stat = fs.statSync(src)
+				if (stat.isDirectory()) {
+					const dest = path.join(tempDir, item)
+					fs.renameSync(src, dest)
+				}
+			}
+		})
+
+		return {
+			...task,
+			description,
+			metadata: {
+				...task.metadata,
+				solutionFiles,
+				tempDir,
+				config,
+			},
+		}
 	}
 
 	/**
-	 * Verify the result of a task execution
+	 * Cleanup after task execution (restores hidden files from temp directory)
 	 * @param task The task that was executed
-	 * @param result The result of the task execution
 	 */
-	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
+	async cleanupTask(task: Task): Promise<void> {
+		const tempDir = path.join(EVALS_DIR, "temp-files", task.id)
+
+		if (fs.existsSync(tempDir)) {
+			const items = fs.readdirSync(tempDir)
+			items.forEach((item) => {
+				const src = path.join(tempDir, item)
+				const dest = path.join(task.workspacePath, item)
+				// Only move if destination doesn't exist (keeps newer test artifacts like .pytest_cache)
+				if (!fs.existsSync(dest)) {
+					fs.renameSync(src, dest)
+				}
+			})
+
+			// Clean up temp directory
+			fs.rmSync(tempDir, { recursive: true, force: true })
+		}
+	}
+
+	/**
+	 * Verify the result of a task execution by running tests
+	 * @param task The task that was executed
+	 */
+	async verifyResult(task: Task): Promise<VerificationResult> {
 		// Run verification commands
 		let success = true
 		let output = ""
 
 		for (const command of task.verificationCommands) {
 			try {
-				const [cmd, ...args] = command.split(" ")
-				const { stdout } = await execa(cmd, args, { cwd: task.workspacePath })
+				const { stdout, stderr } = await execa(command, {
+					cwd: task.workspacePath,
+					shell: true,
+				})
 				output += stdout + "\n"
+				if (stderr) {
+					output += stderr + "\n"
+				}
 			} catch (error: any) {
 				success = false
 				if (error.stdout) {
@@ -176,13 +252,92 @@ export class ExercismAdapter implements BenchmarkAdapter {
 			}
 		}
 
-		// Parse test results
-		const testsPassed = (output.match(/PASS/g) || []).length
-		const testsFailed = (output.match(/FAIL/g) || []).length
+		// Log the raw output
+		// console.log("\n=== TEST OUTPUT START ===")
+		// console.log(output)
+		// console.log("=== TEST OUTPUT END ===\n")
+
+		// Parse test results based on language
+		const language = task.metadata.language
+		let testsPassed = 0
+		let testsFailed = 0
+
+		switch (language) {
+			case "python":
+				const pyPassMatch = output.match(/(\d+) passed/)
+				const pyFailMatch = output.match(/(\d+) failed/)
+				testsPassed = pyPassMatch ? parseInt(pyPassMatch[1]) : 0
+				testsFailed = pyFailMatch ? parseInt(pyFailMatch[1]) : 0
+				break
+
+			case "javascript":
+				const jestMatch = output.match(/Tests:\s+(?:\d+ skipped,\s+)?(\d+) passed(?:,\s+(\d+) failed)?/)
+				if (jestMatch) {
+					testsPassed = parseInt(jestMatch[1])
+					testsFailed = jestMatch[2] ? parseInt(jestMatch[2]) : 0
+				} else {
+					// Fallback to counting test suites
+					testsPassed = (output.match(/PASS/g) || []).length
+					testsFailed = (output.match(/FAIL/g) || []).length
+				}
+				break
+
+			case "go":
+				// This incorrectly counts the parent, but minor and doesn't affect final boolean metric
+				testsPassed = (output.match(/--- PASS:/g) || []).length
+				testsFailed = (output.match(/--- FAIL:/g) || []).length
+				break
+
+			case "rust":
+				// Rust runs multiple test suites (unit, integration, doc tests)
+				// Sum results across all test result lines
+				const resultLines = output.match(/test result:.*?(\d+) passed; (\d+) failed/g)
+				if (resultLines) {
+					testsPassed = 0
+					testsFailed = 0
+					for (const line of resultLines) {
+						const match = line.match(/(\d+) passed; (\d+) failed/)
+						if (match) {
+							testsPassed += parseInt(match[1])
+							testsFailed += parseInt(match[2])
+						}
+					}
+				}
+				break
+
+			case "java":
+				testsPassed = (output.match(/PASSED/g) || []).length
+				testsFailed = (output.match(/FAILED/g) || []).length
+				break
+
+			case "cpp":
+				const cppAllPassedMatch = output.match(/All tests passed \(.*?(\d+) test cases?\)/)
+				const cppTestCasesMatch = output.match(/test cases?: (\d+) \| (\d+) passed/)
+				const cppFailedMatch = output.match(/(\d+) failed/)
+
+				if (cppAllPassedMatch) {
+					// All tests passed - extract total test cases
+					testsPassed = parseInt(cppAllPassedMatch[1])
+					testsFailed = 0
+				} else if (cppTestCasesMatch) {
+					// Mixed results - extract passed count and calculate failed
+					const totalTests = parseInt(cppTestCasesMatch[1])
+					testsPassed = parseInt(cppTestCasesMatch[2])
+					testsFailed = cppFailedMatch ? parseInt(cppFailedMatch[1]) : totalTests - testsPassed
+				}
+				break
+
+			default:
+				// Fallback to generic PASS/FAIL counting
+				testsPassed = (output.match(/PASS/g) || []).length
+				testsFailed = (output.match(/FAIL/g) || []).length
+		}
+
 		const testsTotal = testsPassed + testsFailed
 
 		return {
 			success,
+			rawOutput: output,
 			metrics: {
 				testsPassed,
 				testsFailed,
@@ -191,4 +346,280 @@ export class ExercismAdapter implements BenchmarkAdapter {
 			},
 		}
 	}
+
+	/**
+	 * Hide test files by moving them to temp directory
+	 * @param task The task to hide test files for
+	 */
+	private hideTestFiles(task: Task): void {
+		const tempDir = task.metadata.tempDir
+		const config = task.metadata.config
+
+		if (config?.files?.test) {
+			config.files.test.forEach((testFile: string) => {
+				const src = path.join(task.workspacePath, testFile)
+				if (fs.existsSync(src)) {
+					const dest = path.join(tempDir, testFile)
+					fs.mkdirSync(path.dirname(dest), { recursive: true })
+					fs.renameSync(src, dest)
+				}
+			})
+		}
+
+		// Hide dot directories again (except .git)
+		const items = fs.readdirSync(task.workspacePath)
+		items.forEach((item) => {
+			if (item.startsWith(".") && item !== ".git") {
+				const src = path.join(task.workspacePath, item)
+				if (fs.existsSync(src)) {
+					const stat = fs.statSync(src)
+					if (stat.isDirectory()) {
+						const dest = path.join(tempDir, item)
+						if (!fs.existsSync(dest)) {
+							fs.renameSync(src, dest)
+						}
+					}
+				}
+			}
+		})
+	}
+
+	/**
+	 * Restore test files by moving them from temp directory
+	 * @param task The task to restore test files for
+	 */
+	private restoreTestFiles(task: Task): void {
+		const tempDir = task.metadata.tempDir
+		const config = task.metadata.config
+
+		if (config?.files?.test) {
+			config.files.test.forEach((testFile: string) => {
+				const src = path.join(tempDir, testFile)
+				if (fs.existsSync(src)) {
+					const dest = path.join(task.workspacePath, testFile)
+					fs.mkdirSync(path.dirname(dest), { recursive: true })
+					fs.renameSync(src, dest)
+				}
+			})
+		}
+
+		// Restore dot directories (except .git)
+		if (fs.existsSync(tempDir)) {
+			const items = fs.readdirSync(tempDir)
+			items.forEach((item) => {
+				if (item.startsWith(".") && item !== ".git") {
+					const src = path.join(tempDir, item)
+					const dest = path.join(task.workspacePath, item)
+					if (fs.existsSync(src) && !fs.existsSync(dest)) {
+						fs.renameSync(src, dest)
+					}
+				}
+			})
+		}
+	}
+
+	/**
+	 * Builds retry message with test errors and fix instructions
+	 * @param testOutput The raw test output showing errors
+	 * @param solutionFiles List of solution files to fix
+	 * @returns Formatted retry message
+	 */
+	private buildRetryMessage(testOutput: string, solutionFiles: string[]): string {
+		const fileList = solutionFiles.join(", ")
+		return `${testOutput}\n\nSee the testing errors above. The tests are correct, don't try and change them. Fix the code in ${fileList} to resolve the errors.`
+	}
+
+	/**
+	 * Unskip all JavaScript tests in the repository by replacing xtest with test
+	 * @param repoPath Path to the exercism repository
+	 */
+	private unskipAllJavaScriptTests(repoPath: string): void {
+		const jsDir = path.join(repoPath, "javascript", "exercises", "practice")
+
+		if (!fs.existsSync(jsDir)) {
+			console.log("JavaScript exercises directory not found, skipping test unskipping")
+			return
+		}
+
+		// Walk through all exercise directories
+		const exercises = fs.readdirSync(jsDir).filter((dir) => {
+			const fullPath = path.join(jsDir, dir)
+			return fs.statSync(fullPath).isDirectory()
+		})
+
+		let filesModified = 0
+		for (const exercise of exercises) {
+			const exerciseDir = path.join(jsDir, exercise)
+
+			// Find all .spec.js files
+			const files = fs.readdirSync(exerciseDir).filter((file) => file.endsWith(".spec.js"))
+
+			for (const file of files) {
+				const filePath = path.join(exerciseDir, file)
+				let content = fs.readFileSync(filePath, "utf-8")
+				const originalContent = content
+
+				// Replace xtest with test to unskip tests
+				content = content.replace(/xtest\(/g, "test(")
+
+				if (content !== originalContent) {
+					fs.writeFileSync(filePath, content)
+					filesModified++
+				}
+			}
+		}
+
+		console.log(`Unskipped tests in ${filesModified} JavaScript test files`)
+	}
+
+	/**
+	 * Unskip all Java tests in the repository by removing @Disabled annotations
+	 * @param repoPath Path to the exercism repository
+	 */
+	private unskipAllJavaTests(repoPath: string): void {
+		const javaDir = path.join(repoPath, "java", "exercises", "practice")
+
+		if (!fs.existsSync(javaDir)) {
+			console.log("Java exercises directory not found, skipping test unskipping")
+			return
+		}
+
+		// Walk through all exercise directories
+		const exercises = fs.readdirSync(javaDir).filter((dir) => {
+			const fullPath = path.join(javaDir, dir)
+			return fs.statSync(fullPath).isDirectory()
+		})
+
+		let filesModified = 0
+		for (const exercise of exercises) {
+			const testDir = path.join(javaDir, exercise, "src", "test", "java")
+
+			if (!fs.existsSync(testDir)) {
+				continue
+			}
+
+			// Find all .java test files
+			const files = fs.readdirSync(testDir).filter((file) => file.endsWith(".java"))
+
+			for (const file of files) {
+				const filePath = path.join(testDir, file)
+				let content = fs.readFileSync(filePath, "utf-8")
+				const originalContent = content
+
+				// Remove @Disabled("Remove to run test") annotations
+				content = content.replace(/@Disabled\("Remove to run test"\)\s*\n/g, "")
+
+				if (content !== originalContent) {
+					fs.writeFileSync(filePath, content)
+					filesModified++
+				}
+			}
+		}
+
+		console.log(`Unskipped tests in ${filesModified} Java test files`)
+	}
+
+	/**
+	 * Runs a Cline task with automatic retry on test failure
+	 * Creates a new Cline instance, runs the task, verifies with tests,
+	 * and retries once if tests fail
+	 * @param task The task to execute
+	 * @returns The final verification result, or null
+	 */
+	async runTask(task: Task): Promise<VerificationResult | null> {
+		const startTime = Date.now()
+		let instanceAddress: string | null = null
+		let attempts = 0
+		let finalVerification: VerificationResult | null = null
+
+		try {
+			// Step 1: Start a new Cline instance in the working directory
+			const instanceResult = await execa("cline", ["instance", "new"], {
+				cwd: task.workspacePath,
+				stdin: "ignore",
+			})
+
+			// Step 2: Parse the instance address from output
+			const addressMatch = instanceResult.stdout.match(/Address:\s*([\d.]+:\d+)/)
+			if (!addressMatch) {
+				throw new Error("Failed to parse instance address from output")
+			}
+			instanceAddress = addressMatch[1]
+
+			// Step 3: Create the initial task on this specific instance
+			await execa("cline", ["task", "new", "--yolo", "--address", instanceAddress, task.description], {
+				cwd: task.workspacePath,
+				stdin: "ignore",
+			})
+
+			// Step 4: Wait for initial implementation to complete
+			console.log(chalk.blue(`Waiting for first attempt to complete...`))
+			await execa("cline", ["task", "view", "--follow-complete", "--address", instanceAddress], {
+				cwd: task.workspacePath,
+				stdin: "ignore",
+			})
+
+			// Step 5: Run first test attempt
+			console.log(chalk.blue(`Running tests (attempt 1)...`))
+			this.restoreTestFiles(task)
+			attempts = 1
+			const firstVerification = await this.verifyResult(task)
+			finalVerification = firstVerification
+
+			// Step 6: Retry if tests failed
+			if (!firstVerification.success) {
+				console.log(chalk.blue(`Tests failed on first attempt. Retrying...`))
+
+				// Hide test files again for retry
+				this.hideTestFiles(task)
+
+				attempts = 2
+				const solutionFiles = task.metadata.solutionFiles || []
+				const retryMessage = this.buildRetryMessage(firstVerification.rawOutput || "", solutionFiles)
+
+				// Send retry task message
+				await execa("cline", ["task", "send", "--yolo", "--address", instanceAddress], {
+					cwd: task.workspacePath,
+					input: retryMessage,
+				})
+
+				// Follow retry until complete
+				await execa("cline", ["task", "view", "--follow-complete", "--address", instanceAddress], {
+					cwd: task.workspacePath,
+					stdin: "ignore",
+				})
+
+				// Run second test attempt (final)
+				console.log(chalk.blue(`Running tests (attempt 2)...`))
+				this.restoreTestFiles(task)
+				const secondVerification = await this.verifyResult(task)
+				finalVerification = secondVerification
+			}
+
+			const duration = Date.now() - startTime
+			console.log(
+				chalk.green(
+					`Task completed in ${(duration / 1000).toFixed(1)}s after ${attempts} attempt${attempts > 1 ? "s" : ""}`,
+				),
+			)
+
+			return finalVerification
+		} catch (error: any) {
+			const duration = Date.now() - startTime
+			console.error(chalk.red(`Task failed after ${(duration / 1000).toFixed(1)}s: ${error.message}`))
+
+			return finalVerification
+		} finally {
+			// Step 7: Always clean up the instance, even if task failed
+			if (instanceAddress) {
+				try {
+					await execa("cline", ["instance", "kill", instanceAddress], {
+						stdin: "ignore",
+					})
+				} catch (cleanupError: any) {
+					console.error(chalk.yellow(`Warning: Failed to kill instance ${instanceAddress}: ${cleanupError.message}`))
+				}
+			}
+		}
+	}
 }

evals/cli/src/adapters/index.ts

@@ -1,18 +1,9 @@
-import { BenchmarkAdapter } from "./types"
 import { ExercismAdapter } from "./exercism"
-import { SWEBenchAdapter } from "./swe-bench"
-import { SWELancerAdapter } from "./swelancer"
-import { MultiSWEAdapter } from "./multi-swe"
+import { BenchmarkAdapter } from "./types"
 
 // Registry of all available adapters
 const adapters: Record<string, BenchmarkAdapter> = {
-	// Exercism is the primary adapter with real implementation
 	exercism: new ExercismAdapter(),
-
-	// Dummy adapters for testing
-	"swe-bench": new SWEBenchAdapter(),
-	swelancer: new SWELancerAdapter(),
-	"multi-swe": new MultiSWEAdapter(),
 }
 
 /**

evals/cli/src/adapters/multi-swe.ts

@@ -1,192 +0,0 @@
-import * as path from "path"
-import * as fs from "fs"
-import execa from "execa"
-import { BenchmarkAdapter, Task, VerificationResult } from "./types"
-
-const EVALS_DIR = path.resolve(__dirname, "../../../")
-
-/**
- * Dummy adapter for the Multi-SWE-Bench benchmark
- */
-export class MultiSWEAdapter implements BenchmarkAdapter {
-	name = "multi-swe"
-
-	/**
-	 * Set up the Multi-SWE-Bench benchmark repository (dummy implementation)
-	 */
-	async setup(): Promise<void> {
-		console.log("Multi-SWE-Bench dummy setup completed")
-
-		// Create repositories directory if it doesn't exist
-		const repoDir = path.join(EVALS_DIR, "repositories", "multi-swe")
-		if (!fs.existsSync(repoDir)) {
-			fs.mkdirSync(repoDir, { recursive: true })
-			console.log(`Created dummy Multi-SWE-Bench directory at ${repoDir}`)
-		}
-	}
-
-	/**
-	 * List all available tasks in the Multi-SWE-Bench benchmark (dummy implementation)
-	 */
-	async listTasks(): Promise<Task[]> {
-		return [
-			{
-				id: "multi-swe-task-1",
-				name: "Multi-Language API Integration",
-				description:
-					"Implement a system that integrates a Python backend with a TypeScript frontend and a Rust processing service.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "multi-swe"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					languages: ["python", "typescript", "rust"],
-					complexity: "high",
-					type: "multi-swe",
-				},
-			},
-			{
-				id: "multi-swe-task-2",
-				name: "Cross-Platform Mobile App",
-				description: "Create a cross-platform mobile app using React Native with native modules in Swift and Kotlin.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "multi-swe"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					languages: ["javascript", "swift", "kotlin"],
-					complexity: "medium",
-					type: "multi-swe",
-				},
-			},
-			{
-				id: "multi-swe-task-3",
-				name: "Microservice Architecture",
-				description: "Design and implement a microservice architecture with services written in Go, Node.js, and Java.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "multi-swe"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					languages: ["go", "javascript", "java"],
-					complexity: "high",
-					type: "multi-swe",
-				},
-			},
-		]
-	}
-
-	/**
-	 * Prepare a specific task for execution (dummy implementation)
-	 * @param taskId The ID of the task to prepare
-	 */
-	async prepareTask(taskId: string): Promise<Task> {
-		const tasks = await this.listTasks()
-		const task = tasks.find((t) => t.id === taskId)
-
-		if (!task) {
-			throw new Error(`Task ${taskId} not found`)
-		}
-
-		// Create a dummy workspace for the task
-		const taskDir = path.join(task.workspacePath, taskId)
-		if (!fs.existsSync(taskDir)) {
-			fs.mkdirSync(taskDir, { recursive: true })
-
-			// Create a dummy file for the task
-			fs.writeFileSync(
-				path.join(taskDir, "README.md"),
-				`# ${task.name}\n\n${task.description}\n\nThis is a dummy task for testing purposes.`,
-			)
-
-			// Create additional dummy files based on task type
-			if (task.id === "multi-swe-task-1") {
-				// Python backend
-				fs.mkdirSync(path.join(taskDir, "backend"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "backend", "app.py"),
-					`# TODO: Implement Python backend\nfrom flask import Flask\n\napp = Flask(__name__)\n\n@app.route('/')\ndef hello():\n    return "Hello, World!"\n`,
-				)
-
-				// TypeScript frontend
-				fs.mkdirSync(path.join(taskDir, "frontend"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "frontend", "app.ts"),
-					`// TODO: Implement TypeScript frontend\nconsole.log('Frontend starting...');\n`,
-				)
-
-				// Rust processing service
-				fs.mkdirSync(path.join(taskDir, "processor"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "processor", "main.rs"),
-					`// TODO: Implement Rust processing service\nfn main() {\n    println!("Processor starting...");\n}\n`,
-				)
-			} else if (task.id === "multi-swe-task-2") {
-				// React Native app
-				fs.mkdirSync(path.join(taskDir, "app"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "app", "App.js"),
-					`// TODO: Implement React Native app\nimport React from 'react';\nimport { View, Text } from 'react-native';\n\nexport default function App() {\n  return (\n    <View>\n      <Text>Hello, World!</Text>\n    </View>\n  );\n}\n`,
-				)
-
-				// Swift native module
-				fs.mkdirSync(path.join(taskDir, "ios"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "ios", "NativeModule.swift"),
-					`// TODO: Implement Swift native module\nimport Foundation\n\n@objc(NativeModule)\nclass NativeModule: NSObject {\n  @objc\n  func hello() -> String {\n    return "Hello from Swift"\n  }\n}\n`,
-				)
-
-				// Kotlin native module
-				fs.mkdirSync(path.join(taskDir, "android"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "android", "NativeModule.kt"),
-					`// TODO: Implement Kotlin native module\npackage com.example.app\n\nclass NativeModule {\n  fun hello(): String {\n    return "Hello from Kotlin"\n  }\n}\n`,
-				)
-			} else if (task.id === "multi-swe-task-3") {
-				// Go service
-				fs.mkdirSync(path.join(taskDir, "service-go"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "service-go", "main.go"),
-					`// TODO: Implement Go service\npackage main\n\nimport "fmt"\n\nfunc main() {\n\tfmt.Println("Go service starting...")\n}\n`,
-				)
-
-				// Node.js service
-				fs.mkdirSync(path.join(taskDir, "service-node"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "service-node", "server.js"),
-					`// TODO: Implement Node.js service\nconsole.log('Node.js service starting...');\n`,
-				)
-
-				// Java service
-				fs.mkdirSync(path.join(taskDir, "service-java"), { recursive: true })
-				fs.writeFileSync(
-					path.join(taskDir, "service-java", "Main.java"),
-					`// TODO: Implement Java service\npublic class Main {\n    public static void main(String[] args) {\n        System.out.println("Java service starting...");\n    }\n}\n`,
-				)
-			}
-		}
-
-		// Update the task's workspace path to the task-specific directory
-		return {
-			...task,
-			workspacePath: taskDir,
-		}
-	}
-
-	/**
-	 * Verify the result of a task execution (dummy implementation)
-	 * @param task The task that was executed
-	 * @param result The result of the task execution
-	 */
-	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
-		// Always return success for dummy implementation
-		return {
-			success: true,
-			metrics: {
-				testsPassed: 1,
-				testsFailed: 0,
-				testsTotal: 1,
-				functionalCorrectness: 1.0,
-				crossLanguageIntegration: 0.9, // Dummy metric specific to Multi-SWE
-				architectureQuality: 0.85, // Dummy metric specific to Multi-SWE
-			},
-		}
-	}
-}

evals/cli/src/adapters/swe-bench.ts

@@ -1,125 +0,0 @@
-import * as path from "path"
-import * as fs from "fs"
-import execa from "execa"
-import { BenchmarkAdapter, Task, VerificationResult } from "./types"
-
-const EVALS_DIR = path.resolve(__dirname, "../../../")
-
-/**
- * Dummy adapter for the SWE-Bench benchmark
- */
-export class SWEBenchAdapter implements BenchmarkAdapter {
-	name = "swe-bench"
-
-	/**
-	 * Set up the SWE-Bench benchmark repository (dummy implementation)
-	 */
-	async setup(): Promise<void> {
-		console.log("SWE-Bench dummy setup completed")
-
-		// Create repositories directory if it doesn't exist
-		const repoDir = path.join(EVALS_DIR, "repositories", "swe-bench")
-		if (!fs.existsSync(repoDir)) {
-			fs.mkdirSync(repoDir, { recursive: true })
-			console.log(`Created dummy SWE-Bench directory at ${repoDir}`)
-		}
-	}
-
-	/**
-	 * List all available tasks in the SWE-Bench benchmark (dummy implementation)
-	 */
-	async listTasks(): Promise<Task[]> {
-		return [
-			{
-				id: "swe-bench-task-1",
-				name: "Fix React Component Bug",
-				description: "Fix a bug in a React component where the state is not properly updated.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "swe-bench"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					repository: "facebook/react",
-					issue: "#12345",
-					type: "swe-bench",
-				},
-			},
-			{
-				id: "swe-bench-task-2",
-				name: "Optimize Database Query",
-				description: "Optimize a slow database query in a Django application.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "swe-bench"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					repository: "django/django",
-					issue: "#6789",
-					type: "swe-bench",
-				},
-			},
-			{
-				id: "swe-bench-task-3",
-				name: "Fix Memory Leak",
-				description: "Fix a memory leak in a Node.js application.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "swe-bench"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					repository: "nodejs/node",
-					issue: "#9876",
-					type: "swe-bench",
-				},
-			},
-		]
-	}
-
-	/**
-	 * Prepare a specific task for execution (dummy implementation)
-	 * @param taskId The ID of the task to prepare
-	 */
-	async prepareTask(taskId: string): Promise<Task> {
-		const tasks = await this.listTasks()
-		const task = tasks.find((t) => t.id === taskId)
-
-		if (!task) {
-			throw new Error(`Task ${taskId} not found`)
-		}
-
-		// Create a dummy workspace for the task
-		const taskDir = path.join(task.workspacePath, taskId)
-		if (!fs.existsSync(taskDir)) {
-			fs.mkdirSync(taskDir, { recursive: true })
-
-			// Create a dummy file for the task
-			fs.writeFileSync(
-				path.join(taskDir, "README.md"),
-				`# ${task.name}\n\n${task.description}\n\nThis is a dummy task for testing purposes.`,
-			)
-		}
-
-		// Update the task's workspace path to the task-specific directory
-		return {
-			...task,
-			workspacePath: taskDir,
-		}
-	}
-
-	/**
-	 * Verify the result of a task execution (dummy implementation)
-	 * @param task The task that was executed
-	 * @param result The result of the task execution
-	 */
-	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
-		// Always return success for dummy implementation
-		return {
-			success: true,
-			metrics: {
-				testsPassed: 1,
-				testsFailed: 0,
-				testsTotal: 1,
-				functionalCorrectness: 1.0,
-				performanceImprovement: 0.25, // Dummy metric specific to SWE-Bench
-				codeQuality: 0.9, // Dummy metric specific to SWE-Bench
-			},
-		}
-	}
-}

evals/cli/src/adapters/swelancer.ts

@@ -1,143 +0,0 @@
-import * as path from "path"
-import * as fs from "fs"
-import execa from "execa"
-import { BenchmarkAdapter, Task, VerificationResult } from "./types"
-
-const EVALS_DIR = path.resolve(__dirname, "../../../")
-
-/**
- * Dummy adapter for the SWELancer benchmark
- */
-export class SWELancerAdapter implements BenchmarkAdapter {
-	name = "swelancer"
-
-	/**
-	 * Set up the SWELancer benchmark repository (dummy implementation)
-	 */
-	async setup(): Promise<void> {
-		console.log("SWELancer dummy setup completed")
-
-		// Create repositories directory if it doesn't exist
-		const repoDir = path.join(EVALS_DIR, "repositories", "swelancer")
-		if (!fs.existsSync(repoDir)) {
-			fs.mkdirSync(repoDir, { recursive: true })
-			console.log(`Created dummy SWELancer directory at ${repoDir}`)
-		}
-	}
-
-	/**
-	 * List all available tasks in the SWELancer benchmark (dummy implementation)
-	 */
-	async listTasks(): Promise<Task[]> {
-		return [
-			{
-				id: "swelancer-task-1",
-				name: "Create Landing Page",
-				description: "Create a responsive landing page for a new product using HTML, CSS, and JavaScript.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "swelancer"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					client: "TechStartup Inc.",
-					difficulty: "medium",
-					type: "swelancer",
-				},
-			},
-			{
-				id: "swelancer-task-2",
-				name: "Build REST API",
-				description: "Create a RESTful API for a blog application using Node.js and Express.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "swelancer"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					client: "BlogCo",
-					difficulty: "hard",
-					type: "swelancer",
-				},
-			},
-			{
-				id: "swelancer-task-3",
-				name: "Fix CSS Layout Issues",
-				description: "Fix layout issues in a responsive website across different screen sizes.",
-				workspacePath: path.join(EVALS_DIR, "repositories", "swelancer"),
-				setupCommands: [],
-				verificationCommands: [],
-				metadata: {
-					client: "DesignAgency",
-					difficulty: "easy",
-					type: "swelancer",
-				},
-			},
-		]
-	}
-
-	/**
-	 * Prepare a specific task for execution (dummy implementation)
-	 * @param taskId The ID of the task to prepare
-	 */
-	async prepareTask(taskId: string): Promise<Task> {
-		const tasks = await this.listTasks()
-		const task = tasks.find((t) => t.id === taskId)
-
-		if (!task) {
-			throw new Error(`Task ${taskId} not found`)
-		}
-
-		// Create a dummy workspace for the task
-		const taskDir = path.join(task.workspacePath, taskId)
-		if (!fs.existsSync(taskDir)) {
-			fs.mkdirSync(taskDir, { recursive: true })
-
-			// Create a dummy file for the task
-			fs.writeFileSync(
-				path.join(taskDir, "README.md"),
-				`# ${task.name}\n\n${task.description}\n\nThis is a dummy task for testing purposes.`,
-			)
-
-			// Create additional dummy files based on task type
-			if (task.id === "swelancer-task-1") {
-				fs.writeFileSync(
-					path.join(taskDir, "index.html"),
-					`<!DOCTYPE html>\n<html>\n<head>\n  <title>Landing Page</title>\n</head>\n<body>\n  <!-- TODO: Implement landing page -->\n</body>\n</html>`,
-				)
-			} else if (task.id === "swelancer-task-2") {
-				fs.writeFileSync(
-					path.join(taskDir, "server.js"),
-					`// TODO: Implement REST API\nconsole.log('Server starting...');`,
-				)
-			} else if (task.id === "swelancer-task-3") {
-				fs.writeFileSync(
-					path.join(taskDir, "styles.css"),
-					`/* TODO: Fix layout issues */\nbody {\n  margin: 0;\n  padding: 0;\n}`,
-				)
-			}
-		}
-
-		// Update the task's workspace path to the task-specific directory
-		return {
-			...task,
-			workspacePath: taskDir,
-		}
-	}
-
-	/**
-	 * Verify the result of a task execution (dummy implementation)
-	 * @param task The task that was executed
-	 * @param result The result of the task execution
-	 */
-	async verifyResult(task: Task, result: any): Promise<VerificationResult> {
-		// Always return success for dummy implementation
-		return {
-			success: true,
-			metrics: {
-				testsPassed: 1,
-				testsFailed: 0,
-				testsTotal: 1,
-				functionalCorrectness: 1.0,
-				clientSatisfaction: 0.95, // Dummy metric specific to SWELancer
-				timeEfficiency: 0.85, // Dummy metric specific to SWELancer
-			},
-		}
-	}
-}

evals/cli/src/adapters/types.ts

@@ -17,6 +17,7 @@ export interface Task {
 export interface VerificationResult {
 	success: boolean
 	metrics: Record<string, any>
+	rawOutput?: string
 }
 
 /**
@@ -27,5 +28,7 @@ export interface BenchmarkAdapter {
 	setup(): Promise<void>
 	listTasks(): Promise<Task[]>
 	prepareTask(taskId: string): Promise<Task>
-	verifyResult(task: Task, result: any): Promise<VerificationResult>
+	cleanupTask(task: Task): Promise<void>
+	verifyResult(task: Task): Promise<VerificationResult>
+	runTask(task: Task): Promise<VerificationResult | null>
 }

evals/cli/src/commands/evals-env.ts

@@ -1,53 +0,0 @@
-import * as path from "path"
-import chalk from "chalk"
-import { createEvalsEnvFile, removeEvalsEnvFile, checkEvalsEnvFile } from "../utils/evals-env"
-
-interface EvalsEnvOptions {
-	action: "create" | "remove" | "check"
-	directory?: string
-}
-
-/**
- * Handler for the evals-env command
- * @param options Command options
- */
-export async function evalsEnvHandler(options: EvalsEnvOptions): Promise<void> {
-	// Determine the directory to use - default to repository root instead of current directory
-	const currentDir = process.cwd()
-	const repoRoot = path.resolve(currentDir, "..", "..") // Navigate up from evals/cli to root
-	const directory = options.directory || repoRoot
-
-	console.log(chalk.blue(`Working with directory: ${directory}`))
-
-	// Perform the requested action
-	switch (options.action) {
-		case "create":
-			console.log(chalk.blue("Creating evals.env file..."))
-			createEvalsEnvFile(directory)
-			console.log(chalk.green("The Cline extension should now detect this file and enter test mode."))
-			console.log(chalk.yellow("Note: You may need to reload VSCode for the changes to take effect."))
-			break
-
-		case "remove":
-			console.log(chalk.blue("Removing evals.env file..."))
-			removeEvalsEnvFile(directory)
-			console.log(chalk.green("The Cline extension should now exit test mode."))
-			console.log(chalk.yellow("Note: You may need to reload VSCode for the changes to take effect."))
-			break
-
-		case "check":
-			console.log(chalk.blue("Checking for evals.env file..."))
-			const exists = checkEvalsEnvFile(directory)
-			if (exists) {
-				console.log(chalk.green("The Cline extension should be in test mode."))
-			} else {
-				console.log(chalk.yellow("The Cline extension should not be in test mode."))
-			}
-			break
-
-		default:
-			console.error(chalk.red(`Unknown action: ${options.action}`))
-			console.log(chalk.yellow("Valid actions are: create, remove, check"))
-			break
-	}
-}

evals/cli/src/commands/report.ts

@@ -1,7 +1,7 @@
-import * as fs from "fs"
-import * as path from "path"
 import chalk from "chalk"
+import * as fs from "fs"
 import ora from "ora"
+import * as path from "path"
 import { ResultsDatabase } from "../db"
 import { generateMarkdownReport } from "../utils/markdown"
 
@@ -34,7 +34,6 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 		// Generate summary report
 		const summary = {
 			runs: runs.length,
-			models: [...new Set(runs.map((run) => run.model))],
 			benchmarks: [...new Set(runs.map((run) => run.benchmark))],
 			tasks: 0,
 			successRate: 0,
@@ -45,6 +44,10 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 			totalToolFailures: 0,
 			toolSuccessRate: 0,
 			toolUsage: {} as Record<string, { calls: number; failures: number }>,
+			totalTests: 0,
+			totalTestsPassed: 0,
+			totalTestsFailed: 0,
+			testSuccessRate: 0,
 		}
 
 		let totalTasks = 0
@@ -54,6 +57,9 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 		let totalDuration = 0
 		let totalToolCalls = 0
 		let totalToolFailures = 0
+		let totalTests = 0
+		let totalTestsPassed = 0
+		let totalTestsFailed = 0
 
 		for (const run of runs) {
 			const tasks = db.getRunTasks(run.id)
@@ -73,6 +79,14 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 				totalCost += metrics.find((m) => m.name === "cost")?.value || 0
 				totalDuration += metrics.find((m) => m.name === "duration")?.value || 0
 
+				// Collect test metrics
+				const testsPassed = metrics.find((m) => m.name === "testsPassed")?.value || 0
+				const testsFailed = metrics.find((m) => m.name === "testsFailed")?.value || 0
+				const testsTotal = metrics.find((m) => m.name === "testsTotal")?.value || 0
+				totalTestsPassed += testsPassed
+				totalTestsFailed += testsFailed
+				totalTests += testsTotal
+
 				// Collect tool call metrics
 				totalToolCalls += task.total_tool_calls || 0
 				totalToolFailures += task.total_tool_failures || 0
@@ -99,6 +113,12 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 		summary.totalToolFailures = totalToolFailures
 		summary.toolSuccessRate = totalToolCalls > 0 ? 1 - totalToolFailures / totalToolCalls : 1.0
 
+		// Calculate test metrics
+		summary.totalTests = totalTests
+		summary.totalTestsPassed = totalTestsPassed
+		summary.totalTestsFailed = totalTestsFailed
+		summary.testSuccessRate = totalTests > 0 ? totalTestsPassed / totalTests : 0
+
 		summary.tasks = totalTasks
 		summary.successRate = totalTasks > 0 ? successfulTasks / totalTasks : 0
 		summary.averageTokens = totalTasks > 0 ? totalTokens / totalTasks : 0
@@ -112,12 +132,15 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 			const benchmarkRuns = runs.filter((run) => run.benchmark === benchmark)
 			const benchmarkSummary = {
 				runs: benchmarkRuns.length,
-				models: [...new Set(benchmarkRuns.map((run) => run.model))],
 				tasks: 0,
 				successRate: 0,
 				averageTokens: 0,
 				averageCost: 0,
 				averageDuration: 0,
+				totalTests: 0,
+				totalTestsPassed: 0,
+				totalTestsFailed: 0,
+				testSuccessRate: 0,
 			}
 
 			let benchmarkTasks = 0
@@ -125,6 +148,9 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 			let benchmarkTotalTokens = 0
 			let benchmarkTotalCost = 0
 			let benchmarkTotalDuration = 0
+			let benchmarkTotalTests = 0
+			let benchmarkTotalTestsPassed = 0
+			let benchmarkTotalTestsFailed = 0
 
 			for (const run of benchmarkRuns) {
 				const tasks = db.getRunTasks(run.id)
@@ -143,6 +169,14 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 
 					benchmarkTotalCost += metrics.find((m) => m.name === "cost")?.value || 0
 					benchmarkTotalDuration += metrics.find((m) => m.name === "duration")?.value || 0
+
+					// Collect test metrics
+					const testsPassed = metrics.find((m) => m.name === "testsPassed")?.value || 0
+					const testsFailed = metrics.find((m) => m.name === "testsFailed")?.value || 0
+					const testsTotal = metrics.find((m) => m.name === "testsTotal")?.value || 0
+					benchmarkTotalTestsPassed += testsPassed
+					benchmarkTotalTestsFailed += testsFailed
+					benchmarkTotalTests += testsTotal
 				}
 			}
 
@@ -151,60 +185,14 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 			benchmarkSummary.averageTokens = benchmarkTasks > 0 ? benchmarkTotalTokens / benchmarkTasks : 0
 			benchmarkSummary.averageCost = benchmarkTasks > 0 ? benchmarkTotalCost / benchmarkTasks : 0
 			benchmarkSummary.averageDuration = benchmarkTasks > 0 ? benchmarkTotalDuration / benchmarkTasks : 0
+			benchmarkSummary.totalTests = benchmarkTotalTests
+			benchmarkSummary.totalTestsPassed = benchmarkTotalTestsPassed
+			benchmarkSummary.totalTestsFailed = benchmarkTotalTestsFailed
+			benchmarkSummary.testSuccessRate = benchmarkTotalTests > 0 ? benchmarkTotalTestsPassed / benchmarkTotalTests : 0
 
 			benchmarkReports[benchmark] = benchmarkSummary
 		}
 
-		// Generate model-specific reports
-		const modelReports: Record<string, any> = {}
-
-		for (const model of summary.models) {
-			const modelRuns = runs.filter((run) => run.model === model)
-			const modelSummary = {
-				runs: modelRuns.length,
-				benchmarks: [...new Set(modelRuns.map((run) => run.benchmark))],
-				tasks: 0,
-				successRate: 0,
-				averageTokens: 0,
-				averageCost: 0,
-				averageDuration: 0,
-			}
-
-			let modelTasks = 0
-			let modelSuccessfulTasks = 0
-			let modelTotalTokens = 0
-			let modelTotalCost = 0
-			let modelTotalDuration = 0
-
-			for (const run of modelRuns) {
-				const tasks = db.getRunTasks(run.id)
-				modelTasks += tasks.length
-
-				for (const task of tasks) {
-					if (task.success) {
-						modelSuccessfulTasks++
-					}
-
-					const metrics = db.getTaskMetrics(task.id)
-
-					const tokensIn = metrics.find((m) => m.name === "tokensIn")?.value || 0
-					const tokensOut = metrics.find((m) => m.name === "tokensOut")?.value || 0
-					modelTotalTokens += tokensIn + tokensOut
-
-					modelTotalCost += metrics.find((m) => m.name === "cost")?.value || 0
-					modelTotalDuration += metrics.find((m) => m.name === "duration")?.value || 0
-				}
-			}
-
-			modelSummary.tasks = modelTasks
-			modelSummary.successRate = modelTasks > 0 ? modelSuccessfulTasks / modelTasks : 0
-			modelSummary.averageTokens = modelTasks > 0 ? modelTotalTokens / modelTasks : 0
-			modelSummary.averageCost = modelTasks > 0 ? modelTotalCost / modelTasks : 0
-			modelSummary.averageDuration = modelTasks > 0 ? modelTotalDuration / modelTasks : 0
-
-			modelReports[model] = modelSummary
-		}
-
 		// Save reports
 		const reportDir = path.join(path.resolve(__dirname, "../../../"), "results", "reports")
 		fs.mkdirSync(reportDir, { recursive: true })
@@ -217,14 +205,12 @@ export async function reportHandler(options: ReportOptions): Promise<void> {
 
 			fs.writeFileSync(path.join(reportDir, `benchmarks-${timestamp}.json`), JSON.stringify(benchmarkReports, null, 2))
 
-			fs.writeFileSync(path.join(reportDir, `models-${timestamp}.json`), JSON.stringify(modelReports, null, 2))
-
 			spinner.succeed(`JSON reports generated in ${reportDir}`)
 		} else {
 			// Generate markdown report
 			const outputPath = options.output || path.join(reportDir, `report-${timestamp}.md`)
 
-			generateMarkdownReport(summary, benchmarkReports, modelReports, outputPath)
+			generateMarkdownReport(summary, benchmarkReports, outputPath)
 
 			spinner.succeed(`Markdown report generated at ${outputPath}`)
 		}

evals/cli/src/commands/run.ts

@@ -1,18 +1,13 @@
-import * as path from "path"
-import { v4 as uuidv4 } from "uuid"
 import chalk from "chalk"
 import ora from "ora"
+import { v4 as uuidv4 } from "uuid"
 import { getAdapter } from "../adapters"
 import { ResultsDatabase } from "../db"
-import { spawnVSCode, cleanupVSCode } from "../utils/vscode"
-import { sendTaskToServer } from "../utils/task"
 import { storeTaskResult } from "../utils/results"
 
 interface RunOptions {
 	benchmark?: string
-	model: string
 	count?: number
-	apiKey?: string
 }
 
 /**
@@ -21,12 +16,10 @@ interface RunOptions {
  */
 export async function runHandler(options: RunOptions): Promise<void> {
 	// Determine which benchmarks to run
-	const benchmarks = options.benchmark ? [options.benchmark] : ["exercism"] // Default to exercism for now
-	const model = options.model
+	const benchmarks = options.benchmark ? [options.benchmark] : ["exercism"] // Default to exercism
 	const count = options.count || Infinity
 
-	console.log(chalk.blue(`Running evaluations for model: ${model}`))
-	console.log(chalk.blue(`Benchmarks: ${benchmarks.join(", ")}`))
+	console.log(chalk.blue(`Running evaluations for the following benchmarks: ${benchmarks.join(", ")}`))
 
 	// Create a run for each benchmark
 	for (const benchmark of benchmarks) {
@@ -36,7 +29,7 @@ export async function runHandler(options: RunOptions): Promise<void> {
 		console.log(chalk.green(`\nStarting run for benchmark: ${benchmark}`))
 
 		// Create run in database
-		db.createRun(runId, model, benchmark)
+		db.createRun(runId, benchmark)
 
 		// Get adapter for this benchmark
 		try {
@@ -63,58 +56,47 @@ export async function runHandler(options: RunOptions): Promise<void> {
 				const preparedTask = await adapter.prepareTask(task.id)
 				prepareSpinner.succeed("Task prepared")
 
-				// Spawn VSCode
-				console.log("Spawning VSCode...")
-				await spawnVSCode(preparedTask.workspacePath)
+				let cleanedUp = false
 
-				// Send task to server
-				const sendSpinner = ora("Sending task to server...").start()
 				try {
-					const result = await sendTaskToServer(preparedTask.description, options.apiKey)
-					sendSpinner.succeed("Task completed")
+					// Run task using adapter's execution strategy
+					const finalVerification = await adapter.runTask(preparedTask)
 
-					// Verify result
-					const verifySpinner = ora("Verifying result...").start()
-					const verification = await adapter.verifyResult(preparedTask, result)
+					// Cleanup task
+					const cleanupSpinner = ora("Cleaning up task...").start()
+					await adapter.cleanupTask(preparedTask)
+					cleanedUp = true
+					cleanupSpinner.succeed("Cleanup complete")
+
+					// Use final verification from runTask
+					const verification = finalVerification || (await adapter.verifyResult(preparedTask))
 
 					if (verification.success) {
-						verifySpinner.succeed(
-							`Verification successful: ${verification.metrics.testsPassed}/${verification.metrics.testsTotal} tests passed`,
+						console.log(
+							chalk.green(`Tests passed: ${verification.metrics.testsPassed}/${verification.metrics.testsTotal}`),
 						)
 					} else {
-						verifySpinner.fail(
-							`Verification failed: ${verification.metrics.testsPassed}/${verification.metrics.testsTotal} tests passed`,
+						console.log(
+							chalk.red(`Tests failed: ${verification.metrics.testsPassed}/${verification.metrics.testsTotal}`),
 						)
 					}
 
 					// Store result
 					const storeSpinner = ora("Storing result...").start()
-					await storeTaskResult(runId, preparedTask, result, verification)
+					await storeTaskResult(runId, preparedTask, {}, verification)
 					storeSpinner.succeed("Result stored")
-
-					console.log(chalk.green(`Task completed. Success: ${verification.success}`))
-
-					// Clean up VS Code and temporary files
-					const cleanupSpinner = ora("Cleaning up...").start()
-					try {
-						await cleanupVSCode(preparedTask.workspacePath)
-						cleanupSpinner.succeed("Cleanup completed")
-					} catch (cleanupError: any) {
-						cleanupSpinner.fail(`Cleanup failed: ${cleanupError.message}`)
-						console.error(chalk.yellow(cleanupError.stack))
-					}
 				} catch (error: any) {
-					sendSpinner.fail(`Task failed: ${error.message}`)
-					console.error(chalk.red(error.stack))
-
-					// Clean up VS Code and temporary files even if the task failed
-					const cleanupSpinner = ora("Cleaning up...").start()
-					try {
-						await cleanupVSCode(preparedTask.workspacePath)
-						cleanupSpinner.succeed("Cleanup completed")
-					} catch (cleanupError: any) {
-						cleanupSpinner.fail(`Cleanup failed: ${cleanupError.message}`)
-						console.error(chalk.yellow(cleanupError.stack))
+					console.error(chalk.red(`Task failed: ${error.message}`))
+				} finally {
+					// Ensure cleanup always happens
+					if (!cleanedUp) {
+						try {
+							const finalCleanupSpinner = ora("Performing cleanup...").start()
+							await adapter.cleanupTask(preparedTask)
+							finalCleanupSpinner.succeed("Cleanup complete")
+						} catch (cleanupError: any) {
+							console.error(chalk.red(`Cleanup failed: ${cleanupError.message}`))
+						}
 					}
 				}
 			}
@@ -125,7 +107,6 @@ export async function runHandler(options: RunOptions): Promise<void> {
 			console.log(chalk.green(`\nRun complete for benchmark: ${benchmark}`))
 		} catch (error: any) {
 			console.error(chalk.red(`Error running benchmark ${benchmark}: ${error.message}`))
-			console.error(error.stack)
 		}
 	}
 

evals/cli/src/db/index.ts

@@ -1,6 +1,6 @@
-import * as path from "path"
-import * as fs from "fs"
 import Database from "better-sqlite3"
+import * as fs from "fs"
+import * as path from "path"
 import { SCHEMA } from "./schema"
 
 const EVALS_DIR = path.resolve(__dirname, "../../../")
@@ -34,16 +34,15 @@ export class ResultsDatabase {
 	/**
 	 * Create a new evaluation run
 	 * @param id Run ID
-	 * @param model Model name
 	 * @param benchmark Benchmark name
 	 */
-	createRun(id: string, model: string, benchmark: string): void {
+	createRun(id: string, benchmark: string): void {
 		const stmt = this.db.prepare(`
-      INSERT INTO runs (id, timestamp, model, benchmark)
-      VALUES (?, ?, ?, ?)
+      INSERT INTO runs (id, timestamp, benchmark)
+      VALUES (?, ?, ?)
     `)
 
-		stmt.run(id, Date.now(), model, benchmark)
+		stmt.run(id, Date.now(), benchmark)
 	}
 
 	/**

evals/cli/src/db/schema.ts

@@ -5,7 +5,6 @@ export const SCHEMA = `
 CREATE TABLE IF NOT EXISTS runs (
   id TEXT PRIMARY KEY,
   timestamp INTEGER NOT NULL,
-  model TEXT NOT NULL,
   benchmark TEXT NOT NULL,
   completed INTEGER NOT NULL DEFAULT 0
 );

evals/cli/src/index.ts

@@ -1,11 +1,10 @@
 #!/usr/bin/env node
-import { Command } from "commander"
 import chalk from "chalk"
-import { setupHandler } from "./commands/setup"
-import { runHandler } from "./commands/run"
+import { Command } from "commander"
 import { reportHandler } from "./commands/report"
-import { evalsEnvHandler } from "./commands/evals-env"
+import { runHandler } from "./commands/run"
 import { runDiffEvalHandler } from "./commands/runDiffEval"
+import { setupHandler } from "./commands/setup"
 
 // Create the CLI program
 const program = new Command()
@@ -17,11 +16,7 @@ program.name("cline-eval").description("CLI tool for orchestrating Cline evaluat
 program
 	.command("setup")
 	.description("Clone and set up benchmark repositories")
-	.option(
-		"-b, --benchmarks <benchmarks>",
-		"Comma-separated list of benchmarks to set up",
-		"exercism,swe-bench,swelancer,multi-swe",
-	)
+	.option("-b, --benchmarks <benchmarks>", "Comma-separated list of benchmarks to set up", "exercism")
 	.action(async (options) => {
 		try {
 			await setupHandler(options)
@@ -36,9 +31,7 @@ program
 	.command("run")
 	.description("Run evaluations")
 	.option("-b, --benchmark <benchmark>", "Specific benchmark to run")
-	.option("-m, --model <model>", "Model to evaluate", "claude-3-opus-20240229")
 	.option("-c, --count <count>", "Number of tasks to run", parseInt)
-	.option("-k, --api-key <apiKey>", "Cline API key to use for evaluations")
 	.action(async (options) => {
 		try {
 			await runHandler(options)
@@ -63,21 +56,6 @@ program
 		}
 	})
 
-// Evals-env command
-program
-	.command("evals-env")
-	.description("Manage evals.env files for test mode activation")
-	.argument("<action>", "Action to perform: create, remove, or check")
-	.option("-d, --directory <directory>", "Directory to create/remove/check evals.env file in (defaults to current directory)")
-	.action(async (action, options) => {
-		try {
-			await evalsEnvHandler({ action, ...options })
-		} catch (error) {
-			console.error(chalk.red(`Error managing evals.env file: ${error instanceof Error ? error.message : String(error)}`))
-			process.exit(1)
-		}
-	})
-
 // Run-diff-eval command
 program
 	.command("run-diff-eval")
@@ -86,11 +64,15 @@ program
 	.option("--output-path <path>", "Path to the directory to save the test output JSON files")
 	.option("--model-ids <model_ids>", "Comma-separated list of model IDs to test")
 	.option("--system-prompt-name <name>", "The name of the system prompt to use", "basicSystemPrompt")
-	.option("-n, --valid-attempts-per-case <number>", "Number of valid attempts per test case per model (will retry until this many valid attempts are collected)", "1")
+	.option(
+		"-n, --valid-attempts-per-case <number>",
+		"Number of valid attempts per test case per model (will retry until this many valid attempts are collected)",
+		"1",
+	)
 	.option("--max-attempts-per-case <number>", "Maximum total attempts per test case (default: 10x valid attempts)")
 	.option("--max-cases <number>", "Maximum number of test cases to run (limits total cases loaded)")
 	.option("--parsing-function <name>", "The parsing function to use", "parseAssistantMessageV2")
-	.option("--diff-edit-function <name>", "The diff editing function to use", "constructNewFileContentV2")
+	.option("--diff-edit-function <name>", "The diff editing function to use", "diff-06-26-25")
 	.option("--thinking-budget <tokens>", "Set the thinking tokens budget", "0")
 	.option("--provider <provider>", "API provider to use (openrouter, openai)", "openrouter")
 	.option("--parallel", "Run tests in parallel", false)

evals/cli/src/utils/evals-env.ts

@@ -1,79 +0,0 @@
-import * as fs from "fs"
-import * as path from "path"
-import chalk from "chalk"
-
-/**
- * Creates an evals.env file in the specified directory
- * @param directory The directory where the evals.env file should be created
- * @returns True if the file was created, false if it already exists
- */
-export function createEvalsEnvFile(directory: string): boolean {
-	const evalsEnvPath = path.join(directory, "evals.env")
-
-	// Check if the file already exists
-	if (fs.existsSync(evalsEnvPath)) {
-		console.log(chalk.yellow(`evals.env file already exists at ${evalsEnvPath}`))
-		return false
-	}
-
-	// Create the file
-	try {
-		const content = `# This file activates Cline test mode
-# Created at: ${new Date().toISOString()}
-# 
-# This file is automatically detected by the Cline extension
-# and enables test mode for automated evaluations.
-#
-# Delete this file to deactivate test mode.
-`
-		fs.writeFileSync(evalsEnvPath, content)
-		console.log(chalk.green(`Created evals.env file at ${evalsEnvPath}`))
-		return true
-	} catch (error) {
-		console.error(chalk.red(`Error creating evals.env file: ${error}`))
-		return false
-	}
-}
-
-/**
- * Removes an evals.env file from the specified directory
- * @param directory The directory where the evals.env file should be removed
- * @returns True if the file was removed, false if it doesn't exist
- */
-export function removeEvalsEnvFile(directory: string): boolean {
-	const evalsEnvPath = path.join(directory, "evals.env")
-
-	// Check if the file exists
-	if (!fs.existsSync(evalsEnvPath)) {
-		console.log(chalk.yellow(`No evals.env file found at ${evalsEnvPath}`))
-		return false
-	}
-
-	// Remove the file
-	try {
-		fs.unlinkSync(evalsEnvPath)
-		console.log(chalk.green(`Removed evals.env file from ${evalsEnvPath}`))
-		return true
-	} catch (error) {
-		console.error(chalk.red(`Error removing evals.env file: ${error}`))
-		return false
-	}
-}
-
-/**
- * Checks if an evals.env file exists in the specified directory
- * @param directory The directory to check for an evals.env file
- * @returns True if the file exists, false otherwise
- */
-export function checkEvalsEnvFile(directory: string): boolean {
-	const evalsEnvPath = path.join(directory, "evals.env")
-	const exists = fs.existsSync(evalsEnvPath)
-
-	if (exists) {
-		console.log(chalk.green(`evals.env file found at ${evalsEnvPath}`))
-	} else {
-		console.log(chalk.yellow(`No evals.env file found at ${evalsEnvPath}`))
-	}
-
-	return exists
-}

evals/cli/src/utils/extensions.ts

@@ -1,131 +0,0 @@
-import execa from "execa"
-import * as fs from "fs"
-import * as path from "path"
-import * as os from "os"
-
-/**
- * List of VSCode extensions to install for evaluation environments
- * These extensions provide language support and other useful features
- */
-export const REQUIRED_EXTENSIONS = [
-	"golang.go", // Go language support
-	"dbaeumer.vscode-eslint", // ESLint support
-	"redhat.java", // Java support
-	"ms-python.python", // Python support
-	"rust-lang.rust-analyzer", // Rust support
-	"ms-vscode.cpptools", // C/C++ support
-]
-
-/**
- * Install required VSCode extensions in the specified extensions directory
- * @param extensionsDir The directory where extensions should be installed
- * @returns Promise that resolves when all extensions are installed
- */
-export async function installRequiredExtensions(extensionsDir: string): Promise<void> {
-	console.log("Installing required VSCode extensions...")
-
-	// Create the extensions directory if it doesn't exist
-	if (!fs.existsSync(extensionsDir)) {
-		fs.mkdirSync(extensionsDir, { recursive: true })
-	}
-
-	// Install each extension
-	for (const extension of REQUIRED_EXTENSIONS) {
-		try {
-			console.log(`Installing extension: ${extension}...`)
-			await execa("code", ["--extensions-dir", extensionsDir, "--install-extension", extension, "--force"])
-			console.log(`✅ Extension ${extension} installed successfully`)
-		} catch (error: any) {
-			console.warn(`⚠️ Failed to install extension ${extension}: ${error.message}`)
-			// Continue with other extensions even if one fails
-		}
-	}
-
-	console.log("✅ All required extensions installed")
-}
-
-/**
- * Check if a VSCode extension is installed in the specified directory
- * @param extensionsDir The directory to check for installed extensions
- * @param extensionId The ID of the extension to check
- * @returns True if the extension is installed, false otherwise
- */
-export function isExtensionInstalled(extensionsDir: string, extensionId: string): boolean {
-	// Extensions are installed in directories named publisher.name-version
-	// We need to check if any directory starts with the extensionId
-	const extensionPrefix = extensionId.toLowerCase() + "-"
-
-	try {
-		const files = fs.readdirSync(extensionsDir)
-		return files.some((file) => {
-			const lowerCaseFile = file.toLowerCase()
-			return lowerCaseFile === extensionId.toLowerCase() || lowerCaseFile.startsWith(extensionPrefix)
-		})
-	} catch (error) {
-		return false
-	}
-}
-
-/**
- * Get the path to the VSCode settings file in the specified user data directory
- * @param userDataDir The VSCode user data directory
- * @returns The path to the settings.json file
- */
-export function getSettingsPath(userDataDir: string): string {
-	const settingsDir = path.join(userDataDir, "User")
-	fs.mkdirSync(settingsDir, { recursive: true })
-	return path.join(settingsDir, "settings.json")
-}
-
-/**
- * Configure extension settings in the VSCode user data directory
- * @param userDataDir The VSCode user data directory
- */
-export function configureExtensionSettings(userDataDir: string): void {
-	const settingsPath = getSettingsPath(userDataDir)
-
-	// Read existing settings if they exist
-	let settings = {}
-	if (fs.existsSync(settingsPath)) {
-		try {
-			settings = JSON.parse(fs.readFileSync(settingsPath, "utf8"))
-		} catch (error) {
-			console.warn(`Error reading settings file: ${error}`)
-		}
-	}
-
-	// Add or update extension-specific settings
-	const updatedSettings = {
-		...settings,
-		// Go extension settings
-		"go.toolsManagement.autoUpdate": false,
-		"go.survey.prompt": false,
-
-		// ESLint settings
-		"eslint.enable": true,
-		"eslint.run": "onSave",
-
-		// Java settings
-		"java.configuration.checkProjectSettingsExclusions": false,
-		"java.configure.checkForOutdatedExtensions": false,
-		"java.help.firstView": false,
-
-		// Python settings
-		"python.experiments.enabled": false,
-		"python.showStartPage": false,
-
-		// Rust settings
-		"rust-analyzer.checkOnSave.command": "check",
-
-		// C/C++ settings
-		"C_Cpp.intelliSenseEngine": "default",
-
-		// General extension settings
-		"extensions.autoUpdate": false,
-		"extensions.ignoreRecommendations": true,
-	}
-
-	// Write updated settings
-	fs.writeFileSync(settingsPath, JSON.stringify(updatedSettings, null, 2))
-	console.log("✅ Extension settings configured")
-}

evals/cli/src/utils/markdown.ts

@@ -1,28 +1,24 @@
 import * as fs from "fs"
-import * as path from "path"
 
 /**
  * Generate a markdown report from evaluation results
  * @param summary Overall summary
  * @param benchmarkReports Benchmark-specific reports
- * @param modelReports Model-specific reports
  * @param outputPath Output file path
  */
-export function generateMarkdownReport(
-	summary: any,
-	benchmarkReports: Record<string, any>,
-	modelReports: Record<string, any>,
-	outputPath: string,
-): void {
+export function generateMarkdownReport(summary: any, benchmarkReports: Record<string, any>, outputPath: string): void {
 	let markdown = `# Cline Evaluation Report\n\n`
 
 	// Generate summary section
 	markdown += `## Summary\n\n`
 	markdown += `- **Total Runs:** ${summary.runs}\n`
-	markdown += `- **Models:** ${summary.models.join(", ")}\n`
 	markdown += `- **Benchmarks:** ${summary.benchmarks.join(", ")}\n`
 	markdown += `- **Total Tasks:** ${summary.tasks}\n`
-	markdown += `- **Success Rate:** ${(summary.successRate * 100).toFixed(2)}%\n`
+	markdown += `- **Task Success Rate:** ${(summary.successRate * 100).toFixed(2)}%\n`
+	markdown += `- **Total Tests:** ${summary.totalTests}\n`
+	markdown += `- **Tests Passed:** ${summary.totalTestsPassed}\n`
+	markdown += `- **Tests Failed:** ${summary.totalTestsFailed}\n`
+	markdown += `- **Test Success Rate:** ${(summary.testSuccessRate * 100).toFixed(2)}%\n`
 	markdown += `- **Average Tokens:** ${Math.round(summary.averageTokens)}\n`
 	markdown += `- **Average Cost:** $${summary.averageCost.toFixed(4)}\n`
 	markdown += `- **Average Duration:** ${(summary.averageDuration / 1000).toFixed(2)}s\n`
@@ -48,23 +44,12 @@ export function generateMarkdownReport(
 	for (const [benchmark, report] of Object.entries(benchmarkReports)) {
 		markdown += `### ${benchmark}\n\n`
 		markdown += `- **Runs:** ${report.runs}\n`
-		markdown += `- **Models:** ${report.models.join(", ")}\n`
 		markdown += `- **Tasks:** ${report.tasks}\n`
-		markdown += `- **Success Rate:** ${(report.successRate * 100).toFixed(2)}%\n`
-		markdown += `- **Average Tokens:** ${Math.round(report.averageTokens)}\n`
-		markdown += `- **Average Cost:** $${report.averageCost.toFixed(4)}\n`
-		markdown += `- **Average Duration:** ${(report.averageDuration / 1000).toFixed(2)}s\n\n`
-	}
-
-	// Generate model results section
-	markdown += `## Model Results\n\n`
-
-	for (const [model, report] of Object.entries(modelReports)) {
-		markdown += `### ${model}\n\n`
-		markdown += `- **Runs:** ${report.runs}\n`
-		markdown += `- **Benchmarks:** ${report.benchmarks.join(", ")}\n`
-		markdown += `- **Tasks:** ${report.tasks}\n`
-		markdown += `- **Success Rate:** ${(report.successRate * 100).toFixed(2)}%\n`
+		markdown += `- **Task Success Rate:** ${(report.successRate * 100).toFixed(2)}%\n`
+		markdown += `- **Total Tests:** ${report.totalTests}\n`
+		markdown += `- **Tests Passed:** ${report.totalTestsPassed}\n`
+		markdown += `- **Tests Failed:** ${report.totalTestsFailed}\n`
+		markdown += `- **Test Success Rate:** ${(report.testSuccessRate * 100).toFixed(2)}%\n`
 		markdown += `- **Average Tokens:** ${Math.round(report.averageTokens)}\n`
 		markdown += `- **Average Cost:** $${report.averageCost.toFixed(4)}\n`
 		markdown += `- **Average Duration:** ${(report.averageDuration / 1000).toFixed(2)}s\n\n`
@@ -87,20 +72,6 @@ export function generateMarkdownReport(
 
 	markdown += "```\n\n"
 
-	// Success rate by model chart
-	markdown += `### Success Rate by Model\n\n`
-	markdown += "```mermaid\n"
-	markdown += "graph TD\n"
-	markdown += "  title[Success Rate by Model]\n"
-	markdown += "  style title fill:none,stroke:none\n\n"
-
-	for (const [model, report] of Object.entries(modelReports)) {
-		const successRate = (report.successRate * 100).toFixed(2)
-		markdown += `  ${model.replace(/[-\.]/g, "_")}[${model}: ${successRate}%]\n`
-	}
-
-	markdown += "```\n\n"
-
 	// Add timestamp
 	markdown += `\n\n---\n\nReport generated on ${new Date().toISOString()}\n`
 

evals/cli/src/utils/task.ts

@@ -1,52 +0,0 @@
-import fetch from "node-fetch"
-import chalk from "chalk"
-
-/**
- * Send a task to the Cline test server
- * @param task The task description to send
- * @param apiKey Optional Cline API key to use for the task
- * @returns The result of the task execution
- */
-export async function sendTaskToServer(task: string, apiKey?: string): Promise<any> {
-	const SERVER_URL = "http://localhost:9876/task"
-
-	try {
-		console.log(chalk.blue(`Sending task to server: ${task.substring(0, 100)}${task.length > 100 ? "..." : ""}`))
-
-		const response = await fetch(SERVER_URL, {
-			method: "POST",
-			headers: {
-				"Content-Type": "application/json",
-			},
-			body: JSON.stringify({
-				task,
-				apiKey,
-			}),
-		})
-
-		if (!response.ok) {
-			const errorText = await response.text()
-			throw new Error(`Server responded with status ${response.status}: ${errorText}`)
-		}
-
-		const result = await response.json()
-
-		if (!result.success) {
-			throw new Error(`Task execution failed: ${result.error || "Unknown error"}`)
-		}
-
-		if (result.timeout) {
-			throw new Error("Task execution timed out")
-		}
-
-		return result
-	} catch (error: any) {
-		if (error.code === "ECONNREFUSED") {
-			throw new Error(
-				"Could not connect to the test server. Make sure VSCode is running with the Cline extension and the test server is active.",
-			)
-		}
-
-		throw error
-	}
-}

evals/cli/src/utils/vscode.ts

@@ -1,598 +0,0 @@
-import execa from "execa"
-import * as path from "path"
-import * as fs from "fs"
-import fetch from "node-fetch"
-import * as os from "os"
-import { installRequiredExtensions, configureExtensionSettings } from "./extensions"
-
-// Store temporary directories for cleanup
-interface VSCodeResources {
-	tempUserDataDir: string
-	tempExtensionsDir: string
-	vscodePid?: number
-}
-
-// Global map to track resources for each workspace
-const workspaceResources = new Map<string, VSCodeResources>()
-
-/**
- * Spawn a VSCode instance with the Cline extension
- * @param workspacePath The workspace path to open
- * @param vsixPath Optional path to a VSIX file to install
- * @returns The resources created for this VS Code instance
- */
-export async function spawnVSCode(workspacePath: string, vsixPath?: string): Promise<VSCodeResources> {
-	// Ensure the workspace path exists
-	if (!fs.existsSync(workspacePath)) {
-		throw new Error(`Workspace path does not exist: ${workspacePath}`)
-	}
-
-	// If no VSIX path is provided, build one with IS_TEST=true
-	if (!vsixPath) {
-		try {
-			// Build the VSIX (no longer need to set IS_TEST=true as we'll use evals.env file)
-			console.log("Building VSIX...")
-			const clineRoot = path.resolve(process.cwd(), "..", "..")
-			await execa("npx", ["vsce", "package"], {
-				cwd: clineRoot,
-				stdio: "inherit",
-			})
-
-			// Find the generated VSIX file(s)
-			const files = fs.readdirSync(clineRoot)
-			const vsixFiles = files.filter((file) => file.endsWith(".vsix"))
-
-			if (vsixFiles.length > 0) {
-				// Get file stats to find the most recent one
-				const vsixFilesWithStats = vsixFiles.map((file) => {
-					const filePath = path.join(clineRoot, file)
-					return {
-						file,
-						path: filePath,
-						mtime: fs.statSync(filePath).mtime,
-					}
-				})
-
-				// Sort by modification time (most recent first)
-				vsixFilesWithStats.sort((a, b) => b.mtime.getTime() - a.mtime.getTime())
-
-				// Use the most recent VSIX
-				vsixPath = vsixFilesWithStats[0].path
-				console.log(`Using most recent VSIX: ${vsixPath} (modified ${vsixFilesWithStats[0].mtime.toISOString()})`)
-
-				// Log all found VSIX files for debugging
-				if (vsixFiles.length > 1) {
-					console.log(`Found ${vsixFiles.length} VSIX files:`)
-					vsixFilesWithStats.forEach((f) => {
-						console.log(`  - ${f.file} (modified ${f.mtime.toISOString()})`)
-					})
-				}
-			} else {
-				console.warn("Could not find generated VSIX file")
-			}
-		} catch (error) {
-			console.warn("Failed to build test VSIX:", error)
-		}
-	}
-
-	// Create a temporary user data directory for this VS Code instance
-	const tempUserDataDir = path.join(os.tmpdir(), `vscode-cline-eval-${Date.now()}`)
-	fs.mkdirSync(tempUserDataDir, { recursive: true })
-	console.log(`Created temporary user data directory: ${tempUserDataDir}`)
-
-	// Create a temporary extensions directory to ensure no other extensions are loaded
-	const tempExtensionsDir = path.join(os.tmpdir(), `vscode-cline-eval-ext-${Date.now()}`)
-	fs.mkdirSync(tempExtensionsDir, { recursive: true })
-	console.log(`Created temporary extensions directory: ${tempExtensionsDir}`)
-
-	// Create evals.env file in the workspace to trigger test mode
-	console.log(`Creating evals.env file in workspace: ${workspacePath}`)
-	const evalsEnvPath = path.join(workspacePath, "evals.env")
-	fs.writeFileSync(
-		evalsEnvPath,
-		`# This file activates Cline test mode
-# Created at: ${new Date().toISOString()}
-# 
-# This file is automatically detected by the Cline extension
-# and enables test mode for automated evaluations.
-#
-# Delete this file to deactivate test mode.
-`,
-	)
-
-	// Create settings.json in the temporary user data directory to disable workspace trust
-	// and configure Cline to auto-open on startup
-	const settingsDir = path.join(tempUserDataDir, "User")
-	fs.mkdirSync(settingsDir, { recursive: true })
-	const settingsPath = path.join(settingsDir, "settings.json")
-	const settings = {
-		// Disable workspace trust
-		"security.workspace.trust.enabled": false,
-		"security.workspace.trust.startupPrompt": "never",
-		"security.workspace.trust.banner": "never",
-		"security.workspace.trust.emptyWindow": true,
-
-		// Configure startup behavior
-		"workbench.startupEditor": "none",
-
-		// Auto-open Cline on startup
-		"cline.autoOpenOnStartup": true,
-
-		// Show the activity bar and sidebar
-		"workbench.activityBar.visible": true,
-		"workbench.sideBar.visible": true,
-		"workbench.view.extension.saoudrizwan.claude-dev-ActivityBar.visible": true,
-		"workbench.view.alwaysShowHeaderActions": true,
-		"workbench.editor.openSideBySideDirection": "right",
-
-		// Disable GitLens from opening automatically
-		"gitlens.views.repositories.autoReveal": false,
-		"gitlens.views.fileHistory.autoReveal": false,
-		"gitlens.views.lineHistory.autoReveal": false,
-		"gitlens.views.compare.autoReveal": false,
-		"gitlens.views.search.autoReveal": false,
-		"gitlens.showWelcomeOnInstall": false,
-		"gitlens.showWhatsNewAfterUpgrades": false,
-
-		// Disable other extensions that might compete for startup focus
-		"extensions.autoUpdate": false,
-	}
-	fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2))
-	console.log(`Created settings.json to disable workspace trust and auto-open Cline`)
-
-	// Create keybindings.json to automatically open Cline on startup
-	const keybindingsPath = path.join(settingsDir, "keybindings.json")
-	const keybindings = [
-		{
-			key: "alt+c",
-			command: "workbench.view.extension.saoudrizwan.claude-dev-ActivityBar",
-			when: "viewContainer.workbench.view.extension.saoudrizwan.claude-dev-ActivityBar.enabled",
-		},
-	]
-	fs.writeFileSync(keybindingsPath, JSON.stringify(keybindings, null, 2))
-	console.log(`Created keybindings.json to help with Cline activation`)
-
-	// Build the command arguments with custom user data directory
-	const args = [
-		// Use a custom user data directory to isolate this instance
-		"--user-data-dir",
-		tempUserDataDir,
-		// Use a custom extensions directory to ensure only our extension is loaded
-		"--extensions-dir",
-		tempExtensionsDir,
-		// Disable workspace trust
-		"--disable-workspace-trust",
-		"-n",
-		workspacePath,
-		// Force the extension to be activated on startup
-		"--start-up-extension",
-		"saoudrizwan.claude-dev",
-		// Run a command on startup to open Cline
-		"--command",
-		"workbench.view.extension.saoudrizwan.claude-dev-ActivityBar",
-		// Additional flags to help with extension activation
-		"--disable-gpu=false",
-		"--max-memory=4096",
-	]
-
-	// Create a startup script to run commands after VS Code launches
-	const startupScriptPath = path.join(settingsDir, "startup.js")
-	const startupScript = `
-		// This script will be executed when VS Code starts
-		setTimeout(() => {
-			// Try to open Cline in the sidebar
-			require('vscode').commands.executeCommand('workbench.view.extension.saoudrizwan.claude-dev-ActivityBar');
-		}, 5000);
-	`
-	fs.writeFileSync(startupScriptPath, startupScript)
-	console.log(`Created startup script to activate Cline`)
-
-	// If a VSIX is provided, install it
-	if (vsixPath) {
-		if (!fs.existsSync(vsixPath)) {
-			throw new Error(`VSIX file does not exist: ${vsixPath}`)
-		}
-		args.unshift("--install-extension", vsixPath)
-	}
-
-	// Install required extensions
-	console.log("Installing required VSCode extensions...")
-	await installRequiredExtensions(tempExtensionsDir)
-
-	// Configure extension settings
-	console.log("Configuring extension settings...")
-	configureExtensionSettings(tempUserDataDir)
-
-	// Execute the command
-	try {
-		// We don't need to install extensions globally anymore since we're using a custom user data directory
-		// The VSIX will be installed in the isolated environment if provided in the args
-
-		// Launch VS Code
-		console.log("Launching VS Code...")
-		await execa("code", args, {
-			stdio: "inherit",
-		})
-
-		// Wait longer for VSCode to initialize and extension to load
-		console.log("Waiting for VS Code to initialize...")
-		await new Promise((resolve) => setTimeout(resolve, 30000))
-
-		// Create a JavaScript file that will be loaded as a VS Code extension
-		const extensionDir = path.join(tempExtensionsDir, "cline-activator")
-		fs.mkdirSync(extensionDir, { recursive: true })
-
-		// Create package.json for the extension
-		const packageJsonPath = path.join(extensionDir, "package.json")
-		const packageJson = {
-			name: "cline-activator",
-			displayName: "Cline Activator",
-			description: "Activates Cline and starts the test server",
-			version: "0.0.1",
-			engines: {
-				vscode: "^1.60.0",
-			},
-			main: "./extension.js",
-			activationEvents: ["*"],
-			contributes: {
-				commands: [
-					{
-						command: "cline-activator.activate",
-						title: "Activate Cline",
-					},
-				],
-			},
-		}
-		fs.writeFileSync(packageJsonPath, JSON.stringify(packageJson, null, 2))
-
-		// Create extension.js
-		const extensionJsPath = path.join(extensionDir, "extension.js")
-		const extensionJs = `
-			const vscode = require('vscode');
-			
-			/**
-			 * @param {vscode.ExtensionContext} context
-			 */
-			function activate(context) {
-				console.log('Cline Activator is now active!');
-				
-				// Register the command to activate Cline
-				let disposable = vscode.commands.registerCommand('cline-activator.activate', async function () {
-					try {
-						// Make sure the Cline extension is activated
-						const extension = vscode.extensions.getExtension('saoudrizwan.claude-dev');
-						if (!extension) {
-							console.error('Cline extension not found');
-							return;
-						}
-						
-						if (!extension.isActive) {
-							console.log('Activating Cline extension...');
-							await extension.activate();
-						}
-						
-						// Show the Cline sidebar
-						console.log('Opening Cline sidebar...');
-						await vscode.commands.executeCommand('workbench.view.extension.saoudrizwan.claude-dev-ActivityBar');
-						
-						// Wait a moment for the sidebar to initialize
-						await new Promise(resolve => setTimeout(resolve, 2000));
-						
-						// Create the test server if it doesn't exist
-						console.log('Creating test server...');
-						
-						// Get the visible webview instance
-						const clineRootPath = '${path.resolve(process.cwd(), "..", "..")}';
-						const visibleWebview = require(path.join(clineRootPath, 'src', 'core', 'webview')).WebviewProvider.getVisibleInstance();
-						if (visibleWebview) {
-							require(path.join(clineRootPath, 'src', 'services', 'test', 'TestServer')).createTestServer(visibleWebview);
-							console.log('Test server created successfully');
-						} else {
-							console.error('No visible webview instance found');
-						}
-					} catch (error) {
-						console.error('Error activating Cline:', error);
-					}
-				});
-				
-				context.subscriptions.push(disposable);
-				
-				// Automatically run the command after a delay
-				setTimeout(() => {
-					vscode.commands.executeCommand('cline-activator.activate');
-				}, 5000);
-			}
-			
-			function deactivate() {}
-			
-			module.exports = {
-				activate,
-				deactivate
-			}
-		`
-		fs.writeFileSync(extensionJsPath, extensionJs)
-		console.log(`Created Cline Activator extension`)
-
-		// Try multiple approaches to activate the extension
-		let serverStarted = false
-
-		// Create an activation script to run in VS Code
-		const activationScriptPath = path.join(settingsDir, "activate-cline.js")
-		const activationScript = `
-			// This script will be executed to activate Cline and start the test server
-			const vscode = require('vscode');
-			
-			// Execute the cline-activator.activate command
-			vscode.commands.executeCommand('cline-activator.activate');
-		`
-		fs.writeFileSync(activationScriptPath, activationScript)
-		console.log(`Created activation script to run in VS Code`)
-
-		// Execute the activation script
-		try {
-			console.log("Executing activation script to start Cline and test server...")
-			await execa(
-				"code",
-				[
-					"--user-data-dir",
-					tempUserDataDir,
-					"--extensions-dir",
-					tempExtensionsDir,
-					"--folder-uri",
-					`file://${workspacePath}`,
-					"--execute",
-					activationScriptPath,
-				],
-				{
-					stdio: "inherit",
-				},
-			)
-
-			// Wait for the test server to start
-			console.log("Waiting for test server to start...")
-			for (let i = 0; i < 30; i++) {
-				try {
-					// Try to connect to the test server
-					const response = await fetch("http://localhost:9876/task", {
-						method: "OPTIONS",
-						headers: {
-							"Content-Type": "application/json",
-						},
-					})
-
-					if (response.status === 204) {
-						console.log("Test server is running!")
-						serverStarted = true
-						break
-					}
-				} catch (error) {
-					// Server not started yet, wait and try again
-					await new Promise((resolve) => setTimeout(resolve, 1000))
-				}
-			}
-		} catch (error) {
-			console.warn("Failed to execute activation script:", error)
-		}
-
-		if (!serverStarted) {
-			console.warn("Test server did not start after multiple attempts")
-			console.log("You may need to manually open the Cline extension in VS Code")
-		}
-
-		// Store the resources for this workspace
-		const resources: VSCodeResources = {
-			tempUserDataDir,
-			tempExtensionsDir,
-		}
-
-		// Store in the global map
-		workspaceResources.set(workspacePath, resources)
-
-		// Return the resources
-		return resources
-	} catch (error: any) {
-		throw new Error(`Failed to spawn VSCode: ${error.message}`)
-	}
-}
-
-/**
- * Clean up VS Code resources and shut down the test server
- * @param workspacePath The workspace path to clean up resources for
- */
-export async function cleanupVSCode(workspacePath: string): Promise<void> {
-	console.log(`Cleaning up VS Code resources for workspace: ${workspacePath}`)
-
-	// Get the resources for this workspace
-	const resources = workspaceResources.get(workspacePath)
-	if (!resources) {
-		console.log(`No resources found for workspace: ${workspacePath}`)
-		return
-	}
-
-	// Try to shut down the test server
-	try {
-		console.log("Shutting down test server...")
-		await fetch("http://localhost:9876/shutdown", {
-			method: "POST",
-			headers: {
-				"Content-Type": "application/json",
-			},
-		}).catch(() => {
-			// Ignore errors, the server might already be down
-		})
-	} catch (error) {
-		console.warn(`Error shutting down test server: ${error}`)
-	}
-
-	// Try to gracefully close VS Code instead of killing it
-	try {
-		console.log("Attempting to gracefully close VS Code...")
-
-		// Create a settings file that will disable the crash reporter and the exit confirmation dialog
-		const settingsDir = path.join(resources.tempUserDataDir, "User")
-		const settingsPath = path.join(settingsDir, "settings.json")
-
-		// Read existing settings if they exist
-		let settings = {}
-		if (fs.existsSync(settingsPath)) {
-			try {
-				settings = JSON.parse(fs.readFileSync(settingsPath, "utf8"))
-			} catch (error) {
-				console.warn(`Error reading settings file: ${error}`)
-			}
-		}
-
-		// Update settings to disable crash reporter and exit confirmation
-		settings = {
-			...settings,
-			"window.confirmBeforeClose": "never",
-			"telemetry.enableCrashReporter": false,
-			"window.restoreWindows": "none",
-			"window.newWindowDimensions": "default",
-		}
-
-		// Write updated settings
-		fs.writeFileSync(settingsPath, JSON.stringify(settings, null, 2))
-
-		// On macOS, use AppleScript to quit VS Code gracefully
-		if (process.platform === "darwin") {
-			try {
-				// First try AppleScript to quit VS Code gracefully
-				await execa("osascript", ["-e", 'tell application "Visual Studio Code" to quit'])
-
-				// Wait a moment for VS Code to close
-				await new Promise((resolve) => setTimeout(resolve, 2000))
-			} catch (appleScriptError) {
-				console.warn(`Error using AppleScript to quit VS Code: ${appleScriptError}`)
-			}
-		} else if (process.platform === "win32") {
-			// On Windows, try to use taskkill without /F first
-			try {
-				await execa("taskkill", ["/IM", "code.exe"])
-
-				// Wait a moment for VS Code to close
-				await new Promise((resolve) => setTimeout(resolve, 2000))
-			} catch (taskkillError) {
-				console.warn(`Error using taskkill to quit VS Code: ${taskkillError}`)
-			}
-		} else {
-			// On Linux, try to use SIGTERM first
-			try {
-				// Find VS Code processes
-				const { stdout } = await execa("ps", ["aux"])
-				const lines = stdout.split("\n")
-
-				for (const line of lines) {
-					if (line.includes(resources.tempUserDataDir)) {
-						const parts = line.trim().split(/\s+/)
-						const pid = parseInt(parts[1])
-
-						if (pid && !isNaN(pid)) {
-							console.log(`Sending SIGTERM to VS Code process with PID: ${pid}`)
-							try {
-								// Use SIGTERM instead of SIGKILL for a graceful shutdown
-								process.kill(pid, "SIGTERM")
-							} catch (killError) {
-								console.warn(`Failed to terminate process ${pid}: ${killError}`)
-							}
-						}
-					}
-				}
-
-				// Wait a moment for VS Code to close
-				await new Promise((resolve) => setTimeout(resolve, 2000))
-			} catch (psError) {
-				console.warn(`Error listing processes: ${psError}`)
-			}
-		}
-
-		// If graceful methods failed, fall back to forceful termination as a last resort
-		// Check if VS Code is still running with the temp user data dir
-		let vsCodeStillRunning = false
-
-		if (process.platform !== "win32") {
-			try {
-				const { stdout } = await execa("ps", ["aux"])
-				vsCodeStillRunning = stdout.split("\n").some((line) => line.includes(resources.tempUserDataDir))
-			} catch (error) {
-				console.warn(`Error checking if VS Code is still running: ${error}`)
-			}
-		} else {
-			try {
-				const { stdout } = await execa("tasklist", ["/FI", `IMAGENAME eq code.exe`])
-				vsCodeStillRunning = stdout.includes("code.exe")
-			} catch (error) {
-				console.warn(`Error checking if VS Code is still running: ${error}`)
-			}
-		}
-
-		// If VS Code is still running, use forceful termination as a last resort
-		if (vsCodeStillRunning) {
-			console.log("Graceful shutdown failed, falling back to forceful termination...")
-
-			if (process.platform === "win32") {
-				try {
-					await execa("taskkill", ["/IM", "code.exe", "/F"])
-				} catch (error) {
-					console.warn(`Error forcefully terminating VS Code: ${error}`)
-				}
-			} else {
-				try {
-					const { stdout } = await execa("ps", ["aux"])
-					const lines = stdout.split("\n")
-
-					for (const line of lines) {
-						if (line.includes(resources.tempUserDataDir)) {
-							const parts = line.trim().split(/\s+/)
-							const pid = parseInt(parts[1])
-
-							if (pid && !isNaN(pid)) {
-								console.log(`Forcefully killing VS Code process with PID: ${pid}`)
-								try {
-									process.kill(pid, "SIGKILL")
-								} catch (killError) {
-									console.warn(`Failed to kill process ${pid}: ${killError}`)
-								}
-							}
-						}
-					}
-				} catch (error) {
-					console.warn(`Error forcefully terminating VS Code: ${error}`)
-				}
-			}
-		}
-	} catch (error) {
-		console.warn(`Error closing VS Code: ${error}`)
-	}
-
-	// Clean up temporary directories and evals.env file
-	try {
-		console.log(`Removing temporary user data directory: ${resources.tempUserDataDir}`)
-		fs.rmSync(resources.tempUserDataDir, { recursive: true, force: true })
-	} catch (error) {
-		console.warn(`Error removing temporary user data directory: ${error}`)
-	}
-
-	try {
-		console.log(`Removing temporary extensions directory: ${resources.tempExtensionsDir}`)
-		fs.rmSync(resources.tempExtensionsDir, { recursive: true, force: true })
-	} catch (error) {
-		console.warn(`Error removing temporary extensions directory: ${error}`)
-	}
-
-	// Remove the evals.env file
-	try {
-		const evalsEnvPath = path.join(workspacePath, "evals.env")
-		if (fs.existsSync(evalsEnvPath)) {
-			console.log(`Removing evals.env file: ${evalsEnvPath}`)
-			fs.unlinkSync(evalsEnvPath)
-		}
-	} catch (error) {
-		console.warn(`Error removing evals.env file: ${error}`)
-	}
-
-	// Remove from the global map
-	workspaceResources.delete(workspacePath)
-
-	console.log("Cleanup completed")
-}

evals/package.json

@@ -20,7 +20,7 @@
   "license": "MIT",
   "dependencies": {
     "axios": "^1.12.0",
-    "better-sqlite3": "^11.10.0",
+    "better-sqlite3": "^12.4.1",
     "chalk": "5.6.2",
     "dotenv": "^16.5.0",
     "commander": "^9.4.1",
@@ -40,5 +40,8 @@
     "@types/yargs": "^17.0.19",
     "ts-node": "^10.9.1",
     "typescript": "^4.9.4"
+  },
+  "overrides": {
+    "tar-fs": "^3.1.1"
   }
 }

package.json

@@ -2,7 +2,7 @@
 	"name": "claude-dev",
 	"displayName": "Cline",
 	"description": "Autonomous coding agent right in your IDE, capable of creating/editing files, running commands, using the browser, and more with your permission every step of the way.",
-	"version": "3.33.1",
+	"version": "3.37.1",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -149,6 +149,12 @@
 				"category": "Cline",
 				"when": "cline.isDevMode"
 			},
+			{
+				"command": "cline.dev.expireMcpOAuthTokens",
+				"title": "Expire MCP OAuth Tokens (for testing)",
+				"category": "Cline",
+				"when": "cline.isDevMode"
+			},
 			{
 				"command": "cline.addToChat",
 				"title": "Add to Cline",
@@ -278,11 +284,11 @@
 			"commandPalette": [
 				{
 					"command": "cline.generateGitCommitMessage",
-					"when": "config.git.enabled && scmProvider == git && !cline.isGeneratingCommit"
+					"when": "config.git.enabled && !cline.isGeneratingCommit"
 				},
 				{
 					"command": "cline.abortGitCommitMessage",
-					"when": "config.git.enabled && scmProvider == git && cline.isGeneratingCommit"
+					"when": "config.git.enabled && cline.isGeneratingCommit"
 				}
 			]
 		},
@@ -300,16 +306,20 @@
 		"compile-cli-all-platforms": "scripts/build-cli-all-platforms.sh",
 		"compile-cli-man-page": "pandoc cli/man/cline.1.md -s -t man -o cli/man/cline.1",
 		"build:npm": "scripts/build-npm-package.sh",
+		"build:docker:dev": "node scripts/build-docker-dev.mjs",
+		"docker:shell": "node scripts/docker-shell.mjs",
 		"test:install": "bash scripts/test-install.sh",
 		"dev:cli:watch": "node scripts/dev-cli-watch.mjs",
 		"postcompile-standalone": "node scripts/package-standalone.mjs",
 		"postcompile-standalone-npm": "node scripts/package-standalone.mjs --target=npm",
+		"dev": "npm run protos && npm run watch",
 		"watch": "npm-run-all -p watch:*",
 		"watch:esbuild": "node esbuild.mjs --watch",
 		"watch:tsc": "tsc --noEmit --watch --project tsconfig.json",
 		"package": "npm run check-types && npm run build:webview && npm run lint && node esbuild.mjs --production",
 		"protos": "node scripts/build-proto.mjs",
 		"protos-go": "node scripts/build-go-proto.mjs",
+		"protos-python": "node scripts/build-python-proto.mjs",
 		"cli-providers": "node scripts/cli-providers.mjs",
 		"download-ripgrep": "node scripts/download-ripgrep.mjs",
 		"postprotos": "biome format src/shared/proto src/core/controller src/hosts/ webview-ui/src/services src/generated --write --no-errors-on-unmatched",
@@ -319,7 +329,8 @@
 		"compile-tests": "node ./scripts/build-tests.js",
 		"watch-tests": "tsc -p . -w --outDir out",
 		"check-types": "npm run protos && npx tsc --noEmit && cd webview-ui && npx tsc -b --noEmit",
-		"lint": "biome lint --no-errors-on-unmatched --files-ignore-unknown=true --diagnostic-level=error && buf lint",
+		"lint": "biome lint --no-errors-on-unmatched --files-ignore-unknown=true --diagnostic-level=error && npm run lint:proto",
+		"lint:proto": "bash ./scripts/proto-lint.sh",
 		"format": "biome format --changed --no-errors-on-unmatched --files-ignore-unknown=true --diagnostic-level=error",
 		"format:fix": "biome check --changed --no-errors-on-unmatched --files-ignore-unknown=true --write",
 		"fix:all": "biome check --no-errors-on-unmatched --files-ignore-unknown=true --write --diagnostic-level=error --unsafe",
@@ -328,7 +339,7 @@
 		"pretest": "npm run compile && npm run compile-tests && npm run compile-standalone && npm run lint",
 		"test": "npm-run-all test:unit test:integration",
 		"test:integration": "vscode-test",
-		"test:unit": "cross-env TS_NODE_PROJECT=./tsconfig.unit-test.json mocha",
+		"test:unit": "cross-env TS_NODE_PROJECT=./tsconfig.unit-test.json mocha # Use `UPDATE_SNAPSHOTS=true npm run test:unit` to rebuild prompt snapshots",
 		"test:coverage": "vscode-test --coverage",
 		"test:sca-server": "npx tsx watch scripts/test-standalone-core-api-server.ts",
 		"test:tp-orchestrator": "npx tsx scripts/testing-platform-orchestrator.ts",
@@ -403,8 +414,8 @@
 	"dependencies": {
 		"@anthropic-ai/sdk": "^0.37.0",
 		"@anthropic-ai/vertex-sdk": "^0.6.4",
-		"@aws-sdk/client-bedrock-runtime": "^3.840.0",
-		"@aws-sdk/credential-providers": "^3.840.0",
+		"@aws-sdk/client-bedrock-runtime": "^3.922.0",
+		"@aws-sdk/credential-providers": "^3.922.0",
 		"@bufbuild/protobuf": "^2.2.5",
 		"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 		"@google-cloud/vertexai": "^1.9.3",
@@ -432,11 +443,12 @@
 		"@opentelemetry/sdk-trace-base": "^2.1.0",
 		"@opentelemetry/sdk-trace-node": "^1.30.1",
 		"@opentelemetry/semantic-conventions": "^1.37.0",
-		"@playwright/test": "^1.53.2",
+		"@playwright/test": "^1.55.1",
 		"@sap-ai-sdk/ai-api": "^1.17.0",
 		"@sap-ai-sdk/orchestration": "^1.17.0",
 		"@sentry/browser": "^9.12.0",
 		"@streamparser/json": "^0.0.22",
+		"@tailwindcss/vite": "^4.1.14",
 		"@types/uuid": "^10.0.0",
 		"@vscode/codicons": "^0.0.36",
 		"archiver": "^7.0.1",
@@ -456,14 +468,14 @@
 		"get-folder-size": "^5.0.0",
 		"globby": "^14.0.2",
 		"grpc-health-check": "^2.0.2",
-		"https-proxy-agent": "^7.0.6",
 		"iconv-lite": "^0.6.3",
 		"ignore": "^7.0.3",
 		"image-size": "^2.0.2",
 		"isbinaryfile": "^5.0.2",
 		"jschardet": "^3.1.4",
 		"jwt-decode": "^4.0.0",
-		"mammoth": "^1.8.0",
+		"mammoth": "^1.11.0",
+		"nanoid": "^5.1.6",
 		"nice-grpc": "^2.1.12",
 		"node-machine-id": "^1.1.12",
 		"ollama": "^0.5.13",
@@ -471,6 +483,7 @@
 		"open-graph-scraper": "^6.9.0",
 		"openai": "^4.83.0",
 		"os-name": "^6.0.0",
+		"p-mutex": "^1.0.0",
 		"p-timeout": "^6.1.4",
 		"p-wait-for": "^5.0.2",
 		"pdf-parse": "^1.1.1",
@@ -481,15 +494,20 @@
 		"serialize-error": "^11.0.3",
 		"simple-git": "^3.27.0",
 		"strip-ansi": "^7.1.2",
+		"tailwindcss": "^4.1.14",
 		"tree-sitter-wasms": "^0.1.11",
 		"ts-morph": "^25.0.1",
 		"turndown": "^7.2.0",
 		"ulid": "^2.4.0",
+		"undici": "^7.16.0",
 		"uuid": "^11.1.0",
 		"vscode-uri": "^3.1.0",
 		"web-tree-sitter": "^0.22.6",
 		"zod": "^3.24.2"
 	},
+	"overrides": {
+		"tar-fs": ">=3.1.1"
+	},
 	"c8": {
 		"reporter": [
 			"lcov",

proto/cline/account.proto

@@ -1,10 +1,12 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 // Service for account-related operations
 service AccountService {
@@ -12,20 +14,18 @@ service AccountService {
   // Generates a secure nonce for state validation, stores it in secrets,
   // and opens the authentication URL in the external browser.
   rpc accountLoginClicked(EmptyRequest) returns (String);
-    
+
   // Handles the user clicking the logout button in the UI.
   // Clears API keys and user state.
   rpc accountLogoutClicked(EmptyRequest) returns (Empty);
 
   // Subscribe to auth status update events (when authentication state changes)
-  rpc subscribeToAuthStatusUpdate(EmptyRequest) 
-      returns (stream AuthState);
-    
+  rpc subscribeToAuthStatusUpdate(EmptyRequest) returns (stream AuthState);
+
   // Handles authentication state changes from the Firebase context.
   // Updates the user info in global state and returns the updated value.
-  rpc authStateChanged(AuthStateChangedRequest) 
-      returns (AuthState);
-    
+  rpc authStateChanged(AuthStateChangedRequest) returns (AuthState);
+
   // Fetches all user credits data
   // (balance, usage transactions, payment transactions)
   rpc getUserCredits(EmptyRequest) returns (UserCreditsData);
@@ -40,6 +40,8 @@ service AccountService {
 
   rpc openrouterAuthClicked(EmptyRequest) returns (Empty);
 
+  rpc requestyAuthClicked(StringRequest) returns (Empty);
+
   // Returns a link the webview can use to redirect back to the user's IDE.
   rpc getRedirectUrl(EmptyRequest) returns (String);
 }

proto/cline/browser.proto

@@ -1,10 +1,12 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 service BrowserService {
   rpc getBrowserConnectionInfo(EmptyRequest) returns (BrowserConnectionInfo);

proto/cline/checkpoints.proto

@@ -1,11 +1,13 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
 import "google/protobuf/timestamp.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 service CheckpointsService {
   rpc checkpointDiff(Int64Request) returns (Empty);
@@ -31,13 +33,13 @@ message CheckpointEvent {
     CHECKPOINT_COMMIT = 1;
     CHECKPOINT_RESTORE = 2;
   }
-  
+
   OperationType operation = 1;
   string cwd_hash = 2;
   bool is_active = 3;
   google.protobuf.Timestamp timestamp = 4;
   optional string task_id = 5;
-  optional string commit_hash = 6;  
+  optional string commit_hash = 6;
 }
 
 message PathHashMap {

proto/cline/commands.proto

@@ -1,12 +1,14 @@
 syntax = "proto3";
 
 package cline;
-import "cline/common.proto";
-option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
-option java_multiple_files = true;
 
-// Service for running IDE commands, for example context menu actions, 
+import "cline/common.proto";
+
+option go_package = "github.com/cline/grpc-go/cline";
+option java_multiple_files = true;
+option java_package = "bot.cline.proto";
+
+// Service for running IDE commands, for example context menu actions,
 // commands, etc.
 // In contrast to the rest of the ProtoBus services, these are
 // intended to be called by the IDE directly instead of through the webview,

proto/cline/common.proto

@@ -1,18 +1,16 @@
 syntax = "proto3";
 
 package cline;
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
-message Metadata {
-}
+message Metadata {}
 
-message EmptyRequest {
-}
+message EmptyRequest {}
 
-message Empty {
-}
+message Empty {}
 
 message StringRequest {
   string value = 2;

proto/cline/dictation.proto

@@ -1,10 +1,12 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 service DictationService {
   rpc startRecording(EmptyRequest) returns (RecordingResult);

proto/cline/file.proto

@@ -1,10 +1,12 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 // Service for file-related operations
 service FileService {
@@ -13,10 +15,10 @@ service FileService {
 
   // Opens a file in the editor
   rpc openFile(StringRequest) returns (Empty);
- 
+
   // Opens an image in the system viewer
   rpc openImage(StringRequest) returns (Empty);
-  
+
   // Opens a mention (file, path, git commit, problem, terminal, or URL)
   rpc openMention(StringRequest) returns (Empty);
 
@@ -25,34 +27,37 @@ service FileService {
 
   // Creates a rule file from either global or workspace rules directory
   rpc createRuleFile(RuleFileRequest) returns (RuleFile);
-  
+
   // Search git commits in the workspace
   rpc searchCommits(StringRequest) returns (GitCommits);
 
   // Select images and other files from the file system and returns as data URLs & paths respectively
   rpc selectFiles(BooleanRequest) returns (StringArrays);
-  
+
   // Convert URIs to workspace-relative paths
   rpc getRelativePaths(RelativePathsRequest) returns (RelativePaths);
 
   // Search for files in the workspace with fuzzy matching
   rpc searchFiles(FileSearchRequest) returns (FileSearchResults);
-  
+
   // Toggle a Cline rule (enable or disable)
   rpc toggleClineRule(ToggleClineRuleRequest) returns (ToggleClineRules);
 
   // Toggle a Cursor rule (enable or disable)
   rpc toggleCursorRule(ToggleCursorRuleRequest) returns (ClineRulesToggles);
-  
+
   // Toggle a Windsurf rule (enable or disable)
   rpc toggleWindsurfRule(ToggleWindsurfRuleRequest) returns (ClineRulesToggles);
-  
+
+  // Toggle an Agents rule (enable or disable)
+  rpc toggleAgentsRule(ToggleAgentsRuleRequest) returns (ClineRulesToggles);
+
   // Refreshes all rule toggles (Cline, External, and Workflows)
   rpc refreshRules(EmptyRequest) returns (RefreshedRules);
 
   // Opens a task's conversation history file on disk
   rpc openDiskConversationHistory(StringRequest) returns (Empty);
-  
+
   // Toggles a workflow on or off
   rpc toggleWorkflow(ToggleWorkflowRequest) returns (ClineRulesToggles);
 
@@ -61,7 +66,7 @@ service FileService {
 
   // Open a file in editor by a relative path
   rpc openFileRelativePath(StringRequest) returns (Empty);
-  
+
   // Opens or creates a focus chain checklist markdown file for editing
   rpc openFocusChainFile(StringRequest) returns (Empty);
 }
@@ -72,15 +77,23 @@ message RefreshedRules {
   ClineRulesToggles local_cline_rules_toggles = 2;
   ClineRulesToggles local_cursor_rules_toggles = 3;
   ClineRulesToggles local_windsurf_rules_toggles = 4;
-  ClineRulesToggles local_workflow_toggles = 5;
-  ClineRulesToggles global_workflow_toggles = 6;
+  ClineRulesToggles local_agents_rules_toggles = 5;
+  ClineRulesToggles local_workflow_toggles = 6;
+  ClineRulesToggles global_workflow_toggles = 7;
 }
 
 // Request to toggle a Windsurf rule
 message ToggleWindsurfRuleRequest {
   Metadata metadata = 1;
-  string rule_path = 2;   // Path to the rule file
-  bool enabled = 3;       // Whether to enable or disable the rule
+  string rule_path = 2; // Path to the rule file
+  bool enabled = 3; // Whether to enable or disable the rule
+}
+
+// Request to toggle an Agents rule
+message ToggleAgentsRuleRequest {
+  Metadata metadata = 1;
+  string rule_path = 2; // Path to the rule file
+  bool enabled = 3; // Whether to enable or disable the rule
 }
 
 // Request to convert a list of URIs to relative paths
@@ -103,25 +116,25 @@ enum FileSearchType {
 // Request for file search operations
 message FileSearchRequest {
   Metadata metadata = 1;
-  string query = 2;                  // Search query string
-  optional string mentions_request_id = 3;  // Optional request ID for tracking requests
-  optional int32 limit = 4;          // Optional limit for results (default: 20)
-  optional FileSearchType selected_type = 5;  // Optional selected type filter
-  optional string workspace_hint = 6;  // Optional workspace name to search in
+  string query = 2; // Search query string
+  optional string mentions_request_id = 3; // Optional request ID for tracking requests
+  optional int32 limit = 4; // Optional limit for results (default: 20)
+  optional FileSearchType selected_type = 5; // Optional selected type filter
+  optional string workspace_hint = 6; // Optional workspace name to search in
 }
 
 // Result for file search operations
 message FileSearchResults {
-  repeated FileInfo results = 1;     // Array of file/folder results
-  optional string mentions_request_id = 2;  // Echo of the request ID for tracking
+  repeated FileInfo results = 1; // Array of file/folder results
+  optional string mentions_request_id = 2; // Echo of the request ID for tracking
 }
 
 // File information structure for search results
 message FileInfo {
-  string path = 1;                   // Relative path from workspace root
-  string type = 2;                   // "file" or "folder"
-  optional string label = 3;         // Display name (usually basename)
-  optional string workspace_name = 4;  // Workspace this result came from
+  string path = 1; // Relative path from workspace root
+  string type = 2; // "file" or "folder"
+  optional string label = 3; // Display name (usually basename)
+  optional string workspace_name = 4; // Workspace this result came from
 }
 
 // Response for searchCommits
@@ -141,25 +154,32 @@ message GitCommit {
 // Unified request for all rule file operations
 message RuleFileRequest {
   Metadata metadata = 1;
-  bool is_global = 2;            // Common field for all operations
+  bool is_global = 2; // Common field for all operations
   optional string rule_path = 3; // Path field for deleteRuleFile (optional)
-  optional string filename = 4;  // Filename field for createRuleFile (optional)
-  optional string type = 5;      // Type of the file to create (optional)
+  optional string filename = 4; // Filename field for createRuleFile (optional)
+  optional string type = 5; // Type of the file to create (optional)
 }
 
 // Result for rule file operations with meaningful data only
 message RuleFile {
-  string file_path = 1;     // Path to the rule file
-  string display_name = 2;  // Filename for display purposes
-  bool already_exists = 3;  // For createRuleFile, indicates if file already existed
+  string file_path = 1; // Path to the rule file
+  string display_name = 2; // Filename for display purposes
+  bool already_exists = 3; // For createRuleFile, indicates if file already existed
+}
+
+// Enum for rule scope (local, global, or remote)
+enum RuleScope {
+  LOCAL = 0;
+  GLOBAL = 1;
+  REMOTE = 2;
 }
 
 // Request to toggle a Cline rule
 message ToggleClineRuleRequest {
   Metadata metadata = 1;
-  bool is_global = 2;     // Whether this is a global rule or workspace rule
-  string rule_path = 3;   // Path to the rule file
-  bool enabled = 4;       // Whether to enable or disable the rule
+  RuleScope scope = 2; // Scope of the rule (local, global, or remote)
+  string rule_path = 3; // Path to the rule file
+  bool enabled = 4; // Whether to enable or disable the rule
 }
 
 // Maps from filepath to enabled/disabled status, matching app's ClineRulesToggles type
@@ -171,13 +191,14 @@ message ClineRulesToggles {
 message ToggleClineRules {
   ClineRulesToggles global_cline_rules_toggles = 1;
   ClineRulesToggles local_cline_rules_toggles = 2;
+  ClineRulesToggles remote_rules_toggles = 3;
 }
 
 // Request to toggle a Cursor rule
 message ToggleCursorRuleRequest {
   Metadata metadata = 1;
-  string rule_path = 2;   // Path to the rule file
-  bool enabled = 3;       // Whether to enable or disable the rule
+  string rule_path = 2; // Path to the rule file
+  bool enabled = 3; // Whether to enable or disable the rule
 }
 
 // Request to toggle a workflow on or off
@@ -185,5 +206,5 @@ message ToggleWorkflowRequest {
   Metadata metadata = 1;
   string workflow_path = 2;
   bool enabled = 3;
-  bool is_global = 4;
+  RuleScope scope = 4; // Scope of the workflow (local, global, or remote)
 }

proto/cline/hooks.proto

@@ -1,9 +1,10 @@
 syntax = "proto3";
 
 package cline;
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 // Input message for all hooks
 message HookInput {
@@ -28,7 +29,7 @@ message HookInput {
 // Output message for all hooks
 message HookOutput {
   string context_modification = 1;
-  bool should_continue = 2;
+  bool cancel = 2;
   string error_message = 3;
 }
 

proto/cline/mcp.proto

@@ -1,10 +1,12 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 service McpService {
   rpc toggleMcpServer(ToggleMcpServerRequest) returns (McpServers);
@@ -16,11 +18,12 @@ service McpService {
   rpc toggleToolAutoApprove(ToggleToolAutoApproveRequest) returns (McpServers);
   rpc refreshMcpMarketplace(EmptyRequest) returns (McpMarketplaceCatalog);
   rpc openMcpSettings(EmptyRequest) returns (Empty);
-  
+  rpc authenticateMcpServer(StringRequest) returns (Empty);
+
   // Subscribe to MCP marketplace catalog updates
   rpc subscribeToMcpMarketplaceCatalog(EmptyRequest) returns (stream McpMarketplaceCatalog);
   rpc getLatestMcpServers(Empty) returns (McpServers);
-  
+
   // Subscribe to MCP server updates
   rpc subscribeToMcpServers(EmptyRequest) returns (stream McpServers);
 }
@@ -41,6 +44,7 @@ message AddRemoteMcpServerRequest {
   Metadata metadata = 1;
   string server_name = 2;
   string server_url = 3;
+  optional string transport_type = 4;
 }
 
 message ToggleToolAutoApproveRequest {
@@ -72,7 +76,7 @@ message McpResourceTemplate {
 }
 
 enum McpServerStatus {
-  // Protobuf enums (in proto3) must have a zero value defined, which serves as the default if the field isn't explicitly set. 
+  // Protobuf enums (in proto3) must have a zero value defined, which serves as the default if the field isn't explicitly set.
   // To align with the required nature of the TypeScript type and avoid an unnecessary UNSPECIFIED state, we map one of the existing statuses to this zero value.
   MCP_SERVER_STATUS_DISCONNECTED = 0; // default
   MCP_SERVER_STATUS_CONNECTED = 1;
@@ -89,6 +93,8 @@ message McpServer {
   repeated McpResourceTemplate resource_templates = 7;
   optional bool disabled = 8;
   optional int32 timeout = 9;
+  optional bool oauth_required = 10;
+  optional string oauth_auth_status = 11;
 }
 
 message McpServers {

proto/cline/models.proto

@@ -1,11 +1,13 @@
 syntax = "proto3";
 
 package cline;
+
 import "cline/common.proto";
 import "google/protobuf/field_mask.proto";
+
 option go_package = "github.com/cline/grpc-go/cline";
-option java_package = "bot.cline.proto";
 option java_multiple_files = true;
+option java_package = "bot.cline.proto";
 
 // Service for model-related operations
 service ModelsService {
@@ -16,29 +18,33 @@ service ModelsService {
   // Fetches available models from VS Code LM API
   rpc getVsCodeLmModels(EmptyRequest) returns (VsCodeLmModelsArray);
   // Refreshes and returns OpenRouter models
-  rpc refreshOpenRouterModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
+  rpc refreshOpenRouterModelsRpc(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Refreshes and returns Hugging Face models
   rpc refreshHuggingFaceModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Refreshes and returns OpenAI models
   rpc refreshOpenAiModels(OpenAiModelsRequest) returns (StringArray);
-  // Refreshes and returns Vercel AI Gateway models
-  rpc refreshVercelAiGatewayModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Refreshes and returns Requesty models
   rpc refreshRequestyModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
+  // Refreshes and returns Hicap models
+  rpc refreshHicapModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Subscribe to OpenRouter models updates
   rpc subscribeToOpenRouterModels(EmptyRequest) returns (stream OpenRouterCompatibleModelInfo);
-  // Updates API configuration
+  // Updates API configuration (legacy - uses combined configuration)
   rpc updateApiConfigurationProto(UpdateApiConfigurationRequest) returns (Empty);
+  // Updates API configuration (new - uses separate options and secrets)
+  rpc updateApiConfiguration(UpdateApiConfigurationRequestNew) returns (Empty);
   // Updates API configuration with partial values (only updates fields that are explicitly set)
   rpc updateApiConfigurationPartial(UpdateApiConfigurationPartialRequest) returns (Empty);
   // Refreshes and returns Groq models
-  rpc refreshGroqModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
+  rpc refreshGroqModelsRpc(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Refreshes and returns Baseten models
-  rpc refreshBasetenModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
+  rpc refreshBasetenModelsRpc(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Fetches available models from SAP AI Core
   rpc getSapAiCoreModels(SapAiCoreModelsRequest) returns (SapAiCoreModelsResponse);
   // Fetches available models from OCA
   rpc refreshOcaModels(StringRequest) returns (OcaCompatibleModelInfo);
+  // Fetches available models from AIhubmix
+  rpc getAihubmixModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
 }
 
 // List of VS Code LM models
@@ -56,15 +62,15 @@ message LanguageModelChatSelector {
 
 // Price tier for tiered pricing models
 message PriceTier {
-  int64 token_limit = 1;  // Upper limit (inclusive) of input tokens for this price
-  double price = 2;       // Price per million tokens for this tier
+  int64 token_limit = 1; // Upper limit (inclusive) of input tokens for this price
+  double price = 2; // Price per million tokens for this tier
 }
 
 // Thinking configuration for models that support thinking/reasoning
 message ThinkingConfig {
-  optional int64 max_budget = 1;                    // Max allowed thinking budget tokens
-  optional double output_price = 2;                 // Output price per million tokens when budget > 0
-  repeated PriceTier output_price_tiers = 3;        // Optional: Tiered output price when budget > 0
+  optional int64 max_budget = 1; // Max allowed thinking budget tokens
+  optional double output_price = 2; // Output price per million tokens when budget > 0
+  repeated PriceTier output_price_tiers = 3; // Optional: Tiered output price when budget > 0
 }
 
 // Model tier for tiered pricing structures
@@ -90,6 +96,7 @@ message OpenRouterModelInfo {
   optional ThinkingConfig thinking_config = 10;
   optional bool supports_global_endpoint = 11;
   repeated ModelTier tiers = 12;
+  optional string name = 13;
 }
 
 // Shared response message for model information
@@ -120,35 +127,219 @@ message SapAiCoreModelDeployment {
   string deployment_id = 2;
 }
 
-
 // Response for SAP AI Core models with orchestration availability
 message SapAiCoreModelsResponse {
   repeated SapAiCoreModelDeployment deployments = 1;
   bool orchestration_available = 2;
 }
 
-// Request for updating API configuration
+// API secrets (credentials, API keys)
+message ModelsApiSecrets {
+  optional string api_key = 1;
+  optional string cline_api_key = 2;
+  optional string lite_llm_api_key = 3;
+  optional string open_router_api_key = 4;
+  optional string aws_access_key = 5;
+  optional string aws_secret_key = 6;
+  optional string aws_session_token = 7;
+  optional string aws_bedrock_api_key = 8;
+  optional string open_ai_api_key = 9;
+  optional string ollama_api_key = 10;
+  optional string gemini_api_key = 11;
+  optional string open_ai_native_api_key = 12;
+  optional string deep_seek_api_key = 13;
+  optional string requesty_api_key = 14;
+  optional string together_api_key = 15;
+  optional string fireworks_api_key = 16;
+  optional string qwen_api_key = 17;
+  optional string doubao_api_key = 18;
+  optional string mistral_api_key = 19;
+  optional string nebius_api_key = 20;
+  optional string asksage_api_key = 21;
+  optional string xai_api_key = 22;
+  optional string sambanova_api_key = 23;
+  optional string cerebras_api_key = 24;
+  optional string sap_ai_core_client_id = 25;
+  optional string sap_ai_core_client_secret = 26;
+  optional string moonshot_api_key = 27;
+  optional string cline_account_id = 28;
+  optional string groq_api_key = 29;
+  optional string hugging_face_api_key = 30;
+  optional string huawei_cloud_maas_api_key = 31;
+  optional string baseten_api_key = 32;
+  optional string zai_api_key = 33;
+  optional string vercel_ai_gateway_api_key = 34;
+  optional string dify_api_key = 35;
+  optional string oca_api_key = 36;
+  optional string oca_refresh_token = 37;
+  optional string minimax_api_key = 38;
+  optional string aihubmix_api_key = 39;
+}
+
+// API configuration options (non-secret settings)
+message ModelsApiOptions {
+  // Global configuration fields (not mode-specific)
+  optional string ulid = 1;
+  optional string lite_llm_base_url = 2;
+  optional bool lite_llm_use_prompt_cache = 3;
+  map<string, string> open_ai_headers = 4;
+  optional string anthropic_base_url = 5;
+  optional string open_router_provider_sorting = 6;
+  optional string aws_region = 7;
+  optional bool aws_use_cross_region_inference = 8;
+  optional bool aws_bedrock_use_prompt_cache = 9;
+  optional bool aws_use_profile = 10;
+  optional string aws_profile = 11;
+  optional string aws_bedrock_endpoint = 12;
+  optional string claude_code_path = 13;
+  optional string vertex_project_id = 14;
+  optional string vertex_region = 15;
+  optional string open_ai_base_url = 16;
+  optional string ollama_base_url = 17;
+  optional string ollama_api_options_ctx_num = 18;
+  optional string lm_studio_base_url = 19;
+  optional string gemini_base_url = 20;
+  optional string requesty_base_url = 21;
+  optional int64 fireworks_model_max_completion_tokens = 22;
+  optional int64 fireworks_model_max_tokens = 23;
+  optional string azure_api_version = 24;
+  optional string qwen_api_line = 25;
+  optional string asksage_api_url = 26;
+  optional int64 request_timeout_ms = 27;
+  optional string sap_ai_resource_group = 28;
+  optional string sap_ai_core_token_url = 29;
+  optional string sap_ai_core_base_url = 30;
+  optional bool sap_ai_core_use_orchestration_mode = 31;
+  optional string moonshot_api_line = 32;
+  optional string aws_authentication = 33;
+  optional string zai_api_line = 34;
+  optional string lm_studio_max_tokens = 35;
+  optional string qwen_code_oauth_path = 36;
+  optional string dify_base_url = 37;
+  optional string oca_base_url = 38;
+  optional string oca_mode = 39;
+  optional bool aws_use_global_inference = 40;
+  optional string minimax_api_line = 41;
+  optional string aihubmix_base_url = 42;
+  optional string aihubmix_app_code = 43;
+
+  // Plan mode configurations
+  optional ApiProvider plan_mode_api_provider = 100;
+  optional string plan_mode_api_model_id = 101;
+  optional int64 plan_mode_thinking_budget_tokens = 102;
+  optional string plan_mode_reasoning_effort = 103;
+  optional LanguageModelChatSelector plan_mode_vs_code_lm_model_selector = 104;
+  optional bool plan_mode_aws_bedrock_custom_selected = 105;
+  optional string plan_mode_aws_bedrock_custom_model_base_id = 106;
+  optional string plan_mode_open_router_model_id = 107;
+  optional OpenRouterModelInfo plan_mode_open_router_model_info = 108;
+  optional string plan_mode_open_ai_model_id = 109;
+  optional OpenAiCompatibleModelInfo plan_mode_open_ai_model_info = 110;
+  optional string plan_mode_ollama_model_id = 111;
+  optional string plan_mode_lm_studio_model_id = 112;
+  optional string plan_mode_lite_llm_model_id = 113;
+  optional LiteLLMModelInfo plan_mode_lite_llm_model_info = 114;
+  optional string plan_mode_requesty_model_id = 115;
+  optional OpenRouterModelInfo plan_mode_requesty_model_info = 116;
+  optional string plan_mode_together_model_id = 117;
+  optional string plan_mode_fireworks_model_id = 118;
+  optional string plan_mode_sap_ai_core_model_id = 119;
+  optional string plan_mode_sap_ai_core_deployment_id = 120;
+  optional string plan_mode_groq_model_id = 121;
+  optional OpenRouterModelInfo plan_mode_groq_model_info = 122;
+  optional string plan_mode_hugging_face_model_id = 123;
+  optional OpenRouterModelInfo plan_mode_hugging_face_model_info = 124;
+  optional string plan_mode_huawei_cloud_maas_model_id = 125;
+  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 126;
+  optional string plan_mode_baseten_model_id = 127;
+  optional OpenRouterModelInfo plan_mode_baseten_model_info = 128;
+  optional string plan_mode_vercel_ai_gateway_model_id = 129;
+  optional OpenRouterModelInfo plan_mode_vercel_ai_gateway_model_info = 130;
+  optional string plan_mode_oca_model_id = 131;
+  optional OcaModelInfo plan_mode_oca_model_info = 132;
+  optional string plan_mode_aihubmix_model_id = 133;
+  optional OpenAiCompatibleModelInfo plan_mode_aihubmix_model_info = 134;
+
+  // Act mode configurations
+  optional ApiProvider act_mode_api_provider = 200;
+  optional string act_mode_api_model_id = 201;
+  optional int64 act_mode_thinking_budget_tokens = 202;
+  optional string act_mode_reasoning_effort = 203;
+  optional LanguageModelChatSelector act_mode_vs_code_lm_model_selector = 204;
+  optional bool act_mode_aws_bedrock_custom_selected = 205;
+  optional string act_mode_aws_bedrock_custom_model_base_id = 206;
+  optional string act_mode_open_router_model_id = 207;
+  optional OpenRouterModelInfo act_mode_open_router_model_info = 208;
+  optional string act_mode_open_ai_model_id = 209;
+  optional OpenAiCompatibleModelInfo act_mode_open_ai_model_info = 210;
+  optional string act_mode_ollama_model_id = 211;
+  optional string act_mode_lm_studio_model_id = 212;
+  optional string act_mode_lite_llm_model_id = 213;
+  optional LiteLLMModelInfo act_mode_lite_llm_model_info = 214;
+  optional string act_mode_requesty_model_id = 215;
+  optional OpenRouterModelInfo act_mode_requesty_model_info = 216;
+  optional string act_mode_together_model_id = 217;
+  optional string act_mode_fireworks_model_id = 218;
+  optional string act_mode_sap_ai_core_model_id = 219;
+  optional string act_mode_sap_ai_core_deployment_id = 220;
+  optional string act_mode_groq_model_id = 221;
+  optional OpenRouterModelInfo act_mode_groq_model_info = 222;
+  optional string act_mode_hugging_face_model_id = 223;
+  optional OpenRouterModelInfo act_mode_hugging_face_model_info = 224;
+  optional string act_mode_huawei_cloud_maas_model_id = 225;
+  optional OpenRouterModelInfo act_mode_huawei_cloud_maas_model_info = 226;
+  optional string act_mode_baseten_model_id = 227;
+  optional OpenRouterModelInfo act_mode_baseten_model_info = 228;
+  optional string act_mode_vercel_ai_gateway_model_id = 229;
+  optional OpenRouterModelInfo act_mode_vercel_ai_gateway_model_info = 230;
+  optional string act_mode_oca_model_id = 231;
+  optional OcaModelInfo act_mode_oca_model_info = 232;
+  optional string act_mode_aihubmix_model_id = 233;
+  optional OpenAiCompatibleModelInfo act_mode_aihubmix_model_info = 234;
+}
+
+// Request for updating API configuration (legacy - uses combined configuration)
 message UpdateApiConfigurationRequest {
   Metadata metadata = 1;
   ModelsApiConfiguration api_configuration = 2;
 }
 
+// Combined API configuration containing both options and secrets
+message ApiConfiguration {
+  ModelsApiOptions options = 1;
+  ModelsApiSecrets secrets = 2;
+}
+
+// Request for updating API configuration (new - uses separate options and secrets)
+message UpdateApiConfigurationRequestNew {
+  Metadata metadata = 1;
+  ApiConfiguration updates = 2;
+
+  // Required field mask specifying which fields to update.
+  // Field paths use dot notation with camelCase field names:
+  // - "options.ulid" (for options fields)
+  // - "options.openAiHeaders" (for options fields)
+  // - "secrets.apiKey" (for secrets fields)
+  // - "secrets.openRouterApiKey" (for secrets fields)
+  repeated string update_mask = 3;
+}
+
 // Request for partially updating API configuration using FieldMask
 // Only fields specified in update_mask will be updated from api_configuration
 message UpdateApiConfigurationPartialRequest {
   Metadata metadata = 1;
-  
+
   // The API configuration with values to update.
   // Only fields listed in update_mask will be applied from this configuration.
   ModelsApiConfiguration api_configuration = 2;
-  
+
   // Mask specifying which top-level fields from api_configuration to update.
   // Field names should use camelCase (e.g., "apiKey", "planModeApiProvider").
   // If a field is in the mask but not set in api_configuration, it will be cleared (set to undefined).
   google.protobuf.FieldMask update_mask = 3;
 }
 
- // Model info for OCA (OpenAI-compatible) models exposed by the OCA provider
+// Model info for OCA (OpenAI-compatible) models exposed by the OCA provider
 message OcaModelInfo {
   // Maximum completion tokens per request supported by this model
   optional int64 max_tokens = 1;
@@ -182,7 +373,7 @@ message OcaModelInfo {
   string model_name = 17;
 }
 
- // Aggregated OCA model catalog keyed by model identifier
+// Aggregated OCA model catalog keyed by model identifier
 message OcaCompatibleModelInfo {
   // key: canonical model id as reported by OCA (e.g., "openai/gpt-4o-mini")
   // value: OcaModelInfo describing that model
@@ -228,6 +419,10 @@ enum ApiProvider {
   QWEN_CODE = 33;
   DIFY = 34;
   OCA = 35;
+  MINIMAX = 36;
+  HICAP = 37;
+  AIHUBMIX = 38;
+  NOUSRESEARCH = 39;
 }
 
 // Model info for OpenAI-compatible models
@@ -345,6 +540,14 @@ message ModelsApiConfiguration {
   optional string oca_refresh_token = 75;
   optional string oca_mode = 76;
   optional bool aws_use_global_inference = 77;
+  optional string minimax_api_key = 78;
+  optional string minimax_api_line = 79;
+  optional string hicap_model_id = 80;
+  optional string hicap_api_key = 81;
+  optional string aihubmix_api_key = 82;
+  optional string aihubmix_base_url = 83;
+  optional string aihubmix_app_code = 84;
+  optional string nous_research_api_key = 85;
 
   // Plan mode configurations
   optional ApiProvider plan_mode_api_provider = 100;
@@ -373,14 +576,18 @@ message ModelsApiConfiguration {
   optional string plan_mode_hugging_face_model_id = 123;
   optional OpenRouterModelInfo plan_mode_hugging_face_model_info = 124;
   optional string plan_mode_huawei_cloud_maas_model_id = 125;
-  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 126; 
+  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 126;
   optional string plan_mode_baseten_model_id = 127;
   optional OpenRouterModelInfo plan_mode_baseten_model_info = 128;
   optional string plan_mode_vercel_ai_gateway_model_id = 129;
   optional OpenRouterModelInfo plan_mode_vercel_ai_gateway_model_info = 130;
   optional string plan_mode_oca_model_id = 131;
   optional OcaModelInfo plan_mode_oca_model_info = 132;
-
+  optional string plan_mode_hicap_model_id = 133;
+  optional OpenRouterModelInfo plan_mode_hicap_model_info = 134;
+  optional string plan_mode_aihubmix_model_id = 135;
+  optional OpenAiCompatibleModelInfo plan_mode_aihubmix_model_info = 136;
+  optional string plan_mode_nous_research_model_id = 137;
 
   // Act mode configurations
   optional ApiProvider act_mode_api_provider = 200;
@@ -416,4 +623,9 @@ message ModelsApiConfiguration {
   optional OpenRouterModelInfo act_mode_vercel_ai_gateway_model_info = 230;
   optional string act_mode_oca_model_id = 231;
   optional OcaModelInfo act_mode_oca_model_info = 232;
+  optional string act_mode_hicap_model_id = 233;
+  optional OpenRouterModelInfo act_mode_hicap_model_info = 234;
+  optional string act_mode_aihubmix_model_id = 235;
+  optional OpenAiCompatibleModelInfo act_mode_aihubmix_model_info = 236;
+  optional string act_mode_nous_research_model_id = 237;
 }