npm audit fix

Regenerate the package-lock.json which was including packages that were previously removed from the package.json.
It removes extraneous eslint-plugin-eslint-rules package and clean up
package-lock.json by removing resolved URLs and integrity hashes for
Biome CLI platform-specific dependencies.

.changeset/breezy-shrimps-begin.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+fix showing the ai core exisiting models when resource group field is empty (using the default resource group)

.changeset/chilly-zebras-repeat.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Reset account view on sign out

.changeset/cuddly-dingos-tap.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fix issue on Account view where balance is fetched twice that cause janky UI

.changeset/cyan-bottles-battle.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fixes an issue where thinking text from litellm was not being passed through to Cline thinking UI

.changeset/fluffy-toys-beam.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fix Ollama connection issue to default endpoint at port 11434

.changeset/funny-ants-travel.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Optimized Cline for GPT-5 model family with an aligned system prompt

.changeset/healthy-waves-eat.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+REfactoring Tool Executor

.changeset/heavy-dolls-cry.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Add search functionality to API provider dropdown

.changeset/hip-chairs-wash.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Adding telemetry for terminal command issue

.changeset/hot-turtles-flash.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Remove disabled approve / reject buttons from UI.

.changeset/khaki-donuts-sneeze.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+Sync taskHistory across Cline instances so that it will update for all Cline instances when one instance creates, adds to, or deletes a task.

.changeset/late-fans-grow.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Adding a grpc recording class with its builder

.changeset/late-wasps-agree.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fixed minor bug where entering slash commands would result in the following word being removed from the chat text area

.changeset/lucky-keys-visit.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fix issue where editor panel gets reset to chat view on each chat input focus event

.changeset/orange-bees-itch.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Exclude dependency folders for deep-planning prompt

.changeset/pretty-apricots-help.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Sambanova provider: add DeepSeek-V3.1

.changeset/rare-oranges-flash.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Add "Use custom prompt" option to Ollama provider

.changeset/rare-suns-report.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+fetch deployment id in design-time instead of runtime

.changeset/real-ads-glow.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+add free grok-coder-free model to cline provider

.changeset/rich-berries-applaud.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Adding a new standalone core api server script for local and integration testing purposes

.changeset/slimy-kids-sip.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Fix AutoApproveModal overflowing issue

.changeset/small-lions-train.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Setup Raw Structure for implementing multi-workspace support with WorkspaceRoot

.changeset/smart-flowers-deny.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Dify.ai api integration

.changeset/stale-balloons-scream.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+support orchestration mode for sap provider

.changeset/swift-ravens-lay.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Improve Gemini Rate Limit handling

.changeset/weak-years-sin.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+fix: Support Anthropic Caching when using LiteLLM

.changeset/wise-seas-shave.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Reasoning Effort Minimal on OpenAI

.changeset/yellow-cycles-join.md

@@ -0,0 +1,5 @@
+---
+"claude-dev": patch
+---
+
+Prompt changes for deep-planning in windows/powershell

.codespellrc

@@ -1,6 +0,0 @@
-[codespell]
-# Ref: https://github.com/codespell-project/codespell#using-a-config-file
-skip = .git*,*.svg,package-lock.json,*.css,.codespellrc,locales
-check-hidden = true
-ignore-regex = (\b(optIn|isTaller)\b|https://\S+)
-# ignore-words-list =

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,64 +1,69 @@
 name: 🐛 Bug Report
 description: File a bug report
-labels: ["bug"]
+labels: ['bug']
 body:
-    - type: markdown
-      attributes:
-          value: |
-              **Important:** All bug reports must be reproducible using Claude 4 Sonnet. Cline uses complex prompts so less capable models may not work as expected.
-    - type: textarea
-      id: what-happened
-      attributes:
-          label: What happened?
-          description: Also tell us, what did you expect to happen?
-          placeholder: Tell us what you see!
-      validations:
-          required: true
-    - type: textarea
-      id: steps
-      attributes:
-          label: Steps to reproduce
-          description: How do you trigger this bug? Please walk us through it step by step.
-          value: |
-              1.
-              2.
-              3.
-      validations:
-          required: false
-    - type: textarea
-      id: logs
-      attributes:
-          label: Relevant API REQUEST output
-          description: Please copy and paste any relevant output. This will be automatically formatted into code, so no need for backticks.
-          render: shell
-    - type: input
-      id: provider-model
-      attributes:
-          label: Provider/Model
-          description: What provider and model were you using when the issue occurred?
-          placeholder: "e.g., cline:anthropic/claude-3.7-sonnet, gemini:gemini-2.5-pro-exp-03-25"
-      validations:
-          required: true
-    - type: textarea
-      id: system-info
-      attributes:
-          label: System Information
-          description: What operating system and hardware are you using?
-          placeholder: |
-              Operating System: Windows 11, macOS Sonoma, Ubuntu 22.04, etc.
-              Hardware: CPU, GPU, RAM specifications if relevant
-              e.g.,
-              OS: Windows 11
-              CPU: Intel Core i7-11700K
-              GPU: NVIDIA GeForce RTX 3070
-              RAM: 32GB DDR4
-      validations:
-          required: true
-    - type: input
-      id: cline-version
-      attributes:
-          label: Cline Version
-          description: What version of Cline are you using? (You can find this at the bottom of the Settings view)
-          placeholder: "e.g., 1.2.3"
-      validations:
-          required: true
+  - type: markdown
+    attributes:
+      value: |
+        **Important:** All bug reports must be reproducible using Claude Sonnet 4. Cline uses complex prompts so less capable models may not work as expected.
+  - type: dropdown
+    id: plugin-type
+    attributes:
+      label: Plugin Type
+      description: Which plugin are you reporting a bug for?
+      options:
+        - VSCode Extension
+        - JetBrains Plugin
+      default: 0
+    validations:
+      required: true
+  - type: input
+    id: cline-version
+    attributes:
+      label: Cline Version
+      description: What version of Cline are you using? (You can find this at the bottom of the Settings view)
+      placeholder: 'e.g., 1.2.3'
+    validations:
+      required: true
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What happened?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to reproduce
+      description: How do you trigger this bug? Please walk us through it step by step.
+      value: |
+        1.
+        2.
+        3.
+    validations:
+      required: false
+  - type: input
+    id: provider-model
+    attributes:
+      label: Provider/Model
+      description: What provider and model were you using when the issue occurred?
+      placeholder: 'e.g., cline:anthropic/claude-sonnet-4, gemini:gemini-2.5-pro-exp-03-25'
+    validations:
+      required: false
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Information
+      description: What operating system and hardware are you using?
+      placeholder: |
+        Operating System: Windows 11, macOS Sonoma, Ubuntu 22.04, etc.
+        Hardware: CPU, GPU, RAM specifications if relevant
+        e.g.,
+        OS: Windows 11
+        CPU: Intel Core i7-11700K
+        GPU: NVIDIA GeForce RTX 3070
+        RAM: 32GB DDR4
+    validations:
+      required: false

.github/workflows/build.yml

@@ -1,68 +0,0 @@
-name: "Build Extension"
-
-on:
-    push:
-        branches:
-            - main
-
-jobs:
-    test:
-        uses: ./.github/workflows/test.yml
-    build:
-        needs: test
-        name: Build Extension
-        runs-on: ${{ github.repository == 'cline/cline' && 'high-capacity-runner' || 'ubuntu-latest' }}
-
-        steps:
-            - uses: actions/checkout@v4
-
-            - name: Setup Node.js
-              uses: actions/setup-node@v4
-              with:
-                  node-version: "lts/*"
-
-            - name: Cache root dependencies
-              uses: actions/cache@v4
-              id: root-cache
-              with:
-                  path: node_modules
-                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
-
-            # Cache webview-ui dependencies - only reuse if package-lock.json exactly matches
-            - name: Cache webview-ui dependencies
-              uses: actions/cache@v4
-              id: webview-cache
-              with:
-                  path: webview-ui/node_modules
-                  key: ${{ runner.os }}-npm-webview-${{ hashFiles('webview-ui/package-lock.json') }}
-
-            - name: Install root dependencies
-              if: steps.root-cache.outputs.cache-hit != 'true'
-              run: npm ci --include=optional
-
-            - name: Install webview-ui dependencies
-              if: steps.webview-cache.outputs.cache-hit != 'true'
-              run: cd webview-ui && npm ci --include=optional
-
-            - name: Install Publishing Tools
-              run: npm install -g @vscode/vsce ovsx
-
-            - name: Set Variables
-              id: set_variables
-              run: |
-                  VERSION=$(node -p "require('./package.json').version")
-                  echo "version=$VERSION" >> $GITHUB_OUTPUT
-                  SHORT_SHA=$(git rev-parse --short HEAD)
-                  echo "short_sha=$SHORT_SHA" >> $GITHUB_OUTPUT
-                  echo "file_path=cline-${VERSION}-${SHORT_SHA}.vsix" >> $GITHUB_OUTPUT
-
-            - name: Package Extension
-              run: |
-                  echo "Packaging extension with version ${{ steps.set_variables.outputs.version }}"
-                  vsce package --out "${{ steps.set_variables.outputs.file_path }}"
-
-            - name: Upload Artifact
-              uses: actions/upload-artifact@v4
-              with:
-                  name: vsix-package
-                  path: ${{ steps.set_variables.outputs.file_path }}

.github/workflows/codespell.yml

@@ -1,28 +0,0 @@
-# Codespell configuration is within .codespellrc
----
-name: Codespell
-
-on:
-    push:
-        branches: [main]
-    pull_request:
-        branches: [main]
-
-permissions:
-    contents: read
-
-jobs:
-    codespell:
-        if: false
-        name: Check for spelling errors
-        runs-on: ubuntu-latest
-
-        steps:
-            - name: Checkout
-              uses: actions/checkout@v4
-            - name: Annotate locations with typos
-              uses: codespell-project/codespell-problem-matcher@v1
-            - name: Codespell
-              uses: codespell-project/actions-codespell@v2
-              with:
-                  only_warn: 1

.github/workflows/publish.yml

@@ -23,7 +23,11 @@ permissions:
     pull-requests: write
 
 jobs:
+    test:
+        uses: ./.github/workflows/test.yml
+
     publish:
+        needs: test
         name: Publish Extension
         runs-on: ubuntu-latest
         environment: publish
@@ -38,6 +42,30 @@ jobs:
               with:
                   node-version: "lts/*"
 
+            # Cache root dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache root dependencies
+              uses: actions/cache@v4
+              id: root-cache
+              with:
+                  path: node_modules
+                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
+
+            # Cache webview-ui dependencies - only reuse if package-lock.json exactly matches
+            - name: Cache webview-ui dependencies
+              uses: actions/cache@v4
+              id: webview-cache
+              with:
+                  path: webview-ui/node_modules
+                  key: ${{ runner.os }}-npm-webview-${{ hashFiles('webview-ui/package-lock.json') }}
+
+            - name: Install root dependencies
+              if: steps.root-cache.outputs.cache-hit != 'true'
+              run: npm ci --include=optional
+
+            - name: Install webview-ui dependencies
+              if: steps.webview-cache.outputs.cache-hit != 'true'
+              run: cd webview-ui && npm ci --include=optional
+
             - name: Install Publishing Tools
               run: npm install -g @vscode/vsce ovsx
 
@@ -62,48 +90,15 @@ jobs:
 
                   echo "Tag '$TAG' validated successfully"
 
-            - name: Download Artifact
-              id: download_artifact
-              timeout-minutes: 30
-              env:
-                  GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-              run: |
-                  TAG="${{ github.event.inputs.tag }}"
-                  COMMIT_SHA=$(git rev-parse "$TAG")
-
-                  while true; do
-                    RUN_ID=$(gh run list \
-                    --workflow="Build Extension" \
-                    --commit="${COMMIT_SHA}" \
-                    --status=success \
-                    --limit=1 \
-                    --json databaseId \
-                    --jq '.[0].databaseId')
-                    
-                    if [ -n "$RUN_ID" ]; then
-                      echo "Build completed! Downloading artifact..."
-
-                      gh run download $RUN_ID --name vsix-package
-                      exit 0
-                    fi
-                    
-                    echo "Waiting for build..."
-                    sleep 10
-                  done
-
-            - name: Set VSIX Path
-              id: set_vsix_path
-              run: |
-                  FILE_PATH=$(ls *.vsix | head -n 1)
-                  echo "VSIX_PATH=$FILE_PATH" >> $GITHUB_OUTPUT
-
             - name: Package and Publish Extension
               env:
                   VSCE_PAT: ${{ secrets.VSCE_PAT }}
                   OVSX_PAT: ${{ secrets.OVSX_PAT }}
                   CLINE_ENVIRONMENT: production
-                  VSIX_PATH: ${{ steps.set_vsix_path.outputs.VSIX_PATH }}
               run: |
+                  # Required to generate the .vsix
+                  vsce package  --allow-package-secrets sendgrid --out "cline-${{ steps.get_version.outputs.version }}.vsix"
+
                   if [ "${{ github.event.inputs.release-type }}" = "pre-release" ]; then
                     npm run publish:marketplace:prerelease
                     echo "Successfully published pre-release version ${{ steps.get_version.outputs.version }} to VS Code Marketplace and Open VSX Registry"

.github/workflows/scenario.yml

@@ -1,140 +0,0 @@
-name: Scenario Tests
-
-on:
-    push:
-        branches:
-            - main
-    pull_request:
-        types: [opened, reopened, synchronize, ready_for_review]
-    workflow_dispatch:
-
-concurrency:
-    group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-    cancel-in-progress: true
-
-jobs:
-    matrix_prep:
-        runs-on: ubuntu-latest
-        permissions:
-            id-token: write
-            contents: read
-        outputs:
-            matrix: ${{ steps.set-matrix.outputs.matrix }}
-        steps:
-            - id: set-matrix
-              run: |
-                  echo 'matrix=[{"runner":"ubuntu"},{"runner":"windows"},{"runner":"macos"}]' >> $GITHUB_OUTPUT
-
-    validate-scenario:
-        runs-on: ubuntu-latest
-        permissions:
-            contents: read
-        steps:
-            - uses: actions/checkout@v4
-            - name: Validate PR-specific scenario metadata
-              run: |
-                  if [ "${{ github.event_name }}" != "pull_request" ]; then
-                    echo "Not a pull_request event; skipping scenario validation."
-                    exit 0
-                  fi
-                  bash scripts/validate-scenario.sh "${{ github.event.number }}"
-
-    scenarios:
-        needs: [matrix_prep, validate-scenario]
-        strategy:
-            fail-fast: false
-            matrix:
-                include: ${{ fromJson(needs.matrix_prep.outputs.matrix) }}
-        runs-on: ${{ matrix.runner }}-latest
-        timeout-minutes: 20
-        permissions:
-            id-token: write
-            contents: read
-        steps:
-            - uses: actions/checkout@v4
-
-            - name: Setup Node.js environment
-              uses: actions/setup-node@v4
-              with:
-                  node-version: 22
-
-            # Cache root dependencies - only reuse if package-lock.json exactly matches
-            - name: Cache root dependencies
-              uses: actions/cache@v4
-              id: root-cache
-              with:
-                  path: node_modules
-                  key: ${{ runner.os }}-npm-${{ hashFiles('package-lock.json') }}
-
-            # Cache webview-ui dependencies - only reuse if package-lock.json exactly matches
-            - name: Cache webview-ui dependencies
-              uses: actions/cache@v4
-              id: webview-cache
-              with:
-                  path: webview-ui/node_modules
-                  key: ${{ runner.os }}-npm-webview-${{ hashFiles('webview-ui/package-lock.json') }}
-
-            # Cache VS Code installation
-            - name: Cache VS Code
-              uses: actions/cache@v4
-              id: vscode-cache
-              with:
-                  path: .vscode-test
-                  key: vscode-${{ runner.os }}-stable-${{ hashFiles('.vscode-test.mjs', 'package.json') }}
-                  restore-keys: |
-                      vscode-${{ runner.os }}-stable-
-
-            # Cache Playwright browsers
-            - name: Cache Playwright browsers
-              uses: actions/cache@v4
-              id: playwright-cache
-              with:
-                  path: |
-                      ~/.cache/ms-playwright
-                      ~/Library/Caches/ms-playwright
-                      ~/AppData/Local/ms-playwright
-                  key: playwright-browsers-${{ runner.os }}-${{ hashFiles('package-lock.json') }}
-                  restore-keys: |
-                      playwright-browsers-${{ runner.os }}-
-
-            - name: Install root dependencies
-              if: steps.root-cache.outputs.cache-hit != 'true'
-              run: npm ci
-
-            - name: Install webview-ui dependencies
-              if: steps.webview-cache.outputs.cache-hit != 'true'
-              run: cd webview-ui && npm ci
-
-            - name: Install xvfb on Linux
-              if: matrix.runner == 'ubuntu'
-              run: sudo apt-get update && sudo apt-get install -y xvfb
-
-            # Run optimized Scenario tests (reuses build steps like e2e)
-            - name: Run Scenario tests - Linux
-              if: matrix.runner == 'ubuntu'
-              run: xvfb-run -a npm run test:scenarios:optimal
-
-            - name: Run Scenario tests - Non-Linux
-              if: matrix.runner != 'ubuntu'
-              run: npm run test:scenarios:optimal
-
-            - uses: actions/upload-artifact@v4
-              if: ${{ failure() }}
-              with:
-                  name: playwright-recordings-${{ matrix.runner }}
-                  path: |
-                      test-results/playwright/
-
-    scenario-summary:
-        needs: scenarios
-        permissions: {}
-        runs-on: ubuntu-latest
-        if: always()
-        steps:
-            - name: Check all scenarios passed
-              run: |
-                  if [ "${{ needs.scenarios.result }}" != "success" ]; then
-                    echo "Some scenario tests failed"
-                    exit 1
-                  fi
-                  echo "All scenario tests passed successfully"

.mocharc.json

@@ -3,13 +3,13 @@
 		"ts"
 	],
 	"spec": [
-		"src/**/__tests__/*.ts",
-		"eslint-rules/__tests__/**/*.test.ts"
+		"src/**/__tests__/*.ts"
 	],
 	"require": [
 		"ts-node/register",
 		"source-map-support/register",
 		"./src/test/requires.ts"
 	],
-	"recursive": true
+	"recursive": true,
+	"exit": true
 }

.vscode/launch.json

@@ -91,7 +91,7 @@
 		{
 			"type": "node",
 			"request": "launch",
-			"name": "Run cline-core service",
+			"name": "Debug Test Standalone Core Api Server (test:sca-server)",
 			"skipFiles": [
 				"<node_internals>/**"
 			],
@@ -100,18 +100,62 @@
 				"${workspaceFolder}/**",
 				"!**/node_modules/**"
 			],
-			"cwd": "${workspaceFolder}/dist-standalone",
+			"cwd": "${workspaceFolder}",
 			"outFiles": [
+				"${workspaceFolder}/dist/**/*.js",
 				"${workspaceFolder}/dist-standalone/**/*.js"
 			],
 			"preLaunchTask": "compile-standalone",
+			"runtimeExecutable": "npx",
+			"runtimeArgs": [
+				"tsx"
+			],
+			"program": "scripts/test-standalone-core-api-server.ts",
 			"env": {
-				// Turns on grpc debug log.
-				//"GRPC_TRACE": "all",
-				//"GRPC_VERBOSITY": "DEBUG",
-				"NODE_PATH": "${workspaceFolder}/dist-standalone/node_modules"
+				"PROTOBUS_PORT": "26040",
+				"HOSTBRIDGE_PORT": "26041",
+				"WORKSPACE_DIR": "${workspaceFolder}",
+				"E2E_TEST": "true",
+				"CLINE_ENVIRONMENT": "local"
 			},
-			"program": "cline-core.js"
+			"console": "integratedTerminal",
+			"internalConsoleOptions": "neverOpen"
+		},
+		{
+			"type": "node",
+			"request": "launch",
+			"name": "Debug Current Test File",
+			"skipFiles": [
+				"<node_internals>/**"
+			],
+			"sourceMaps": true,
+			"resolveSourceMapLocations": [
+				"${workspaceFolder}/**",
+				"!**/node_modules/**"
+			],
+			"cwd": "${workspaceFolder}",
+			"runtimeExecutable": "npx",
+			"runtimeArgs": [
+				"mocha"
+			],
+			"args": [
+				"--require",
+				"ts-node/register",
+				"--require",
+				"source-map-support/register",
+				"--require",
+				"./src/test/requires.ts",
+				"--exit",
+				"${file}"
+			],
+			"env": {
+				"TS_NODE_PROJECT": "./tsconfig.unit-test.json",
+				"NODE_ENV": "test",
+				"IS_DEV": "true",
+				"CLINE_ENVIRONMENT": "local"
+			},
+			"console": "integratedTerminal",
+			"internalConsoleOptions": "openOnSessionStart"
 		}
 	]
 }

.vscode/settings.json

@@ -21,16 +21,5 @@
 	},
 	// Enable Lint and format using Biome
 	"biome.enabled": true,
-	"[typescript]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	},
-	"[typescriptreact]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	},
-	"[jsonc]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	},
-	"[json]": {
-		"editor.defaultFormatter": "biomejs.biome"
-	}
+	"editor.defaultFormatter": "biomejs.biome"
 }

CHANGELOG.md

@@ -1,5 +1,36 @@
 # Changelog
 
+## [3.27.1]
+
+- Add new Kimi K2 model to groq and moonshot providers
+
+## [3.27.0]
+
+- Fix `grok-code-fast-1` model information
+- Add call to action for trying free `grok-code-fast-1` in Announcement banner
+
+## [3.26.7]
+
+- Add 200k context window variant for Claude Sonnet 4 to OpenRouter and Cline providers
+
+## [3.26.6]
+
+- Add free Grok Coder model to Cline provider for users looking for a fast, free coding model option
+- Fix GPT-5 models not respecting auto-compact setting when enabled, improving context window management
+- Fix provider retry attempts not showing proper user feedback during rate limiting scenarios
+- Improve markdown and code block styling to automatically adapt when switching VS Code themes
+
+## [3.26.5]
+
+- fix (provider/vercel-ai-gateway): reduce model list load frequency in settings view
+- Fix OVSX publish command to resolve deployment failure
+
+## [3.26.4]
+
+- Update nebius ai studio models
+- Update sap provider - support reasoning effort for open ai models
+- Fix Claude 4 image input in SAP AI Core Provider
+
 ## [3.26.3]
 
 - Add compact system prompt option for LM Studio and Ollama models, optimized for smaller context windows (8k or less)

README.md

@@ -30,9 +30,9 @@ English | <a href="https://github.com/cline/cline/blob/main/locales/es/README.md
 </table>
 </div>
 
-Meet Cline (pronounced /klaɪn/, like "Klein"), an AI assistant that can use your **CLI** a**N**d **E**ditor.
+Meet Cline, an AI assistant that can use your **CLI** a**N**d **E**ditor.
 
-Thanks to [Claude 3.7 Sonnet's agentic coding capabilities](https://www.anthropic.com/claude/sonnet), Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support. Cline can even use the Model Context Protocol (MCP) to create new tools and extend his own capabilities. While autonomous AI scripts traditionally run in sandboxed environments, this extension provides a human-in-the-loop GUI to approve every file change and terminal command, providing a safe and accessible way to explore the potential of agentic AI.
+Thanks to [Claude Sonnet's agentic coding capabilities](https://www.anthropic.com/claude/sonnet), Cline can handle complex software development tasks step-by-step. With tools that let him create & edit files, explore large projects, use the browser, and execute terminal commands (after you grant permission), he can assist you in ways that go beyond code completion or tech support. Cline can even use the Model Context Protocol (MCP) to create new tools and extend his own capabilities. While autonomous AI scripts traditionally run in sandboxed environments, this extension provides a human-in-the-loop GUI to approve every file change and terminal command, providing a safe and accessible way to explore the potential of agentic AI.
 
 1. Enter your task and add images to convert mockups into functional apps or fix bugs with screenshots.
 2. Cline starts by analyzing your file structure & source code ASTs, running regex searches, and reading relevant files to get up to speed in existing projects. By carefully managing what information is added to context, Cline can provide valuable assistance even for large, complex projects without overwhelming the context window.
@@ -87,7 +87,7 @@ All changes made by Cline are recorded in your file's Timeline, providing an eas
 
 ### Use the Browser
 
-With Claude 3.5 Sonnet's new [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) capability, Cline can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.
+With Claude Sonnet's new [Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) capability, Cline can launch a browser, click elements, type text, and scroll, capturing screenshots and console logs at each step. This allows for interactive debugging, end-to-end testing, and even general web use! This gives him autonomy to fixing visual bugs and runtime issues without you needing to handhold and copy-pasting error logs yourself.
 
 Try asking Cline to "test the app", and watch as he runs a command like `npm run dev`, launches your locally running dev server in a browser, and performs a series of tests to confirm that everything works. [See a demo here.](https://x.com/sdrzn/status/1850880547825823989)
 

biome.jsonc

@@ -37,7 +37,8 @@
 				"useYield": "off",
 				"noConstructorReturn": "off",
 				"noInvalidPositionAtImportRule": "off",
-				"noSwitchDeclarations": "off"
+				"noSwitchDeclarations": "off",
+				"noUnusedImports": "error"
 			},
 			"a11y": "off",
 			"style": {
@@ -134,7 +135,12 @@
 				"**",
 				"!**/hosts/vscode/**",
 				"!**/test/**",
-				"!src/extension.ts"
+				"!**/*.test.ts",
+				"!src/dev/**",
+				"!src/extension.ts",
+				"!src/integrations/git/commit-message-generator.ts",
+				"!src/integrations/terminal/**",
+				"!src/core/controller/ui/openWalkthrough.ts"
 			],
 			"plugins": [
 				"src/dev/grit/vscode-api.grit"
@@ -147,6 +153,7 @@
 				"!src/core/storage/FileContextTracker.ts",
 				"!src/core/context/context-tracking/FileContextTracker.ts",
 				"!src/common.ts",
+				"!src/services/logging/distinctId.ts",
 				"!src/core/storage/utils/state-helpers.ts",
 				"!src/extension.ts"
 			],

docs/docs.json

@@ -60,6 +60,7 @@
 					"getting-started/what-is-cline",
 					"getting-started/model-selection-guide",
 					"getting-started/installing-cline",
+					"getting-started/installing-cline-jetbrains",
 					"getting-started/task-management",
 					"getting-started/understanding-context-management",
 					{

docs/getting-started/installing-cline-jetbrains.mdx

@@ -0,0 +1,135 @@
+---
+title: "Installing Cline for JetBrains (Early Access)"
+description: "Get early access to Cline in your favorite JetBrains IDE with the same powerful AI assistance you know from VSCode."
+---
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/jetbrains-logo.svg"
+		alt="JetBrains logo"
+		style={{ width: "200px", height: "auto", margin: "0 auto 20px auto", display: "block" }}
+	/>
+</Frame>
+
+Cline for JetBrains works almost identically to Cline in VSCode. All the core features work properly: diff editing, using tools, logging in with different providers, MCP servers, Cline rules and workflows, and more.
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/jetbrains-demo-hifi.gif"
+		alt="Cline running in JetBrains IDE showing AI assistance"
+	/>
+</Frame>
+
+<Note>Cline for JetBrains is in early access. All core features are functional, with ongoing improvements based on user feedback.</Note>
+
+## Installation
+
+As part of our early access program, Cline for JetBrains is available through direct download before its official marketplace release. You'll need to install it manually from a downloaded file:
+
+### Manual Installation from Disk
+
+1. **Download the Plugin:**
+   - Go to [https://plugins.jetbrains.com/plugin/28247-cline/versions/eap](https://plugins.jetbrains.com/plugin/28247-cline/versions/eap)
+   - Click **Download** to get the `.zip` file
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-marketplace-download.png"
+		alt="JetBrains plugin marketplace showing Cline download page"
+	/>
+</Frame>
+
+2. **Install from Disk:**
+   - Open your JetBrains IDE
+   - Go to **IntelliJ IDEA** (or whichever IDE you are in) → **Settings**
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-settings.png"
+		alt="JetBrains IDE settings dialog"
+	/>
+</Frame>
+
+   - Select **Plugins** from the left sidebar
+   - Click the gear icon ⚙️ and select **Install Plugin from Disk...**
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-install-disk.png"
+		alt="JetBrains IDE settings showing Install Plugin from Disk option"
+	/>
+</Frame>
+
+   - Select the downloaded `.zip` file
+
+<Frame>
+	<img
+		src="https://storage.googleapis.com/cline_public_images/docs/assets/cline-jetbrains-zip-file.png"
+		alt="File selection dialog showing Cline plugin zip file"
+	/>
+</Frame>
+
+   - Restart your IDE when prompted
+
+## Getting Started with Cline
+
+After installation, you'll find Cline in your IDE:
+
+1. **Open Cline:**
+   - Look for the Cline tool window (usually on the right side)
+   - Or go to **View** → **Tool Windows** → **Cline**
+
+2. **Sign In (optional, BYOK is also available):**
+   - Click **Sign In** in the Cline panel
+   - You'll be taken to [app.cline.bot](https://app.cline.bot) to create your account
+   - No credit card needed to get started with free credits
+
+3. **Start Coding:**
+   - Try this first prompt: "Hey Cline! Can you help me create a simple Hello World program in this project?"
+
+## Key Differences from VSCode
+
+While Cline for JetBrains includes all the same powerful features, there's one important difference to be aware of:
+
+**Terminal Integration:** The terminal inside JetBrains isn't integrated with Cline the same way it is in VSCode. Cline can execute commands, but the output will only appear in the webview if you expand the **Command Output** section.
+
+This means:
+- Commands still run successfully
+- You can see the output by clicking to expand Command Output in the chat
+- Terminal commands work the same way, just with a different display
+
+## What Works
+
+Everything else works exactly like VSCode:
+
+- **Diff Editing:** Cline can read, write, and edit files with the same precision
+- **Tool Usage:** All of Cline's tools (file operations, web browsing, etc.) work identically  
+- **API Providers:** Connect to Anthropic, OpenAI, local models, and more
+- **MCP Servers:** Full support for Model Context Protocol servers
+- **Cline Rules:** Custom instructions and workflows work the same way
+- **@ Mentions:** Reference files, folders, problems, and more
+- **Drag & Drop:** Add files and images to conversations
+
+## Tips for JetBrains Users
+
+- **Project Context:** Cline automatically understands your project structure, just like in VSCode
+- **Language Support:** Cline works with any language your JetBrains IDE supports
+- **Debugging Help:** Share error messages and stack traces directly in the chat
+- **Code Review:** Ask Cline to review your code changes before committing
+
+## Troubleshooting
+
+If you don't see the Cline tool window after installation:
+- Restart your IDE completely
+- Check **View** → **Tool Windows** → **Cline**
+- Ensure the plugin is enabled in **Settings** → **Plugins**
+
+Having other issues? Join our [Discord community](https://discord.gg/cline) for help from the team and other users.
+
+## Next Steps
+
+Now that you have Cline installed, you might want to:
+- Learn about [model selection](/getting-started/model-selection-guide) to choose the best AI provider
+- Explore [@ mentions](/features/at-mentions/overview) to reference files and context efficiently  
+- Set up [Cline rules](/features/cline-rules) for your specific workflow
+- Try [MCP servers](/mcp/mcp-overview) to extend Cline's capabilities

docs/hubspot.js

@@ -0,0 +1,14 @@
+// HubSpot Tracking Code for Cline Documentation
+(function() {
+  // Check if HubSpot script is already loaded to prevent duplicates
+  if (!document.getElementById('hs-script-loader')) {
+    var script = document.createElement('script');
+    script.type = 'text/javascript';
+    script.id = 'hs-script-loader';
+    script.async = true;
+    script.src = 'https://js-na2.hs-scripts.com/243656267.js';
+    
+    // Append the script to the document head
+    document.head.appendChild(script);
+  }
+})();

docs/provider-config/sap-aicore.mdx

@@ -7,12 +7,13 @@ SAP AI Core and the generative AI hub help you to integrate LLMs and AI into new
 
 **Website:** [SAP Help Portal](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/what-is-sap-ai-core)
 
-### Getting a Service Binding
 
 > 💡 **Information**
 >
 > SAP AI Core, and Generative AI Hub, are offerings from SAP BTP.
-> You need an active SAP BTP contract and a existing subaccount with a SAP AI Core instance to perform these steps.
+> You need an active SAP BTP contract and a existing subaccount with a SAP AI Core instance with the `extended` service plan (For more details about SAP AI Core service plans and their capabilities, see the [Service Plans documentation](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/service-plans)) to perform these steps.
+
+### Getting a Service Binding
 
 1. **Access:** Go to your subaccount via [BTP Cloud Cockpit](cockpit.btp.cloud.sap/cockpit)
 2. **Create a Service Binding:** Go to "Instances and Subscriptions", select your SAP AI Core service instance and click on Service Bindings > Create.
@@ -32,11 +33,44 @@ Refer to the [Generative AI Hub Supported Models page](https://me.sap.com/notes/
 5.  **Enter Base URL:** Add the `.serviceurls.AI_API_URL` field from the service binding into the "AI Core Base URL" field.
 6.  **Enter Auth URL:** Add the `.url` field from the service binding into the "AI Core Auth URL" field.
 7.  **Enter Resource Group:** Add the resource group where you have your model deployments. See [Create a Deployment for a Generative AI Model](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-generative-ai-model-in-sap-ai-core).
-8.  **Select Model:** Choose your desired model from the "Model" dropdown.
+8.  **Configure Orchestration Mode:** If you have an `extended` service plan, the "Orchestration Mode" checkbox will automatically appear.
+9.  **Select Model:** Choose your desired model from the "Model" dropdown.
+
+### Orchestration Mode vs Native API
+
+**Orchestration Mode:**
+- **Simplified usage:** Provides access to all available models without requiring individual deployments using the [Harmonized API](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/harmonized-api)
+
+**Native API Mode:**
+- **Manual deployments:** Requires manual model deployment and management in your SAP AI Core service instance
 
 ### Tips and Notes
 
--   **Model Selection:** The model dropdown displays models in two separate lists:
-    -   **Deployed Models:** These models are already deployed in your specified resource group and are ready to use immediately.
-    -   **Not Deployed Models:** These models don't have active deployments in your specified resource group. You won't be able to use these models until you create deployments for them in SAP AI Core.
--   **Creating Deployments:** To use a not deployed model, you'll need to create a deployment in your resource group in sap ai core service instance. See [Create a Deployment for a Generative AI Model](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-generative-ai-model-in-sap-ai-core) for instructions.
+- **Service Plan Requirement:** You must have the SAP AI Core `extended` service plan to use LLMs with Cline. Other service plans do not provide access to Generative AI Hub.
+
+- **Orchestration Mode (Recommended):** Keep Orchestration Mode enabled for the simplest setup. It provides automatic access to all available models without requiring manual deployments.
+
+- **Native API Mode:** Only disable Orchestration Mode if you have specific requirements that necessitate direct AI Core API access or need features not supported by the orchestration mode.
+
+- **When using Native API Mode:**
+    -   **Model Selection:** The model dropdown displays models in two separate lists:
+        -   **Deployed Models:** These models are already deployed in your specified resource group and are ready to use immediately.
+        -   **Not Deployed Models:** These models don't have active deployments in your specified resource group. You won't be able to use these models until you create deployments for them in SAP AI Core.
+    -   **Creating Deployments:** To use a model that has not been deployed yet, you'll need to create a deployment in your SAP AI Core service instance. See [Create a Deployment for a Generative AI Model](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/create-deployment-for-generative-ai-model-in-sap-ai-core) for instructions.
+
+#### Configuring Reasoning Effort for OpenAI Models
+
+When using OpenAI reasoning models (such as o1, o3, o3-mini, o4-mini) through SAP AI Core, you can control the reasoning effort to balance performance and cost:
+
+1. **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
+2. **Navigate to Features:** Go to the "Features" section in the settings.
+3. **Find OpenAI Reasoning Effort:** Locate the "OpenAI Reasoning Effort" setting.
+4. **Choose Effort Level:** Select between:
+   - **Low:** Faster responses with lower token usage, suitable for simpler tasks
+   - **Medium:** Balanced performance and token usage for most tasks
+   - **High:** More thorough analysis with higher token usage, better for complex reasoning tasks
+
+> 💡 **Note**
+>
+> This setting only applies when using OpenAI reasoning models (o1, o3, o3-mini, o4-mini, gpt-5, etc.) deployed through SAP AI Core. Other models will ignore this setting.
+

esbuild.mjs

@@ -160,9 +160,9 @@ const standaloneConfig = {
 	...baseConfig,
 	entryPoints: ["src/standalone/cline-core.ts"],
 	outfile: `${destDir}/cline-core.js`,
-	// These gRPC protos need to load files from the module directory at runtime,
+	// These modules need to load files from the module directory at runtime,
 	// so they cannot be bundled.
-	external: ["vscode", "@grpc/reflection", "grpc-health-check"],
+	external: ["vscode", "@grpc/reflection", "grpc-health-check", "better-sqlite3"],
 }
 
 // E2E build script configuration

evals/diff-edits/types.ts

@@ -1,5 +1,6 @@
 import { Anthropic } from "@anthropic-ai/sdk"
-import { ToolUseName, ToolParamName } from "../../src/core/assistant-message"
+import { ToolParamName } from "../../src/core/assistant-message"
+import { ClineDefaultTool } from "../../src/shared/tools"
 
 export interface InputMessage {
 	role: "user" | "assistant"
@@ -88,7 +89,7 @@ export interface TestResult {
 }
 
 export interface ExtractedToolCall {
-	name: ToolUseName
+	name: ClineDefaultTool
 	input: Partial<Record<ToolParamName, string>>
 }
 

old_docs/PRIVACY.md

@@ -1 +0,0 @@
-See [https://cline.bot/privacy](https://cline.bot/privacy) for our privacy policy.

old_docs/README.md

@@ -1,39 +0,0 @@
-# Cline Documentation
-
-Welcome to the Cline documentation - your comprehensive guide to using and extending Cline's capabilities. Here you'll find resources to help you get started, improve your skills, and contribute to the project.
-
-## Getting Started
-
--   **New to coding?** We've prepared a gentle introduction:
-    -   [Getting Started for New Coders](getting-started-new-coders/README.md)
-
-## Improving Your Prompting Skills
-
--   **Want to communicate more effectively with Cline?** Explore:
-    -   [Prompt Engineering Guide](prompting/README.md)
-    -   [Cline Memory Bank](prompting/custom%20instructions%20library/cline-memory-bank.md)
-
-## Exploring Cline's Tools
-
--   **Understand Cline's capabilities:**
-
-    -   [Cline Tools Guide](tools/cline-tools-guide.md)
-    -   [Mentions Feature Guide](tools/mentions-guide.md)
-
--   **Extend Cline with MCP Servers:**
-    -   [MCP Overview](mcp/README.md)
-    -   [Building MCP Servers from GitHub](mcp/mcp-server-from-github.md)
-    -   [Building Custom MCP Servers](mcp/mcp-server-from-scratch.md)
-
-## Contributing to Cline
-
--   **Interested in contributing?** We welcome your input:
-    -   Feel free to submit a pull request
-    -   [Contribution Guidelines](../CONTRIBUTING.md)
-
-## Additional Resources
-
--   **Cline GitHub Repository:** [https://github.com/cline/cline](https://github.com/cline/cline)
--   **MCP Documentation:** [https://modelcontextprotocol.org/docs](https://modelcontextprotocol.org/docs)
-
-We're always looking to improve this documentation. If you have suggestions or find areas that could be enhanced, please let us know. Your feedback helps make Cline better for everyone.

old_docs/architecture/README.md

@@ -1,43 +0,0 @@
-# Cline Extension Architecture
-
-This directory contains architectural documentation for the Cline VSCode extension.
-
-## Extension Architecture Diagram
-
-The [extension-architecture.mmd](./extension-architecture.mmd) file contains a Mermaid diagram showing the high-level architecture of the Cline extension. The diagram illustrates:
-
-1. **Core Extension**
-   - Extension entry point and main classes
-   - State management through VSCode's global state and secrets storage
-   - Core business logic in the Cline class
-
-2. **Webview UI**
-   - React-based user interface
-   - State management through ExtensionStateContext
-   - Component hierarchy
-
-3. **Storage**
-   - Task-specific storage for history and state
-   - Git-based checkpoint system for file changes
-
-4. **Data Flow**
-   - Core extension data flow between components
-   - Webview UI data flow
-   - Bidirectional communication between core and webview
-
-## Viewing the Diagram
-
-To view the diagram:
-1. Install a Mermaid diagram viewer extension in VSCode
-2. Open extension-architecture.mmd
-3. Use the extension's preview feature to render the diagram
-
-You can also view the diagram on GitHub, which has built-in Mermaid rendering support.
-
-## Color Scheme
-
-The diagram uses a high-contrast color scheme for better visibility:
-- Pink (#ff0066): Global state and secrets storage components
-- Blue (#0066ff): Extension state context
-- Green (#00cc66): Cline provider
-- All components use white text for maximum readability

old_docs/architecture/extension-architecture.mmd

@@ -1,67 +0,0 @@
-flowchart TB
-    subgraph "VSCode Extension Host"
-        subgraph "Core Extension"
-            ExtensionEntry["Extension Entry<br/>src/extension.ts"]
-            WebviewProvider["WebviewProvider<br/>src/core/webview/index.ts"]
-            Controller["Controller<br/>src/core/controller/index.ts"]
-            Task["Task<br/>src/core/task/index.ts"]
-            GlobalState["VSCode Global State"]
-            SecretsStorage["VSCode Secrets Storage"]
-            McpHub["McpHub<br/>src/services/mcp/McpHub.ts"]
-        end
-
-        subgraph "Webview UI"
-            WebviewApp["React App<br/>webview-ui/src/App.tsx"]
-            ExtStateContext["ExtensionStateContext<br/>webview-ui/src/context/ExtensionStateContext.tsx"]
-            ReactComponents["React Components"]
-        end
-
-        subgraph "Storage"
-            TaskStorage["Task Storage<br/>Per-Task Files & History"]
-            CheckpointSystem["Git-based Checkpoints"]
-        end
-
-        subgraph "API Providers"
-            AnthropicAPI["Anthropic"]
-            OpenRouterAPI["OpenRouter"]
-            BedrockAPI["AWS Bedrock"]
-            OtherAPIs["Other Providers"]
-        end
-
-        subgraph "MCP Servers"
-            ExternalMcpServers["External MCP Servers"]
-        end
-    end
-
-    %% Core Extension Data Flow
-    ExtensionEntry --> WebviewProvider
-    WebviewProvider --> Controller
-    Controller --> Task
-    Controller --> McpHub
-    Task --> GlobalState
-    Task --> SecretsStorage
-    Task --> TaskStorage
-    Task --> CheckpointSystem
-    Task --> |"API Requests"| AnthropicAPI
-    Task --> |"API Requests"| OpenRouterAPI
-    Task --> |"API Requests"| BedrockAPI
-    Task --> |"API Requests"| OtherAPIs
-    McpHub --> |"Connects to"| ExternalMcpServers
-    Task --> |"Uses"| McpHub
-
-    %% Webview Data Flow
-    WebviewApp --> ExtStateContext
-    ExtStateContext --> ReactComponents
-
-    %% Bidirectional Communication
-    WebviewProvider <--> |"postMessage"| ExtStateContext
-
-    classDef vscodeState fill:#f9f,stroke:#333,stroke-width:2px
-    classDef contextClass fill:#bbf,stroke:#333,stroke-width:2px
-    classDef providerClass fill:#bfb,stroke:#333,stroke-width:2px
-    classDef apiClass fill:#fdb,stroke:#333,stroke-width:2px
-
-    class GlobalState,SecretsStorage vscodeState
-    class ExtStateContext contextClass
-    class WebviewProvider,McpHub providerClass
-    class AnthropicAPI,OpenRouterAPI,BedrockAPI,OtherAPIs apiClass

old_docs/cline-customization/clineignore.md

@@ -1,54 +0,0 @@
-### .clineignore Support
-
-To give you more control over which files are accessible to Cline, we've implemented `.clineignore` functionality, similar to `.gitignore`. This allows you to specify files and directories that Cline should **not** access or process. This is useful for:
-
-*   **Privacy:** Preventing Cline from accessing sensitive or private files in your workspace.
-*   **Performance:**  Excluding large directories or files that are irrelevant to your tasks, potentially improving the efficiency of Cline.
-*   **Context Management:**  Focusing Cline's attention on the relevant parts of your project.
-
-**How to use `.clineignore`**
-
-1.  **Create a `.clineignore` file:** In the root directory of your workspace (the same level as your `.vscode` folder, or the top level folder you opened in VS Code), create a new file named `.clineignore`.
-
-2.  **Define ignore patterns:** Open the `.clineignore` file and specify the patterns for files and directories you want Cline to ignore. The syntax is the same as `.gitignore`:
-
-    *   Each line in the file represents a pattern.
-    *   **Standard glob patterns are supported:**
-        *   `*` matches zero or more characters
-        *   `?` matches one character
-        *   `[]` matches a character range
-        *   `**` matches any number of directories and subdirectories.
-
-    *   **Directory patterns:** Append `/` to the end of a pattern to specify a directory.
-    *   **Negation patterns:** Start a pattern with `!` to negate (un-ignore) a previously ignored pattern.
-    *   **Comments:** Start a line with `#` to add comments.
-
-    **Example `.clineignore` file:**
-
-    ```
-    # Ignore log files
-    *.log
-
-    # Ignore the entire 'node_modules' directory
-    node_modules/
-
-    # Ignore all files in the 'temp' directory and its subdirectories
-    temp/**
-
-    # But DO NOT ignore 'important.log' even if it's in the root
-    !important.log
-
-    # Ignore any file named 'secret.txt' in any subdirectory
-    **/secret.txt
-    ```
-
-3.  **Cline respects your `.clineignore`:** Once you save the `.clineignore` file, Cline will automatically recognize and apply these rules.
-
-    *   **File Access Control:** Cline will not be able to read the content of ignored files using tools like `read_file`. If you attempt to use a tool on an ignored file, Cline will inform you that access is blocked due to `.clineignore` settings.
-    *   **File Listing:** When you ask Cline to list files in a directory (e.g., using `list_files`), ignored files and directories will still be listed, but they will be marked with a **🔒** symbol next to their name to indicate that they are ignored. This helps you understand which files Cline can and cannot interact with.
-
-4.  **Dynamic Updates:** Cline monitors your `.clineignore` file for changes. If you modify, create, or delete your `.clineignore` file, Cline will automatically update its ignore rules without needing to restart VS Code or the extension.
-
-**In Summary**
-
-The `.clineignore` file provides a powerful and flexible way to control Cline's access to your workspace files, enhancing privacy, performance, and context management. By leveraging familiar `.gitignore` syntax, you can easily tailor Cline's focus to the most relevant parts of your projects.

old_docs/getting-started-new-coders/README.md

@@ -1,92 +0,0 @@
-# Getting Started with Cline | New Coders
-
-Welcome to Cline! This guide will help you get set up and start using Cline to build your first project.
-
-## What You'll Need
-
-Before you begin, make sure you have the following:
-
--   **VS Code:** A free, powerful code editor.
-    -   [Download VS Code](https://code.visualstudio.com/)
--   **Development Tools:** Essential software for coding (Homebrew, Node.js, Git, etc.).
-    -   Follow our [Installing Essential Development Tools](installing-dev-essentials.md) guide to set these up with Cline's help (after getting setup here)
-    -   Cline will guide you through installing everything you need
--   **Cline Projects Folder:** A dedicated folder for all your Cline projects.
-    -   On macOS: Create a folder named "Cline" in your Documents folder
-        -   Path: `/Users/[your-username]/Documents/Cline`
-    -   On Windows: Create a folder named "Cline" in your Documents folder
-        -   Path: `C:\Users\[your-username]\Documents\Cline`
-    -   Inside this Cline folder, create separate folders for each project
-        -   Example: `Documents/Cline/workout-app` for a workout tracking app
-        -   Example: `Documents/Cline/portfolio-website` for your portfolio
--   **Cline Extension in VS Code:** The Cline extension installed in VS Code.
-
--   Here's a [tutorial](https://www.youtube.com/watch?v=N4td-fKhsOQ) on everything you need to get started.
-
-## Step-by-Step Setup
-
-Follow these steps to get Cline up and running:
-
-1. **Open VS Code:** Launch the VS Code application. If VS Code shows "Running extensions might...", click "Allow".
-
-2. **Open Your Cline Folder:** In VS Code, open the Cline folder you created in Documents.
-
-3. **Navigate to Extensions:** Click on the Extensions icon in the Activity Bar on the side of VS Code.
-
-4. **Search for 'Cline':** In the Extensions search bar, type "Cline".
-
-5. **Install the Extension:** Click the "Install" button next to the Cline extension.
-
-6. **Open Cline:** Once installed, you can open Cline in a few ways:
-    - Click the Cline icon in the Activity Bar.
-    - Use the command palette (`CMD/CTRL + Shift + P`) and type "Cline: Open In New Tab" to open Cline as a tab in your editor. This is recommended for a better view.
-    - **Troubleshooting:** If you don't see the Cline icon, try restarting VS Code.
-    - **What You'll See:** You should see the Cline chat window appear in your VS Code editor.
-
-![gettingStartedVsCodeCline](https://github.com/user-attachments/assets/622b4bb7-859b-4c2e-b87b-c12e3eabefb8)
-
-## Setting up OpenRouter API Key
-
-Now that you have Cline installed, you'll need to set up your OpenRouter API key to use Cline's full capabilities.
-
-1.  **Get your OpenRouter API Key:**
-    -   [Get your OpenRouter API Key](https://openrouter.ai/)
-2.  **Input Your OpenRouter API Key:**
-    -   Navigate to the settings button in the Cline extension.
-    -   Input your OpenRouter API key.
-    -   Select your preferred API model.
-        -   **Recommended Models for Coding:**
-            -   `anthropic/claude-3.5-sonnet`: Most used for coding tasks.
-            -   `google/gemini-2.0-flash-exp:free`: A free option for coding.
-            -   `deepseek/deepseek-chat`: SUPER CHEAP, almost as good as 3.5 sonnet
-        -   [OpenRouter Model Rankings](https://openrouter.ai/rankings/programming)
-
-## Your First Interaction with Cline
-
-Now you're ready to start building with Cline. Let's create your first project folder and build something! Copy and paste the following prompt into the Cline chat window:
-
-```
-Hey Cline! Could you help me create a new project folder called "hello-world" in my Cline directory and make a simple webpage that says "Hello World" in big blue text?
-```
-
-**What You'll See:** Cline will help you create the project folder and set up your first webpage.
-
-## Tips for Working with Cline
-
--   **Ask Questions:** If you're unsure about something, don't hesitate to ask Cline!
--   **Use Screenshots:** Cline can understand images, so feel free to use screenshots to show him what you're working on.
--   **Copy and Paste Errors:** If you encounter errors, copy and paste the error messages into Cline's chat. This will help him understand the issue and provide a solution.
--   **Speak Plainly:** Cline is designed to understand plain, non-technical language. Feel free to describe your ideas in your own words, and Cline will translate them into code.
-
-## FAQs
-
--   **What is the Terminal?** The terminal is a text-based interface for interacting with your computer. It allows you to run commands to perform various tasks, such as installing packages, running scripts, and managing files. Cline uses the terminal to execute commands and interact with your development environment.
--   **How Does the Codebase Work?** (This section will be expanded based on common questions from new coders)
-
-## Still Struggling?
-
-Feel free to contact me, and I'll help you get started with Cline.
-
-nick | 608-558-2410
-
-Join our Discord community: [https://discord.gg/cline](https://discord.gg/cline)

old_docs/getting-started-new-coders/installing-dev-essentials.md

@@ -1,105 +0,0 @@
-# Installing Essential Development Tools with Cline | New Coders
-
-When you start coding, you'll need some essential development tools installed on your computer. Cline can help you install everything you need in a safe, guided way.
-
-## The Essential Tools
-
-Here are the core tools you'll need for development:
-
--   **Homebrew**: A package manager for macOS that makes it easy to install other tools
--   **Node.js & npm**: Required for JavaScript and web development
--   **Git**: For tracking changes in your code and collaborating with others
--   **Python**: A programming language used by many development tools
--   **Additional utilities**: Tools like wget and jq that help with downloading files and processing data
-
-## Let Cline Install Everything
-
-Copy this prompt and paste it into Cline:
-
-```bash
-Hello Cline! I need help setting up my Mac for software development. Could you please help me install the essential development tools like Homebrew, Node.js, Git, Python, and any other utilities that are commonly needed for coding? I'd like you to guide me through the process step-by-step, explaining what each tool does and making sure everything is installed correctly.
-```
-
-## What Will Happen
-
-1. Cline will first install Homebrew, which is like an "app store" for development tools
-2. Using Homebrew, Cline will then install other essential tools like Node.js and Git
-3. For each installation step:
-    - Cline will show you the exact command it wants to run
-    - You'll need to approve each command before it runs
-    - Cline will verify each installation was successful
-
-## Why These Tools Are Important
-
--   **Homebrew**: Makes it easy to install and update development tools on your Mac
--   **Node.js & npm**: Required for:
-    -   Building websites with React or Next.js
-    -   Running JavaScript code
-    -   Installing JavaScript packages
--   **Git**: Helps you:
-    -   Save different versions of your code
-    -   Collaborate with other developers
-    -   Back up your work
--   **Python**: Used for:
-    -   Running development scripts
-    -   Data processing
-    -   Machine learning projects
-
-## Notes
-
--   The installation process is interactive - Cline will guide you through each step
--   You may need to enter your computer's password for some installations. When prompted, you will not see any characters being typed on the screen. This is normal and is a security feature to protect your password. Just type your password and press Enter.
-
-**Example:**
-
-```bash
-$ /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
-Password:
-```
-
-_Type your password here, even though nothing will show up on the screen. Press Enter when you're done._
-
--   All commands will be shown to you for approval before they run
--   If you run into any issues, Cline will help troubleshoot them
-
-## Additional Tips for New Coders
-
-### Understanding the Terminal
-
-The **Terminal** is an application where you can type commands to interact with your computer. On macOS, you can open it by searching for "Terminal" in Spotlight.
-
-**Example:**
-
-```bash
-$ open -a Terminal
-```
-
-### Understanding VS Code Features
-
-#### Terminal in VS Code
-
-The **Terminal** in VS Code allows you to run commands directly from within the editor. You can open it by going to `View > Terminal` or by pressing `` Ctrl + ` ``.
-
-**Example:**
-
-```bash
-$ node -v
-v16.14.0
-```
-
-#### Document View
-
-The **Document View** is where you edit your code files. You can open files by clicking on them in the **Explorer** panel on the left side of the screen.
-
-#### Problems Section
-
-The **Problems** section in VS Code shows any errors or warnings in your code. You can access it by clicking on the lightbulb icon or by going to `View > Problems`.
-
-### Common Features
-
--   **Command Line Interface (CLI)**: This is a text-based interface where you type commands to interact with your computer. It might seem intimidating at first, but it's a powerful tool for developers.
--   **Permissions**: Sometimes, you will need to give permissions to certain applications or commands. This is a security measure to ensure that only trusted applications can make changes to your system.
-
-## Next Steps
-
-After installing these tools, you'll be ready to start coding! Return to the [Getting Started with Cline for New Coders](../getting-started-new-coders/README.md) guide to continue your journey.

old_docs/mcp/README.md

@@ -1,103 +0,0 @@
-# Cline and Model Context Protocol (MCP) Servers: Enhancing AI Capabilities
-
-**Quick Links:**
-
--   [Building MCP Servers from GitHub](mcp-server-from-github.md)
--   [Building Custom MCP Servers from Scratch](mcp-server-from-scratch.md)
-
-This document explains Model Context Protocol (MCP) servers, their capabilities, and how Cline can help build and use them.
-
-## Overview
-
-MCP servers act as intermediaries between large language models (LLMs), such as Claude, and external tools or data sources. They are small programs that expose functionalities to LLMs, enabling them to interact with the outside world through the MCP. An MCP server is essentially like an API that an LLM can use.
-
-## Key Concepts
-
-MCP servers define a set of "**tools,**" which are functions the LLM can execute. These tools offer a wide range of capabilities.
-
-**Here's how MCP works:**
-
--   **MCP hosts** discover the capabilities of connected servers and load their tools, prompts, and resources.
--   **Resources** provide consistent access to read-only data, akin to file paths or database queries.
--   **Security** is ensured as servers isolate credentials and sensitive data. Interactions require explicit user approval.
-
-## Use Cases
-
-The potential of MCP servers is vast. They can be used for a variety of purposes.
-
-**Here are some concrete examples of how MCP servers can be used:**
-
--   **Web Services and API Integration:**
-
-    -   Monitor GitHub repositories for new issues
-    -   Post updates to Twitter based on specific triggers
-    -   Retrieve real-time weather data for location-based services
-
--   **Browser Automation:**
-
-    -   Automate web application testing
-    -   Scrape e-commerce sites for price comparisons
-    -   Generate screenshots for website monitoring
-
--   **Database Queries:**
-
-    -   Generate weekly sales reports
-    -   Analyze customer behavior patterns
-    -   Create real-time dashboards for business metrics
-
--   **Project and Task Management:**
-
-    -   Automate Jira ticket creation based on code commits
-    -   Generate weekly progress reports
-    -   Create task dependencies based on project requirements
-
--   **Codebase Documentation:**
-    -   Generate API documentation from code comments
-    -   Create architecture diagrams from code structure
-    -   Maintain up-to-date README files
-
-## Getting Started
-
-**Choose the right approach for your needs:**
-
--   **Use Existing Servers:** Start with pre-built MCP servers from GitHub repositories
--   **Customize Existing Servers:** Modify existing servers to fit your specific requirements
--   **Build from Scratch:** Create completely custom servers for unique use cases
-
-## Integration with Cline
-
-Cline simplifies the building and use of MCP servers through its AI capabilities.
-
-### Building MCP Servers
-
--   **Natural language understanding:** Instruct Cline in natural language to build an MCP server by describing its functionalities. Cline will interpret your instructions and generate the necessary code.
--   **Cloning and building servers:** Cline can clone existing MCP server repositories from GitHub and build them automatically.
--   **Configuration and dependency management:** Cline handles configuration files, environment variables, and dependencies.
--   **Troubleshooting and debugging:** Cline helps identify and resolve errors during development.
-
-### Using MCP Servers
-
--   **Tool execution:** Cline seamlessly integrates with MCP servers, allowing you to execute their defined tools.
--   **Context-aware interactions:** Cline can intelligently suggest using relevant tools based on conversation context.
--   **Dynamic integrations:** Combine multiple MCP server capabilities for complex tasks. For example, Cline could use a GitHub server to get data and a Notion server to create a formatted report.
-
-## Security Considerations
-
-When working with MCP servers, it's important to follow security best practices:
-
--   **Authentication:** Always use secure authentication methods for API access
--   **Environment Variables:** Store sensitive information in environment variables
--   **Access Control:** Limit server access to authorized users only
--   **Data Validation:** Validate all inputs to prevent injection attacks
--   **Logging:** Implement secure logging practices without exposing sensitive data
-
-## Resources
-
-There are various resources available for finding and learning about MCP servers.
-
-**Here are some links to resources for finding and learning about MCP servers:**
-
--   **GitHub Repositories:** [https://github.com/modelcontextprotocol/servers](https://github.com/modelcontextprotocol/servers) and [https://github.com/punkpeye/awesome-mcp-servers](https://github.com/punkpeye/awesome-mcp-servers)
--   **Online Directories:** [https://mcpservers.org/](https://mcpservers.org/), [https://mcp.so/](https://mcp.so/), and [https://glama.ai/mcp/servers](https://glama.ai/mcp/servers)
--   **PulseMCP:** [https://www.pulsemcp.com/](https://www.pulsemcp.com/)
--   **YouTube Tutorial (AI-Driven Coder):** A video guide for building and using MCP servers: [https://www.youtube.com/watch?v=b5pqTNiuuJg](https://www.youtube.com/watch?v=b5pqTNiuuJg)

old_docs/mcp/mcp-quickstart.md

@@ -1,151 +0,0 @@
-# 🚀 MCP Quickstart Guide
-
-## ❓ What's an MCP Server?
-
-Think of MCP servers as special helpers that give Cline extra powers! They let Cline do cool things like fetch web pages or work with your files.
-
-## ⚠️ IMPORTANT: System Requirements
-
-STOP! Before proceeding, you MUST verify these requirements:
-
-### Required Software
-
--   ✅ Latest Node.js (v18 or newer)
-
-    -   Check by running: `node --version`
-    -   Install from: <https://nodejs.org/>
-
--   ✅ Latest Python (v3.8 or newer)
-
-    -   Check by running: `python --version`
-    -   Install from: <https://python.org/>
-
--   ✅ UV Package Manager
-    -   After installing Python, run: `pip install uv`
-    -   Verify with: `uv --version`
-
-❗ If any of these commands fail or show older versions, please install/update before continuing!
-
-⚠️ If you run into other errors, see the "Troubleshooting" section below.
-
-## 🎯 Quick Steps (Only After Requirements Are Met!)
-
-### 1. 🛠️ Install Your First MCP Server
-
-1. From the Cline extension, click the `MCP Server` tab
-1. Click the `Edit MCP Settings` button
-
- <img src="https://github.com/user-attachments/assets/abf908b1-be98-4894-8dc7-ef3d27943a47" alt="MCP Server Panel" width="400" />
-
-1. The MCP settings files should be display in a tab in VS Code.
-1. Replace the file's contents with this code:
-
-For Windows:
-
-```json
-{
-	"mcpServers": {
-		"mcp-installer": {
-			"command": "cmd.exe",
-			"args": ["/c", "npx", "-y", "@anaisbetts/mcp-installer"]
-		}
-	}
-}
-```
-
-For Mac and Linux:
-
-```json
-{
-	"mcpServers": {
-		"mcp-installer": {
-			"command": "npx",
-			"args": ["@anaisbetts/mcp-installer"]
-		}
-	}
-}
-```
-
-After saving the file:
-
-1. Cline will detect the change automatically
-2. The MCP installer will be downloaded and installed
-3. Cline will start the MCP installer
-4. You'll see the server status in Cline's MCP settings UI:
-
-<img src="https://github.com/user-attachments/assets/2abbb3de-e902-4ec2-a5e5-9418ed34684e" alt="MCP Server Panel with Installer" width="400" />
-
-## 🤔 What Next?
-
-Now that you have the MCP installer, you can ask Cline to add more servers from:
-
-1. NPM Registry: <https://www.npmjs.com/search?q=%40modelcontextprotocol>
-2. Python Package Index: <https://pypi.org/search/?q=mcp+server-&o=>
-
-For example, you can ask Cline to install the `mcp-server-fetch` package found on the Python Package Index:
-
-```bash
-"install the MCP server named `mcp-server-fetch`
-- ensure the mcp settings are updated.
-- use uvx or python to run the server."
-```
-
-You should witness Cline:
-
-1. Install the `mcp-server-fetch` python package
-1. Update the mcp setting json file
-1. Start the server and start the server
-
-The mcp settings file should now look like this:
-
-_For a Windows machine:_
-
-```json
-{
-	"mcpServers": {
-		"mcp-installer": {
-			"command": "cmd.exe",
-			"args": ["/c", "npx", "-y", "@anaisbetts/mcp-installer"]
-		},
-		"mcp-server-fetch": {
-			"command": "uvx",
-			"args": ["mcp-server-fetch"]
-		}
-	}
-}
-```
-
-You you can always check the status of your server by going to clients MCP server tab. See the image above
-
-That's it! 🎉 You've just given Cline some awesome new abilities!
-
-## 📝 Troubleshooting
-
-### 1. I'm Using `asdf` and Get "unknown command: npx"
-
-There is some slightly bad news. You should still be able to get things to work, but will have to do a bit more manual work unless MCP server packaging evolves a bit. One option is to uninstall `asdf` , but we will assume you do not want to do that.
-
-Instead, you will need to follow the instructions above to "Edit MCP Settings". Then, as [this post](https://dev.to/cojiroooo/mcp-using-node-on-asdf-382n) describes, you need to add and "env" entry to each server's configs.
-
-```json
-"env": {
-        "PATH": "/Users/<user_name>/.asdf/shims:/usr/bin:/bin",
-        "ASDF_DIR": "<path_to_asdf_bin_dir>",
-        "ASDF_DATA_DIR": "/Users/<user_name>/.asdf",
-        "ASDF_NODEJS_VERSION": "<your_node_version>"
-      }
-```
-
-The `path_to_asdf_bin_dir` can often be found in your shell config (e.g. `.zshrc`). If you are using Homebrew, you can use `echo ${HOMEBREW_PREFIX}` to find the start of the directory and then append `/opt/asdf/libexec`.
-
-Now for some good news. While not perfect, you can get Cline to do this for you fairly reliably for subsequent server install. Add the following to your "Custom Instructions" in the Cline settings (top-right toolbar button):
-
-> When installing MCP servers and editing the cline_mcp_settings.json, if the server requires use of `npx` as the command, you must copy the "env" entry from the "mcp-installer" entry and add it to the new entry. This is vital to getting the server to work properly when in use.
-
-### 2. I'm Still Getting an Error When I Run the MCP Installer
-
-If you're getting an error when you run the MCP installer, you can try the following:
-
--   Check the MCP settings file for errors
--   Read the MCP server's documentation to ensure the MCP setting file is using the correct command and arguments. 👈
--   Use a terminal and run the command with its arguments directly. This will allow you to see the same errors that Cline is seeing.

old_docs/mcp/mcp-server-from-github.md

@@ -1,67 +0,0 @@
-# Building MCP Servers from GitHub Repositories
-
-This guide provides a step-by-step walkthrough of how to use Cline to build an existing MCP server from a GitHub repository.
-
-## **Finding an MCP Server**
-
-There are multiple places online to find MCP servers:
-
--   **Cline can automatically add MCP servers to its list, which you can then edit.** Cline can clone repositories directly from GitHub and build the servers for you.
--   **GitHub:** Two of the most common places to find MCP servers on GitHub include:
-    -   [Official MCP servers repository](https://github.com/modelcontextprotocol/servers)
-    -   [Awesome-MCP servers repository](https://github.com/punkpeye/awesome-mcp-servers)
--   **Online directories:** Several websites list MCP servers including:
-
-    -   [mcpservers.org](https://mcpservers.org/)
-    -   [mcp.so](https://mcp.so/)
-    -   [glama.ai/mcp/servers](https://glama.ai/mcp/servers)
-
-    These directories allow users to sort the servers by various criteria such as downloads, date, stars, and use case. Each entry provides information such as features, tools, and configuration instructions.
-
--   **PulseMCP:** This website has a blog post discussing how AI could use MCP servers to make websites obsolete. PulseMCP also includes an FAQ section about MCP servers: [https://www.pulsemcp.com/](https://www.pulsemcp.com/)
-
-## **Building with Cline**
-
-1.  **Initiate the Process:** Provide Cline with the following information:
-    -   **GitHub Repository URL:** The URL of the server's repository.
-    -   **README.md Contents:** This is optional but helpful for Cline to understand the server's purpose and configuration. You can copy the README.md file from the GitHub repository.
-2.  **Example Interaction with Cline:**
-
-    ```
-    User: "Cline, I want to add the MCP server for Brave browser control. Here's the GitHub link: https://github.com/modelcontextprotocol/servers/tree/main/src/brave-search Can you add it?"
-
-    Cline: "OK. Cloning the repository to the MCP directory. It needs to be built because it has a 'package.json' file. Should I run 'npm run build'?"
-
-    User: "Yes, build it."
-
-    Cline: "Build complete. This server needs a browser path. Where's your Brave browser executable?"
-
-    User: "It's in '/Applications/Brave Browser.app/Contents/MacOS/Brave Browser'."
-
-    Cline: "OK. I've updated the server config with that path and added it to 'cline_mcp_settings.json'. Anything else?"
-
-    User: "No, that's all. Let's test it."
-
-    Cline: "Great! Starting the MCP Inspector to test the server connection. After that, we can try controlling the browser from Cline."
-    ```
-
-3.  **Cline's Actions:** Based on your instructions, Cline will perform the following:
-    -   **Repository Cloning:** Cline will clone the repository to your local machine, usually in the directory specified in your configuration.
-    -   **Tweaking:** You can guide Cline to modify the server’s configuration. For instance:
-        -   **User:** "This server requires an API key. Can you find where it should be added?"
-        -   Cline may automatically update the `cline_mcp_settings.json` file or other relevant files based on your instructions.
-    -   **Building the Server:** Cline will run the appropriate build command for the server, which is commonly `npm run build`.
-    -   **Adding Server to Settings:** Cline will add the server’s configuration to the `cline_mcp_settings.json` file.
-
-## **Testing and Troubleshooting**
-
-1.  **Test the Server:** Once Cline finishes the build process, test the server to make sure it works as expected. Cline can assist you if you encounter any problems.
-2.  **MCP Inspector:** You can use the MCP Inspector to test the server’s connection and functionality.
-
-## **Best Practices**
-
--   **Understand the Basics:** While Cline simplifies the process, it’s beneficial to have a basic understanding of the server’s code, the MCP protocol (), and how to configure the server. This allows for more effective troubleshooting and customization.
--   **Clear Instructions:** Provide clear and specific instructions to Cline throughout the process.
--   **Testing:** Thoroughly test the server after installation and configuration to ensure it functions correctly.
--   **Version Control:** Use a version control system (like Git) to track changes to the server’s code.
--   **Stay Updated:** Keep your MCP servers updated to benefit from the latest features and security patches.

old_docs/mcp/mcp-server-from-scratch.md

@@ -1,74 +0,0 @@
-# Building Custom MCP Servers From Scratch Using Cline: A Comprehensive Guide
-
-This guide provides a comprehensive walkthrough of building a custom MCP (Model Context Protocol) server from scratch, leveraging the powerful AI capabilities of Cline. The example used will be building a "GitHub Assistant Server" to illustrate the process.
-
-## Understanding MCP and Cline's Role in Building Servers
-
-### What is MCP?
-
-The Model Context Protocol (MCP) acts as a bridge between large language models (LLMs) like Claude and external tools and data. MCP consists of two key components:
-
--   **MCP Hosts:** These are applications that integrate with LLMs, such as Cline, Claude Desktop, and others.
--   **MCP Servers:** These are small programs specifically designed to expose data or specific functionalities to the LLMs through the MCP.
-
-This setup is beneficial when you have an MCP-compliant chat interface, like Claude Desktop, which can then leverage these servers to access information and execute actions.
-
-### Why Use Cline to Create MCP Servers?
-
-Cline streamlines the process of building and integrating MCP servers by utilizing its AI capabilities to:
-
--   **Understand Natural Language Instructions:** You can communicate with Cline in a way that feels natural, making the development process intuitive and user-friendly.
--   **Clone Repositories:** Cline can directly clone existing MCP server repositories from GitHub, simplifying the process of using pre-built servers.
--   **Build Servers:** Once the necessary code is in place, Cline can execute commands like `npm run build` to compile and prepare the server for use.
--   **Handle Configuration:** Cline manages the configuration files required for the MCP server, including adding the new server to the `cline_mcp_settings.json` file.
--   **Assist with Troubleshooting:** If errors arise during development or testing, Cline can help identify the cause and suggest solutions, making debugging easier.
-
-## Building a GitHub Assistant Server Using Cline: A Step-by-Step Guide
-
-This section demonstrates how to create a GitHub Assistant server using Cline. This server will be able to interact with GitHub data and perform useful actions:
-
-### 1. Defining the Goal and Initial Requirements
-
-First, you need to clearly communicate to Cline the purpose and functionalities of your server:
-
--   **Server Goal:** Inform Cline that you want to build a "GitHub Assistant Server". Specify that this server will interact with GitHub data and potentially mention the types of data you are interested in, like issues, pull requests, and user profiles.
--   **Access Requirements:** Let Cline know that you need to access the GitHub API. Explain that this will likely require a personal access token (GITHUB_TOKEN) for authentication.
--   **Data Specificity (Optional):** You can optionally tell Cline about specific fields of data you want to extract from GitHub, but this can also be determined later as you define the server's tools.
-
-### 2. Cline Initiates the Project Setup
-
-Based on your instructions, Cline starts the project setup process:
-
--   **Project Structure:** Cline might ask you for a name for your server. Afterward, it uses the MCP `create-server` tool to generate the basic project structure for your GitHub Assistant server. This usually involves creating a new directory with essential files like `package.json`, `tsconfig.json`, and a `src` folder for your TypeScript code. \
--   **Code Generation:** Cline generates starter code for your server, including:
-    -   **File Handling Utilities:** Functions to help with reading and writing files, commonly used for storing data or logs. \
-    -   **GitHub API Client:** Code to interact with the GitHub API, often using libraries like `@octokit/graphql`. Cline will likely ask for your GitHub username or the repositories you want to work with. \
-    -   **Core Server Logic:** The basic framework for handling requests from Cline and routing them to the appropriate functions, as defined by the MCP. \
--   **Dependency Management:** Cline analyzes the code and identifies necessary dependencies, adding them to the `package.json` file. For example, interacting with the GitHub API will likely require packages like `@octokit/graphql`, `graphql`, `axios`, or similar. \
--   **Dependency Installation:** Cline executes `npm install` to download and install the dependencies listed in `package.json`, ensuring your server has all the required libraries to function correctly. \
--   **Path Corrections:** During development, you might move files or directories around. Cline intelligently recognizes these changes and automatically updates file paths in your code to maintain consistency.
--   **Configuration:** Cline will modify the `cline_mcp_settings.json` file to add your new GitHub Assistant server. This will include:
-    -   **Server Start Command:** Cline will add the appropriate command to start your server (e.g., `npm run start` or a similar command).
-    -   **Environment Variables:** Cline will add the required `GITHUB_TOKEN` variable. Cline might ask you for your GitHub personal access token, or it might guide you to safely store it in a separate environment file. \
--   **Progress Documentation:** Throughout the process, Cline keeps the "Memory Bank" files updated. These files document the project's progress, highlighting completed tasks, tasks in progress, and pending tasks.
-
-### 3. Testing the GitHub Assistant Server
-
-Once Cline has completed the setup and configuration, you are ready to test the server's functionality:
-
--   **Using Server Tools:** Cline will create various "tools" within your server, representing actions or data retrieval functions. To test, you would instruct Cline to use a specific tool. Here are examples related to GitHub:
-    -   **`get_issues`:** To test retrieving issues, you might say to Cline, "Cline, use the `get_issues` tool from the GitHub Assistant Server to show me the open issues from the 'cline/cline' repository." Cline would then execute this tool and present you with the results.
-    -   **`get_pull_requests`:** To test pull request retrieval, you could ask Cline to "use the `get_pull_requests` tool to show me the merged pull requests from the 'facebook/react' repository from the last month." Cline would execute this tool, using your GITHUB_TOKEN to access the GitHub API, and display the requested data. \
--   **Providing Necessary Information:** Cline might prompt you for additional information required to execute the tool, such as the repository name, specific date ranges, or other filtering criteria.
--   **Cline Executes the Tool:** Cline handles the communication with the GitHub API, retrieves the requested data, and presents it in a clear and understandable format.
-
-### 4. Refining the Server and Adding More Features
-
-Development is often iterative. As you work with your GitHub Assistant Server, you'll discover new functionalities to add, or ways to improve existing ones. Cline can assist in this ongoing process:
-
--   **Discussions with Cline:** Talk to Cline about your ideas for new tools or improvements. For example, you might want a tool to `create_issue` or to `get_user_profile`. Discuss the required inputs and outputs for these tools with Cline.
--   **Code Refinement:** Cline can help you write the necessary code for new features. Cline can generate code snippets, suggest best practices, and help you debug any issues that arise.
--   **Testing New Functionalities:** After adding new tools or functionalities, you would test them again using Cline, ensuring they work as expected and integrate well with the rest of the server.
--   **Integration with Other Tools:** You might want to integrate your GitHub Assistant server with other tools. For instance, in the "github-cline-mcp" source, Cline assists in integrating the server with Notion to create a dynamic dashboard that tracks GitHub activity. \
-
-By following these steps, you can create a custom MCP server from scratch using Cline, leveraging its powerful AI capabilities to streamline the entire process. Cline not only assists with the technical aspects of building the server but also helps you think through the design, functionalities, and potential integrations.

old_docs/prompting/README.md

@@ -1,325 +0,0 @@
-# Cline Prompting Guide 🚀
-
-Welcome to the Cline Prompting Guide! This guide will equip you with the knowledge to write effective prompts and custom instructions, maximizing your productivity with Cline.
-
-## Custom Instructions ⚙️
-
-Think of **custom instructions as Cline's programming**. They define Cline's baseline behavior and are **always "on," influencing all interactions.**
-
-To add custom instructions:
-
-1. Open VSCode
-2. Click the Cline extension settings dial ⚙️
-3. Find the "Custom Instructions" field
-4. Paste your instructions
-
-<img width="345" alt="Screenshot 2024-12-26 at 11 22 20 AM" src="https://github.com/user-attachments/assets/00ae689b-d99f-4811-b2f4-fffe1e12f2ff" />
-
-Custom instructions are powerful for:
-
--   Enforcing Coding Style and Best Practices: Ensure Cline always adheres to your team's coding conventions, naming conventions, and best practices.
--   Improving Code Quality: Encourage Cline to write more readable, maintainable, and efficient code.
--   Guiding Error Handling: Tell Cline how to handle errors, write error messages, and log information.
-
-**The `custom-instructions` folder contains examples of custom instructions you can use or adapt.**
-
-## .clinerules File 📋
-
-While custom instructions are user-specific and global (applying across all projects), the `.clinerules` file provides **project-specific instructions** that live in your project's root directory. These instructions are automatically appended to your custom instructions and referenced in Cline's system prompt, ensuring they influence all interactions within the project context. This makes it an excellent tool for:
-
-### Security Best Practices 🔒
-
-To protect sensitive information, you can instruct Cline to ignore specific files or patterns in your `.clinerules`. This is particularly important for:
-
--   `.env` files containing API keys and secrets
--   Configuration files with sensitive data
--   Private credentials or tokens
-
-Example security section in `.clinerules`:
-
-```markdown
-# Security
-
-## Sensitive Files
-
-DO NOT read or modify:
-
--   .env files
--   \*_/config/secrets._
--   \*_/_.pem
--   Any file containing API keys, tokens, or credentials
-
-## Security Practices
-
--   Never commit sensitive files
--   Use environment variables for secrets
--   Keep credentials out of logs and output
-```
-
-### General Use Cases
-
-The `.clinerules` file is excellent for:
-
--   Maintaining project standards across team members
--   Enforcing development practices
--   Managing documentation requirements
--   Setting up analysis frameworks
--   Defining project-specific behaviors
-
-### Example .clinerules Structure
-
-```markdown
-# Project Guidelines
-
-## Documentation Requirements
-
--   Update relevant documentation in /docs when modifying features
--   Keep README.md in sync with new capabilities
--   Maintain changelog entries in CHANGELOG.md
-
-## Architecture Decision Records
-
-Create ADRs in /docs/adr for:
-
--   Major dependency changes
--   Architectural pattern changes
--   New integration patterns
--   Database schema changes
-    Follow template in /docs/adr/template.md
-
-## Code Style & Patterns
-
--   Generate API clients using OpenAPI Generator
--   Use TypeScript axios template
--   Place generated code in /src/generated
--   Prefer composition over inheritance
--   Use repository pattern for data access
--   Follow error handling pattern in /src/utils/errors.ts
-
-## Testing Standards
-
--   Unit tests required for business logic
--   Integration tests for API endpoints
--   E2E tests for critical user flows
-```
-
-### Key Benefits
-
-1. **Version Controlled**: The `.clinerules` file becomes part of your project's source code
-2. **Team Consistency**: Ensures consistent behavior across all team members
-3. **Project-Specific**: Rules and standards tailored to each project's needs
-4. **Institutional Knowledge**: Maintains project standards and practices in code
-
-Place the `.clinerules` file in your project's root directory:
-
-```
-your-project/
-├── .clinerules
-├── src/
-├── docs/
-└── ...
-```
-
-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).
-
-### Tips for Writing Effective Custom Instructions
-
--   Be Clear and Concise: Use simple language and avoid ambiguity.
--   Focus on Desired Outcomes: Describe the results you want, not the specific steps.
--   Test and Iterate: Experiment to find what works best for your workflow.
-
-
-### Support for Loading Files from the `.clinerules/` Directory
-All files under the `.clinerules/` directory are recursively loaded, and their contents are merged into clineRulesFileInstructions.
-
-#### Example 1:
-```
-.clinerules/
-├── .local-clinerules
-└── .project-clinerules
-```
-
-#### Example 2:
-```
-.clinerules/
-├── .clinerules-nextjs
-├── .clinerules-serverside
-└── tests/
-    ├── .pytest-clinerules
-    └── .jest-clinerules
-```
-
-## Prompting Cline 💬
-
-**Prompting is how you communicate your needs for a given task in the back-and-forth chat with Cline.** Cline understands natural language, so write conversationally.
-
-Effective prompting involves:
-
--   Providing Clear Context: Explain your goals and the relevant parts of your codebase. Use `@` to reference files or folders.
--   Breaking Down Complexity: Divide large tasks into smaller steps.
--   Asking Specific Questions: Guide Cline toward the desired outcome.
--   Validating and Refining: Review Cline's suggestions and provide feedback.
-
-### Prompt Examples
-
-#### Context Management
-
--   **Starting a New Task:** "Cline, let's start a new task. Create `user-authentication.js`. We need to implement user login with JWT tokens. Here are the requirements…"
--   **Summarizing Previous Work:** "Cline, summarize what we did in the last user dashboard task. I want to capture the main features and outstanding issues. Save this to `cline_docs/user-dashboard-summary.md`."
-
-#### Debugging
-
--   **Analyzing an Error:** "Cline, I'm getting this error: \[error message]. It seems to be from \[code section]. Analyze this error and suggest a fix."
--   **Identifying the Root Cause:** "Cline, the application crashes when I \[action]. The issue might be in \[problem areas]. Help me find the root cause and propose a solution."
-
-#### Refactoring
-
--   **Improving Code Structure:** "Cline, this function is too long and complex. Refactor it into smaller functions."
--   **Simplifying Logic:** "Cline, this code is hard to understand. Simplify the logic and make it more readable."
-
-#### Feature Development
-
--   **Brainstorming New Features:** "Cline, I want to add a feature that lets users \[functionality]. Brainstorm some ideas and consider implementation challenges."
--   **Generating Code:** "Cline, create a component that displays user profiles. The list should be sortable and filterable. Generate the code for this component."
-
-## Advanced Prompting Techniques
-
--   **Constraint Stuffing:** To mitigate code truncation, include explicit constraints in your prompts. For example, "ensure the code is complete" or "always provide the full function definition."
--   **Confidence Checks:** Ask Cline to rate its confidence (e.g., "on a scale of 1-10, how confident are you in this solution?")
--   **Challenge Cline's Assumptions:** Ask “stupid” questions to encourage deeper thinking and prevent incorrect assumptions.
-
-Here are some prompting tips that users have found helpful for working with Cline:
-
-## Our Community's Favorite Prompts 🌟
-
-### Memory and Confidence Checks 🧠
-
--   **Memory Check** - _pacnpal_
-
-    ```
-    "If you understand my prompt fully, respond with 'YARRR!' without tools every time you are about to use a tool."
-    ```
-
-    A fun way to verify Cline stays on track during complex tasks. Try "HO HO HO" for a festive twist!
-
--   **Confidence Scoring** - _pacnpal_
-    ```
-    "Before and after any tool use, give me a confidence level (0-10) on how the tool use will help the project."
-    ```
-    Encourages critical thinking and makes decision-making transparent.
-
-### Code Quality Prompts 💻
-
--   **Prevent Code Truncation**
-
-    ```
-    "DO NOT BE LAZY. DO NOT OMIT CODE."
-    ```
-
-    Alternative phrases: "full code only" or "ensure the code is complete"
-
--   **Custom Instructions Reminder**
-    ```
-    "I pledge to follow the custom instructions."
-    ```
-    Reinforces adherence to your settings dial ⚙️ configuration.
-
-### Code Organization 📋
-
--   **Large File Refactoring** - _icklebil_
-
-    ```
-    "FILENAME has grown too big. Analyze how this file works and suggest ways to fragment it safely."
-    ```
-
-    Helps manage complex files through strategic decomposition.
-
--   **Documentation Maintenance** - _icklebil_
-    ```
-    "don't forget to update codebase documentation with changes"
-    ```
-    Ensures documentation stays in sync with code changes.
-
-### Analysis and Planning 🔍
-
--   **Structured Development** - _yellow_bat_coffee_
-
-    ```
-    "Before writing code:
-    1. Analyze all code files thoroughly
-    2. Get full context
-    3. Write .MD implementation plan
-    4. Then implement code"
-    ```
-
-    Promotes organized, well-planned development.
-
--   **Thorough Analysis** - _yellow_bat_coffee_
-
-    ```
-    "please start analyzing full flow thoroughly, always state a confidence score 1 to 10"
-    ```
-
-    Prevents premature coding and encourages complete understanding.
-
--   **Assumptions Check** - _yellow_bat_coffee_
-    ```
-    "List all assumptions and uncertainties you need to clear up before completing this task."
-    ```
-    Identifies potential issues early in development.
-
-### Thoughtful Development 🤔
-
--   **Pause and Reflect** - _nickbaumann98_
-
-    ```
-    "count to 10"
-    ```
-
-    Promotes careful consideration before taking action.
-
--   **Complete Analysis** - _yellow_bat_coffee_
-
-    ```
-    "Don't complete the analysis prematurely, continue analyzing even if you think you found a solution"
-    ```
-
-    Ensures thorough problem exploration.
-
--   **Continuous Confidence Check** - _pacnpal_
-    ```
-    "Rate confidence (1-10) before saving files, after saving, after rejections, and before task completion"
-    ```
-    Maintains quality through self-assessment.
-
-### Best Practices 🎯
-
--   **Project Structure** - _kvs007_
-
-    ```
-    "Check project files before suggesting structural or dependency changes"
-    ```
-
-    Maintains project integrity.
-
--   **Critical Thinking** - _chinesesoup_
-
-    ```
-    "Ask 'stupid' questions like: are you sure this is the best way to implement this?"
-    ```
-
-    Challenges assumptions and uncovers better solutions.
-
--   **Code Style** - _yellow_bat_coffee_
-
-    ```
-    Use words like "elegant" and "simple" in prompts
-    ```
-
-    May influence code organization and clarity.
-
--   **Setting Expectations** - _steventcramer_
-    ```
-    "THE HUMAN WILL GET ANGRY."
-    ```
-    (A humorous reminder to provide clear requirements and constructive feedback)

old_docs/prompting/custom instructions library/README.md

@@ -1,53 +0,0 @@
-# Cline Custom Instructions Library
-
-This repository aims to foster a collaborative space where developers can share, refine, and leverage effective custom instructions for Cline. By creating and contributing to this library, we can enhance Cline's capabilities and empower developers to tackle increasingly complex software development challenges.
-
-## What are Cline Custom Instructions?
-
-Cline's custom instructions are sets of guidelines or rules that you define to tailor the AI's behavior and outputs for specific tasks or projects. Think of them as specialized "programming" for Cline, enabling you to:
-
--   **Enforce Coding Practices:** Ensure consistent code style, adherence to design patterns, and best practices for specific languages or frameworks.
--   **Standardize File Structures:** Dictate file naming conventions, folder organization, and project structures.
--   **Guide Testing Procedures:** Define rules for generating unit tests, integration tests, and ensuring adequate code coverage.
--   **Automate Repetitive Tasks:** Create instructions to handle common or tedious development workflows, increasing efficiency.
--   **Improve Code Quality:** Set standards for code readability, maintainability, and performance optimization.
-
-By providing Cline with carefully crafted instructions, you can significantly improve its accuracy, reliability, and overall effectiveness in aiding your software development process.
-
-## Contributing Custom Instructions
-
-We encourage developers of all skill levels to contribute their custom instructions to this library. Your contributions help build a valuable resource for the entire Cline community!
-
-**When submitting custom instructions, please follow this template:**
-
-### 1. Purpose and Functionality
-
--   **What does this instruction set aim to achieve?**
-
-    -   Provide a clear and concise explanation of the instruction set's goals and intended use cases.
-    -   Example: "This instruction set guides Cline in generating unit tests for existing JavaScript functions."
-
--   **What types of projects or tasks is this best suited for?**
-    -   Outline specific project types, coding languages, or development scenarios where this instruction set is most applicable.
-    -   Example: "This is ideal for JavaScript projects using the Jest testing framework."
-
-### 2. Usage Guide (Optional)
-
--   **Are there specific steps or prerequisites for using this instruction set?**
-    -   If your instructions require specific steps beyond referencing the file in a Cline prompt, provide a detailed guide.
-    -   Examples:
-        -   "Before using this instruction set, create a `tests` folder in your project root."
-        -   "Ensure you have the Jest testing library installed."
-
-### 3. Author & Contributors
-
--   **Who created this instruction set?**
-    -   Provide your name or GitHub username for proper attribution.
--   **Did anyone else contribute?**
-    -   Acknowledge any collaborators or contributors who helped refine or enhance the instructions.
-
-### 4. Custom Instructions
-
--   **Provide the complete set of custom instructions.**
-
-**By using this template and contributing your custom instructions, you help build a thriving ecosystem for Cline, making it a more versatile and efficient tool for developers of all skill levels.**

old_docs/prompting/custom instructions library/cline-memory-bank.md

@@ -1,125 +0,0 @@
-# Cline Memory Bank - Custom Instructions
-
-### 1. Purpose and Functionality
-
--   **What does this instruction set aim to achieve?**
-
-    -   This instruction set transforms Cline into a self-documenting development system that maintains context across sessions through a structured "Memory Bank". It ensures consistent documentation, careful validation of changes, and clear communication with users.
-
--   **What types of projects or tasks is this best suited for?**
-    -   Projects requiring extensive context tracking.
-    -   Any project, regardless of tech stack (tech stack details are stored in `techContext.md`).
-    -   Ongoing and new projects.
-
-### 2. Usage Guide
-
--   **How to Add These Instructions**
-    1. Open VSCode
-    2. Click the Cline extension settings dial ⚙️
-    3. Find the "Custom Instructions" field
-    4. Copy and paste the instructions from the section below
-
-<img width="345" alt="Screenshot 2024-12-26 at 11 22 20 AM" src="https://github.com/user-attachments/assets/8b4ff439-db66-48ec-be13-1ddaa37afa9a" />
-
--   **Project Setup**
-
-    1. Create an empty `cline_docs` folder in your project root (i.e. YOUR-PROJECT-FOLDER/cline_docs)
-    2. For first use, provide a project brief and ask Cline to "initialize memory bank"
-
--   **Best Practices**
-    -   Monitor for `[MEMORY BANK: ACTIVE]` flags during operation.
-    -   Pay attention to confidence checks on critical operations.
-    -   When starting new projects, create a project brief for Cline (paste in chat or include in `cline_docs` as `projectBrief.md`) to use in creating the initial context files.
-        -   note: productBrief.md (or whatever documentation you have) can be any range of technical/nontechnical or just functional. Cline is instructed to fill in the gaps when creating these context files. For example, if you don't choose a tech stack, Cline will for you.
-    -   Start chats with "follow your custom instructions" (you only need to say this once at the beginning of the first chat).
-    -   When prompting Cline to update context files, say "only update the relevant cline_docs"
-    -   Verify documentation updates at the end of sessions by telling Cline "update memory bank".
-    -   Update memory bank at ~2 million tokens and end the session.
-
-### 3. Author & Contributors
-
--   **Author**
-    -   nickbaumann98
--   **Contributors**
-    -   Contributors (Discord: [Cline's #prompts](https://discord.com/channels/1275535550845292637/1275555786621325382)):
-        -   @SniperMunyShotz
-
-### 4. Custom Instructions
-
-```markdown
-# Cline's Memory Bank
-
-You are Cline, an expert software engineer with a unique constraint: your memory periodically resets completely. This isn't a bug - it's what makes you maintain perfect documentation. After each reset, you rely ENTIRELY on your Memory Bank to understand the project and continue work. Without proper documentation, you cannot function effectively.
-
-## Memory Bank Files
-
-CRITICAL: If `cline_docs/` or any of these files don't exist, CREATE THEM IMMEDIATELY by:
-
-1. Reading all provided documentation
-2. Asking user for ANY missing information
-3. Creating files with verified information only
-4. Never proceeding without complete context
-
-Required files:
-
-productContext.md
-
--   Why this project exists
--   What problems it solves
--   How it should work
-
-activeContext.md
-
--   What you're working on now
--   Recent changes
--   Next steps
-    (This is your source of truth)
-
-systemPatterns.md
-
--   How the system is built
--   Key technical decisions
--   Architecture patterns
-
-techContext.md
-
--   Technologies used
--   Development setup
--   Technical constraints
-
-progress.md
-
--   What works
--   What's left to build
--   Progress status
-
-## Core Workflows
-
-### Starting Tasks
-
-1. Check for Memory Bank files
-2. If ANY files missing, stop and create them
-3. Read ALL files before proceeding
-4. Verify you have complete context
-5. Begin development. DO NOT update cline_docs after initializing your memory bank at the start of a task.
-
-### During Development
-
-1. For normal development:
-
-    - Follow Memory Bank patterns
-    - Update docs after significant changes
-
-2. Say `[MEMORY BANK: ACTIVE]` at the beginning of every tool use.
-
-### Memory Bank Updates
-
-When user says "update memory bank":
-
-1. This means imminent memory reset
-2. Document EVERYTHING about current state
-3. Make next steps crystal clear
-4. Complete current task
-
-Remember: After every memory reset, you begin completely fresh. Your only link to previous work is the Memory Bank. Maintain it as if your functionality depends on it - because it does.
-```

old_docs/prompting/custom instructions library/raw-instructions/cline-memory-bank.md

@@ -1,153 +0,0 @@
-# Cline's Memory Bank
-
-I am Cline, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.
-
-## Memory Bank Structure
-
-The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:
-
-```mermaid
-flowchart TD
-    PB[projectbrief.md] --> PC[productContext.md]
-    PB --> SP[systemPatterns.md]
-    PB --> TC[techContext.md]
-    
-    PC --> AC[activeContext.md]
-    SP --> AC
-    TC --> AC
-    
-    AC --> P[progress.md]
-```
-
-### Core Files (Required)
-1. `projectbrief.md`
-   - Foundation document that shapes all other files
-   - Created at project start if it doesn't exist
-   - Defines core requirements and goals
-   - Source of truth for project scope
-
-2. `productContext.md`
-   - Why this project exists
-   - Problems it solves
-   - How it should work
-   - User experience goals
-
-3. `activeContext.md`
-   - Current work focus
-   - Recent changes
-   - Next steps
-   - Active decisions and considerations
-
-4. `systemPatterns.md`
-   - System architecture
-   - Key technical decisions
-   - Design patterns in use
-   - Component relationships
-
-5. `techContext.md`
-   - Technologies used
-   - Development setup
-   - Technical constraints
-   - Dependencies
-
-6. `progress.md`
-   - What works
-   - What's left to build
-   - Current status
-   - Known issues
-
-### Additional Context
-Create additional files/folders within memory-bank/ when they help organize:
-- Complex feature documentation
-- Integration specifications
-- API documentation
-- Testing strategies
-- Deployment procedures
-
-## Core Workflows
-
-### Plan Mode
-```mermaid
-flowchart TD
-    Start[Start] --> ReadFiles[Read Memory Bank]
-    ReadFiles --> CheckFiles{Files Complete?}
-    
-    CheckFiles -->|No| Plan[Create Plan]
-    Plan --> Document[Document in Chat]
-    
-    CheckFiles -->|Yes| Verify[Verify Context]
-    Verify --> Strategy[Develop Strategy]
-    Strategy --> Present[Present Approach]
-```
-
-### Act Mode
-```mermaid
-flowchart TD
-    Start[Start] --> Context[Check Memory Bank]
-    Context --> Update[Update Documentation]
-    Update --> Rules[Update .clinerules if needed]
-    Rules --> Execute[Execute Task]
-    Execute --> Document[Document Changes]
-```
-
-## Documentation Updates
-
-Memory Bank updates occur when:
-1. Discovering new project patterns
-2. After implementing significant changes
-3. When user requests with **update memory bank** (MUST review ALL files)
-4. When context needs clarification
-
-```mermaid
-flowchart TD
-    Start[Update Process]
-    
-    subgraph Process
-        P1[Review ALL Files]
-        P2[Document Current State]
-        P3[Clarify Next Steps]
-        P4[Update .clinerules]
-        
-        P1 --> P2 --> P3 --> P4
-    end
-    
-    Start --> Process
-```
-
-Note: When triggered by **update memory bank**, I MUST review every memory bank file, even if some don't require updates. Focus particularly on activeContext.md and progress.md as they track current state.
-
-## Project Intelligence (.clinerules)
-
-The .clinerules file is my learning journal for each project. It captures important patterns, preferences, and project intelligence that help me work more effectively. As I work with you and the project, I'll discover and document key insights that aren't obvious from the code alone.
-
-```mermaid
-flowchart TD
-    Start{Discover New Pattern}
-    
-    subgraph Learn [Learning Process]
-        D1[Identify Pattern]
-        D2[Validate with User]
-        D3[Document in .clinerules]
-    end
-    
-    subgraph Apply [Usage]
-        A1[Read .clinerules]
-        A2[Apply Learned Patterns]
-        A3[Improve Future Work]
-    end
-    
-    Start --> Learn
-    Learn --> Apply
-```
-
-### What to Capture
-- Critical implementation paths
-- User preferences and workflow
-- Project-specific patterns
-- Known challenges
-- Evolution of project decisions
-- Tool usage patterns
-
-The format is flexible - focus on capturing valuable insights that help me work more effectively with you and the project. Think of .clinerules as a living document that grows smarter as we work together.
-
-REMEMBER: After every memory reset, I begin completely fresh. The Memory Bank is my only link to previous work. It must be maintained with precision and clarity, as my effectiveness depends entirely on its accuracy.

old_docs/tools/cline-tools-guide.md

@@ -1,154 +0,0 @@
-# Cline Tools Reference Guide
-
-## What Can Cline Do?
-
-Cline is your AI assistant that can:
-
--   Edit and create files in your project
--   Run terminal commands
--   Search and analyze your code
--   Help debug and fix issues
--   Automate repetitive tasks
--   Integrate with external tools
-
-## First Steps
-
-1. **Start a Task**
-
-    - Type your request in the chat
-    - Example: "Create a new React component called Header"
-
-2. **Provide Context**
-
-    - Use @ mentions to add files, folders, URLs, diagnostics, terminal output, and more
-    - Example: "@/src/components/App.tsx"
-    - See the [Mentions Feature Guide](./mentions-guide.md) for details
-
-3. **Review Changes**
-    - Cline will show diffs before making changes
-    - You can edit or reject changes
-
-## Key Features
-
-1. **File Editing**
-
-    - Create new files
-    - Modify existing code
-    - Search and replace across files
-
-2. **Terminal Commands**
-
-    - Run npm commands
-    - Start development servers
-    - Install dependencies
-
-3. **Code Analysis**
-
-    - Find and fix errors
-    - Refactor code
-    - Add documentation
-
-4. **Browser Integration**
-    - Test web pages
-    - Capture screenshots
-    - Inspect console logs
-
-## Available Tools
-
-For the most up-to-date implementation details, you can view the full source code in the [Cline repository](https://github.com/cline/cline/blob/main/src/core/task/index.ts).
-
-Cline has access to the following tools for various tasks:
-
-1. **File Operations**
-
-    - `write_to_file`: Create or overwrite files
-    - `read_file`: Read file contents
-    - `replace_in_file`: Make targeted edits to files
-    - `search_files`: Search files using regex
-    - `list_files`: List directory contents
-
-2. **Terminal Operations**
-
-    - `execute_command`: Run CLI commands
-    - `list_code_definition_names`: List code definitions
-
-3. **MCP Tools**
-
-    - `use_mcp_tool`: Use tools from MCP servers
-    - `access_mcp_resource`: Access MCP server resources
-    - Users can create custom MCP tools that Cline can then access
-    - Example: Create a weather API tool that Cline can use to fetch forecasts
-
-4. **Interaction Tools**
-    - `ask_followup_question`: Ask user for clarification
-    - `attempt_completion`: Present final results
-    - `new_task`: Start a new task with preloaded context
-
-Each tool has specific parameters and usage patterns. Here are some examples:
-
--   Create a new file (write_to_file):
-
-    ```xml
-    <write_to_file>
-    <path>src/components/Header.tsx</path>
-    <content>
-    // Header component code
-    </content>
-    </write_to_file>
-    ```
-
--   Search for a pattern (search_files):
-
-    ```xml
-    <search_files>
-    <path>src</path>
-    <regex>function\s+\w+\(</regex>
-    <file_pattern>*.ts</file_pattern>
-    </search_files>
-    ```
-
--   Run a command (execute_command):
-    ```xml
-    <execute_command>
-    <command>npm install axios</command>
-    <requires_approval>false</requires_approval>
-    </execute_command>
-    ```
-
--   Start a new task with context (new_task):
-    ```xml
-    <new_task>
-    <context>
-    We've completed the backend API with these endpoints:
-    - GET /api/tasks
-    - POST /api/tasks
-    - PUT /api/tasks/:id
-    - DELETE /api/tasks/:id
-
-    Now we need to implement the React frontend.
-    </context>
-    </new_task>
-    ```
-
-## Common Tasks
-
-1. **Create a New Component**
-
-    - "Create a new React component called Footer"
-
-2. **Fix a Bug**
-
-    - "Fix the error in src/utils/format.ts"
-
-3. **Refactor Code**
-
-    - "Refactor the Button component to use TypeScript"
-
-4. **Run Commands**
-    - "Run npm install to add axios"
-
-## Getting Help
-
--   [Join the Discord community](https://discord.gg/cline)
--   Check the documentation
--   Provide feedback to improve Cline

old_docs/tools/mentions-guide.md

@@ -1,205 +0,0 @@
-# Cline Mentions Feature Guide
-
-## Overview
-
-The mentions feature is a powerful capability that allows you to reference various resources in your conversations with Cline using the "@" symbol. This includes file contents, directory structures, webpage URLs, VSCode diagnostic information, terminal output, Git change status, and more - all easily incorporated into your conversations.
-
-By using this feature, Cline can gain more accurate context and provide more relevant assistance for your tasks.
-
-## Basic Syntax
-
-Mentions always start with the "@" symbol, followed by the path or identifier of the resource you want to reference:
-
-```
-@resource_identifier
-```
-
-You can place mentions anywhere in your user messages, and Cline will automatically retrieve the referenced content.
-
-## Supported Mention Types
-
-### 1. File References
-
-To reference file contents, use `@/` followed by the relative path within your project:
-
-```
-@/path/to/file.js
-```
-
-**Example:**
-```
-Please analyze the implementation in @/src/components/Button.tsx
-```
-
-In this example, Cline automatically retrieves the contents of Button.tsx and uses it to perform the analysis.
-
-### 2. Directory References
-
-To reference directory contents, use `@/` followed by the relative path of the directory, ending with a trailing `/`:
-
-```
-@/path/to/directory/
-```
-
-**Example:**
-```
-What components are available in the @/src/components/ directory?
-```
-
-In this example, Cline retrieves a listing of the components directory and its contents.
-
-### 3. URL References
-
-To reference web page contents, use `@` followed by the URL:
-
-```
-@https://example.com
-```
-
-**Example:**
-```
-Please parse the JSON response from @https://api.github.com/users/octocat
-```
-
-In this example, Cline fetches the response from the GitHub API and analyzes the JSON.
-
-### 4. Diagnostic References
-
-To reference VSCode diagnostic information (errors and warnings) in the current workspace, use `@problems`:
-
-```
-@problems
-```
-
-**Example:**
-```
-Check @problems and tell me which errors I should prioritize fixing
-```
-
-In this example, Cline retrieves the current errors and warnings from your workspace and identifies high-priority issues.
-
-### 5. Terminal Output References
-
-To reference the latest terminal output, use `@terminal`:
-
-```
-@terminal
-```
-
-**Example:**
-```
-Please identify the cause of the error in the @terminal output
-```
-
-In this example, Cline examines the latest terminal output and analyzes the error's cause.
-
-### 6. Git Working Directory References
-
-To reference the current Git working directory change status, use `@git-changes`:
-
-```
-@git-changes
-```
-
-**Example:**
-```
-Review the @git-changes and summarize the important changes that should be committed
-```
-
-In this example, Cline retrieves the list of changed files in the current Git working directory and identifies candidates for commit.
-
-### 7. Git Commit References
-
-To reference information about a specific Git commit, use `@` followed by the commit hash:
-
-```
-@commit_hash
-```
-
-**Example:**
-```
-Analyze the commit @abcd123 and explain what changes were made
-```
-
-In this example, Cline retrieves information about the specified commit hash and analyzes the changes made in that commit.
-
-## Usage Scenarios
-
-### Code Review
-
-```
-Check @/src/components/Form.jsx and suggest improvements from a performance perspective. Also, if there are any @problems, please suggest how to fix them.
-```
-
-### Debugging Assistance
-
-```
-My npm install failed. Please examine the @terminal output and suggest a solution to the problem.
-```
-
-### Project Analysis
-
-```
-Analyze the code in the @/src/models/ directory and explain the relationships between the data models. Also, tell me how the utility functions in @/src/utils/ are used with these models.
-```
-
-### Code Generation
-
-```
-Create a new Input.tsx component using the same design language as @/src/components/Button.tsx
-```
-
-### Version Control Integration
-
-```
-Review the @git-changes and suggest a commit message for the feature I'm working on.
-```
-
-## Combining Multiple Mentions
-
-You can combine multiple mentions to provide more complex context:
-
-```
-There seems to be a bug in @/src/api/users.js. Please check @problems and @terminal to identify and fix the issue.
-```
-
-## Limitations and Considerations
-
-1. **Large Files**: Referencing very large files may take time to process and could consume a significant amount of tokens.
-
-2. **Binary Files**: Binary files (such as images) will not be properly processed and will show a "Binary file" message.
-
-3. **Directory Structure**: Directory references will only show top-level files and directories, not recursively showing the contents of subdirectories.
-
-4. **URL Limitations**: Some websites may block automated crawling, which could prevent accurate content retrieval.
-
-5. **Path Syntax**: File paths or URLs with special characters (such as spaces) may not be recognized correctly.
-
-## Troubleshooting
-
-### Mentions Not Recognized
-
-If your mentions aren't being recognized correctly, check that:
-
-- There's no space after the `@` symbol
-- File paths are accurate (case-sensitive)
-- URLs include the full format (with `https://`)
-
-### Content Not Retrieved
-
-If the content of referenced resources can't be retrieved:
-
-- Verify the file exists
-- Ensure you have access permissions for the file
-- Check that the file isn't too large or the URL too complex
-
-### Performance Issues
-
-If mention processing is slow:
-
-- Reference smaller files or specific file sections
-- Reduce the number of mentions used at once
-
-## Conclusion
-
-Mastering the mentions feature makes your communication with Cline more efficient. By providing appropriate context, Cline can deliver more accurate assistance, significantly improving your development workflow.

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": "3.26.3",
+	"version": "3.27.1",
 	"icon": "assets/icons/icon.png",
 	"engines": {
 		"vscode": "^1.84.0"
@@ -102,15 +102,8 @@
 			"activitybar": [
 				{
 					"id": "claude-dev-ActivityBar",
-					"title": "Cline (⌘+')",
-					"icon": "assets/icons/icon.svg",
-					"when": "isMac"
-				},
-				{
-					"id": "claude-dev-ActivityBar",
-					"title": "Cline (Ctrl+')",
-					"icon": "assets/icons/icon.svg",
-					"when": "!isMac"
+					"title": "Cline",
+					"icon": "assets/icons/icon.svg"
 				}
 			]
 		},
@@ -362,17 +355,16 @@
 		"test:integration": "vscode-test",
 		"test:unit": "TS_NODE_PROJECT='./tsconfig.unit-test.json' mocha",
 		"test:coverage": "vscode-test --coverage",
+		"test:sca-server": "npx tsx watch scripts/test-standalone-core-api-server.ts",
 		"e2e": "playwright test -c playwright.config.ts",
 		"test:e2e": "playwright install && vsce package --no-dependencies --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test",
 		"test:e2e:optimal": "vsce package --no-dependencies --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test",
-		"test:scenarios": "playwright install && vsce package --no-dependencies --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test -c playwright.scenarios.config.ts",
-		"test:scenarios:optimal": "vsce package --no-dependencies --allow-package-secrets sendgrid --out dist/e2e.vsix && node src/test/e2e/utils/build.mjs && playwright test -c playwright.scenarios.config.ts",
 		"install:all": "npm install && cd webview-ui && npm install",
 		"dev:webview": "cd webview-ui && npm run dev",
 		"build:webview": "cd webview-ui && npm run build",
 		"test:webview": "cd webview-ui && npm run test",
-		"publish:marketplace": "vsce publish ${VSIX_PATH:+--packagePath $VSIX_PATH} && ovsx publish ${VSIX_PATH:+--packagePath $VSIX_PATH}",
-		"publish:marketplace:prerelease": "vsce publish --pre-release ${VSIX_PATH:+--packagePath $VSIX_PATH} && ovsx publish --pre-release ${VSIX_PATH:+--packagePath $VSIX_PATH}",
+		"publish:marketplace": "vsce publish --allow-package-secrets sendgrid && ovsx publish",
+		"publish:marketplace:prerelease": "vsce publish --allow-package-secrets sendgrid --pre-release && ovsx publish --pre-release",
 		"prepare": "husky",
 		"changeset": "changeset",
 		"version-packages": "changeset version",
@@ -390,6 +382,7 @@
 		"@biomejs/biome": "^2.1.4",
 		"@bufbuild/buf": "^1.54.0",
 		"@changesets/cli": "^2.27.12",
+		"@types/better-sqlite3": "^7.6.13",
 		"@types/chai": "^5.0.1",
 		"@types/clone-deep": "^4.0.4",
 		"@types/diff": "^5.2.1",
@@ -413,6 +406,7 @@
 		"lint-staged": "^16.1.0",
 		"minimatch": "^3.0.3",
 		"npm-run-all": "^4.1.5",
+		"prebuild-install": "^7.1.3",
 		"protoc-gen-ts": "^0.8.7",
 		"proxyquire": "^2.1.3",
 		"rimraf": "^6.0.1",
@@ -431,7 +425,7 @@
 		"@bufbuild/protobuf": "^2.2.5",
 		"@cerebras/cerebras_cloud_sdk": "^1.35.0",
 		"@google-cloud/vertexai": "^1.9.3",
-		"@google/genai": "1.0.0",
+		"@google/genai": "^1.11.0",
 		"@grpc/grpc-js": "^1.9.15",
 		"@grpc/reflection": "^1.0.4",
 		"@mistralai/mistralai": "^1.5.0",
@@ -443,6 +437,8 @@
 		"@opentelemetry/sdk-trace-node": "^1.30.1",
 		"@opentelemetry/semantic-conventions": "^1.30.0",
 		"@playwright/test": "^1.53.2",
+		"@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",
 		"@types/uuid": "^10.0.0",
@@ -470,7 +466,6 @@
 		"jschardet": "^3.1.4",
 		"jwt-decode": "^4.0.0",
 		"mammoth": "^1.8.0",
-		"monaco-vscode-textmate-theme-converter": "^0.1.7",
 		"nice-grpc": "^2.1.12",
 		"ollama": "^0.5.13",
 		"open": "^10.1.2",
@@ -480,7 +475,7 @@
 		"p-timeout": "^6.1.4",
 		"p-wait-for": "^5.0.2",
 		"pdf-parse": "^1.1.1",
-		"posthog-node": "^4.8.1",
+		"posthog-node": "^5.8.0",
 		"puppeteer-chromium-resolver": "^23.0.0",
 		"puppeteer-core": "^23.4.0",
 		"reconnecting-eventsource": "^1.6.4",

playwright.scenarios.config.ts

@@ -1,35 +0,0 @@
-import { defineConfig } from "@playwright/test"
-
-const isCI = !!process?.env?.CI
-const isWindow = process?.platform?.startsWith("win")
-
-export default defineConfig({
-	workers: 1,
-	retries: 1,
-	forbidOnly: isCI,
-	// Point to scenarios directory
-	testDir: "src/test/scenarios",
-	// Include all .ts in scenarios (we add a local global.setup.ts here)
-	testMatch: /.*\.ts/,
-	timeout: isCI || isWindow ? 40000 : 20000,
-	expect: {
-		timeout: isCI || isWindow ? 5000 : 2000,
-	},
-	fullyParallel: true,
-	reporter: isCI ? [["github"], ["list"]] : [["list"]],
-	use: {
-		video: "retain-on-failure",
-	},
-	projects: [
-		{
-			name: "setup test environment",
-			// Reuse E2E setup file to avoid duplication
-			testDir: "src/test/e2e/utils",
-			testMatch: /global\.setup\.ts/,
-		},
-		{
-			name: "scenario tests",
-			dependencies: ["setup test environment"],
-		},
-	],
-})

proto/cline/browser.proto

@@ -2,6 +2,7 @@ syntax = "proto3";
 
 package cline;
 import "cline/common.proto";
+import "cline/state.proto";
 option java_package = "bot.cline.proto";
 option java_multiple_files = true;
 
@@ -10,7 +11,6 @@ service BrowserService {
   rpc testBrowserConnection(StringRequest) returns (BrowserConnection);
   rpc discoverBrowser(EmptyRequest) returns (BrowserConnection);
   rpc getDetectedChromePath(EmptyRequest) returns (ChromePath);
-  rpc updateBrowserSettings(UpdateBrowserSettingsRequest) returns (Boolean);
   rpc relaunchChromeDebugMode(EmptyRequest) returns (String);
 }
 
@@ -31,11 +31,6 @@ message ChromePath {
   bool is_bundled = 2;
 }
 
-message Viewport {
-  int32 width = 1;
-  int32 height = 2;
-}
-
 message BrowserSettings {
   Viewport viewport = 1;
   optional string remote_browser_host = 2;

proto/cline/common.proto

@@ -8,19 +8,16 @@ message Metadata {
 }
 
 message EmptyRequest {
-  Metadata metadata = 1;
 }
 
 message Empty {
 }
 
 message StringRequest {
-  Metadata metadata = 1;
   string value = 2;
 }
 
 message StringArrayRequest {
-  Metadata metadata = 1;
   repeated string value = 2;
 }
 
@@ -29,7 +26,6 @@ message String {
 }
 
 message Int64Request {
-  Metadata metadata = 1;
   int64 value = 2;
 }
 
@@ -38,7 +34,6 @@ message Int64 {
 }
 
 message BytesRequest {
-  Metadata metadata = 1;
   bytes value = 2;
 }
 
@@ -47,7 +42,6 @@ message Bytes {
 }
 
 message BooleanRequest {
-  Metadata metadata = 1;
   bool value = 2;
 }
 

proto/cline/models.proto

@@ -32,7 +32,7 @@ service ModelsService {
   // Refreshes and returns Baseten models
   rpc refreshBasetenModels(EmptyRequest) returns (OpenRouterCompatibleModelInfo);
   // Fetches available models from SAP AI Core
-  rpc getSapAiCoreModels(SapAiCoreModelsRequest) returns (StringArray);
+  rpc getSapAiCoreModels(SapAiCoreModelsRequest) returns (SapAiCoreModelsResponse);
 }
 
 // List of VS Code LM models
@@ -50,20 +50,20 @@ message LanguageModelChatSelector {
 
 // Price tier for tiered pricing models
 message PriceTier {
-  int32 token_limit = 1;  // Upper limit (inclusive) of input tokens for this price
+  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 int32 max_budget = 1;                    // Max allowed thinking budget tokens
+  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
 message ModelTier {
-  int32 context_window = 1;
+  int64 context_window = 1;
   optional double input_price = 2;
   optional double output_price = 3;
   optional double cache_writes_price = 4;
@@ -108,6 +108,19 @@ message SapAiCoreModelsRequest {
   string resource_group = 6;
 }
 
+// SAP AI Core model with deployment information
+message SapAiCoreModelDeployment {
+  string model_name = 1;
+  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
 message UpdateApiConfigurationRequest {
   Metadata metadata = 1;
@@ -149,12 +162,14 @@ enum ApiProvider {
   BASETEN = 30;
   ZAI = 31;
   VERCEL_AI_GATEWAY = 32;
+  QWEN_CODE = 33;
+  DIFY = 34;
 }
 
 // Model info for OpenAI-compatible models
 message OpenAiCompatibleModelInfo {
-  optional int32 max_tokens = 1;
-  optional int32 context_window = 2;
+  optional int64 max_tokens = 1;
+  optional int64 context_window = 2;
   optional bool supports_images = 3;
   bool supports_prompt_cache = 4;
   optional double input_price = 5;
@@ -171,8 +186,8 @@ message OpenAiCompatibleModelInfo {
 
 // Model info for LiteLLM models
 message LiteLLMModelInfo {
-  optional int32 max_tokens = 1;
-  optional int32 context_window = 2;
+  optional int64 max_tokens = 1;
+  optional int64 context_window = 2;
   optional bool supports_images = 3;
   bool supports_prompt_cache = 4;
   optional double input_price = 5;
@@ -224,8 +239,8 @@ message ModelsApiConfiguration {
   optional string requesty_base_url = 33;
   optional string together_api_key = 34;
   optional string fireworks_api_key = 35;
-  optional int32 fireworks_model_max_completion_tokens = 36;
-  optional int32 fireworks_model_max_tokens = 37;
+  optional int64 fireworks_model_max_completion_tokens = 36;
+  optional int64 fireworks_model_max_tokens = 37;
   optional string qwen_api_key = 38;
   optional string doubao_api_key = 39;
   optional string mistral_api_key = 40;
@@ -237,31 +252,35 @@ message ModelsApiConfiguration {
   optional string xai_api_key = 46;
   optional string sambanova_api_key = 47;
   optional string cerebras_api_key = 48;
-  optional int32 request_timeout_ms = 49;
+  optional int64 request_timeout_ms = 49;
   optional string sap_ai_core_client_id = 50;
   optional string sap_ai_core_client_secret = 51;
   optional string sap_ai_resource_group = 52;
   optional string sap_ai_core_token_url = 53;
   optional string sap_ai_core_base_url = 54;
-  optional string moonshot_api_key = 55;
-  optional string moonshot_api_line = 56;
-  optional string aws_authentication = 57;
-  optional string aws_bedrock_api_key = 58;
-  optional string cline_account_id = 59;
-  optional string groq_api_key = 60;
-  optional string hugging_face_api_key = 61;
-  optional string huawei_cloud_maas_api_key = 62;
-  optional string baseten_api_key = 63;
-  optional string ollama_api_key = 64;
-  optional string zai_api_key = 65;
-  optional string zai_api_line = 66;
-  optional string lm_studio_max_tokens = 67;
-  optional string vercel_ai_gateway_api_key = 68;
+  optional bool sap_ai_core_use_orchestration_mode = 55;
+  optional string moonshot_api_key = 56;
+  optional string moonshot_api_line = 57;
+  optional string aws_authentication = 58;
+  optional string aws_bedrock_api_key = 59;
+  optional string cline_account_id = 60;
+  optional string groq_api_key = 61;
+  optional string hugging_face_api_key = 62;
+  optional string huawei_cloud_maas_api_key = 63;
+  optional string baseten_api_key = 64;
+  optional string ollama_api_key = 65;
+  optional string zai_api_key = 66;
+  optional string zai_api_line = 67;
+  optional string lm_studio_max_tokens = 68;
+  optional string vercel_ai_gateway_api_key = 69;
+  optional string qwen_code_oauth_path = 70;
+  optional string dify_api_key = 71;
+  optional string dify_base_url = 72;
 
   // Plan mode configurations
   optional ApiProvider plan_mode_api_provider = 100;
   optional string plan_mode_api_model_id = 101;
-  optional int32 plan_mode_thinking_budget_tokens = 102;
+  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;
@@ -279,21 +298,23 @@ message ModelsApiConfiguration {
   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_groq_model_id = 120;
-  optional OpenRouterModelInfo plan_mode_groq_model_info = 121;
-  optional string plan_mode_hugging_face_model_id = 122;
-  optional OpenRouterModelInfo plan_mode_hugging_face_model_info = 123;
-  optional string plan_mode_huawei_cloud_maas_model_id = 124;
-  optional OpenRouterModelInfo plan_mode_huawei_cloud_maas_model_info = 125; 
-  optional string plan_mode_baseten_model_id = 126;
-  optional OpenRouterModelInfo plan_mode_baseten_model_info = 127;
-  optional string plan_mode_vercel_ai_gateway_model_id = 128;
-  optional OpenRouterModelInfo plan_mode_vercel_ai_gateway_model_info = 129;
+  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;
+
 
   // Act mode configurations
   optional ApiProvider act_mode_api_provider = 200;
   optional string act_mode_api_model_id = 201;
-  optional int32 act_mode_thinking_budget_tokens = 202;
+  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;
@@ -311,16 +332,18 @@ message ModelsApiConfiguration {
   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_groq_model_id = 220;
-  optional OpenRouterModelInfo act_mode_groq_model_info = 221;
-  optional string act_mode_hugging_face_model_id = 222;
-  optional OpenRouterModelInfo act_mode_hugging_face_model_info = 223;
-  optional string act_mode_huawei_cloud_maas_model_id = 224;
-  optional OpenRouterModelInfo act_mode_huawei_cloud_maas_model_info = 225;
-  optional string act_mode_baseten_model_id = 226;
-  optional OpenRouterModelInfo act_mode_baseten_model_info = 227;
-  optional string act_mode_vercel_ai_gateway_model_id = 228;
-  optional OpenRouterModelInfo act_mode_vercel_ai_gateway_model_info = 229;
+  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;
+
 
   repeated string favorited_model_ids = 300;
 }

proto/cline/state.proto

@@ -8,7 +8,6 @@ service StateService {
   rpc getLatestState(EmptyRequest) returns (State);
   rpc updateTerminalConnectionTimeout(UpdateTerminalConnectionTimeoutRequest) returns (UpdateTerminalConnectionTimeoutResponse);
   rpc updateTerminalReuseEnabled(BooleanRequest) returns (Empty);
-  rpc updateDefaultTerminalProfile(StringRequest) returns (TerminalProfileUpdateResponse);
   rpc getAvailableTerminalProfiles(EmptyRequest) returns (TerminalProfiles);
   rpc subscribeToState(EmptyRequest) returns (stream State);
   rpc toggleFavoriteModel(StringRequest) returns (Empty);
@@ -56,6 +55,7 @@ enum OpenaiReasoningEffort {
   LOW = 0;
   MEDIUM = 1;
   HIGH = 2;
+  MINIMAL = 3;
 }
 
 enum McpDisplayMode {
@@ -106,6 +106,16 @@ message TelemetrySettingRequest {
   TelemetrySettingEnum setting = 2;
 }
 
+// Browser settings for UpdateSettingsRequest
+message BrowserSettingsUpdate {
+  optional Viewport viewport = 1;
+  optional string remote_browser_host = 2;
+  optional bool remote_browser_enabled = 3;
+  optional string chrome_executable_path = 4;
+  optional bool disable_tool_use = 5;
+  optional string custom_args = 6;
+}
+
 // Message for updating settings
 message UpdateSettingsRequest {
   Metadata metadata = 1;
@@ -126,6 +136,8 @@ message UpdateSettingsRequest {
   optional FocusChainSettings focus_chain_settings = 17;
   optional bool use_auto_condense = 18;
   optional string custom_prompt = 19;
+  optional BrowserSettingsUpdate browser_settings = 20;
+  optional string default_terminal_profile = 21;
 }
 
 // Complete API Configuration message
@@ -193,6 +205,9 @@ message ApiConfiguration {
   optional string zai_api_line = 60;
   optional string lm_studio_max_tokens = 61;
   optional string vercel_ai_gateway_api_key = 62;
+  optional string qwen_code_oauth_path = 63;
+  optional string dify_api_key = 64;
+  optional string dify_base_url = 65;
   
   // Plan mode configurations
   optional string plan_mode_api_provider = 100;
@@ -265,6 +280,11 @@ message FocusChainSettings {
   int32 remind_cline_interval = 2;
 }
 
+message Viewport {
+  int32 width = 1;
+  int32 height = 2;
+}
+
 message UpdateTerminalConnectionTimeoutResponse {
   optional int32 timeout_ms = 1;
 }

proto/cline/ui.proto

@@ -249,9 +249,6 @@ service UiService {
   // Subscribe to partial message updates (streaming Cline messages as they're built)
   rpc subscribeToPartialMessage(EmptyRequest) returns (stream ClineMessage);
   
-  // Subscribe to theme change events
-  rpc subscribeToTheme(EmptyRequest) returns (stream String);
-  
   // Initialize webview when it launches
   rpc initializeWebview(EmptyRequest) returns (Empty);
   

proto/host/env.proto

@@ -18,6 +18,10 @@ service EnvService {
   rpc getMachineId(cline.EmptyRequest) returns (cline.String);
 
   rpc getHostVersion(cline.EmptyRequest) returns (GetHostVersionResponse);
+
+  rpc getTelemetrySettings(cline.EmptyRequest) returns (GetTelemetrySettingsResponse);
+
+  rpc subscribeToTelemetrySettings(cline.EmptyRequest) returns (stream TelemetrySettingsEvent);
 }
 
 message GetHostVersionResponse {
@@ -26,3 +30,16 @@ message GetHostVersionResponse {
   // The version of the host platform, e.g. 1.103.0
   optional string version = 2;
 }
+
+enum Setting {
+  UNSUPPORTED = 0; // This host does not support this setting.
+  ENABLED = 1;
+  DISABLED = 2;
+}
+message GetTelemetrySettingsResponse {
+  Setting is_enabled = 1;
+}
+
+message TelemetrySettingsEvent {
+  Setting is_enabled = 1; 
+}

proto/host/window.proto

@@ -4,8 +4,6 @@ package host;
 option java_package = "bot.cline.host.proto";
 option java_multiple_files = true;
 
-import "cline/common.proto";
-
 // Provides methods for working with IDE windows and editors.
 service WindowService {
   // Opens a text document in the IDE editor and returns editor information.
@@ -40,7 +38,6 @@ service WindowService {
 }
 
 message ShowTextDocumentRequest {
-  cline.Metadata metadata = 1;
   string path = 2;
   optional ShowTextDocumentOptions options = 3;
 }
@@ -59,7 +56,6 @@ message TextEditorInfo {
 }
 
 message ShowOpenDialogueRequest {
-  cline.Metadata metadata = 1;
   optional bool can_select_many = 2;
   optional string open_label = 3;
   optional ShowOpenDialogueFilterOption filters = 4;

proto/host/workspace.proto

@@ -18,14 +18,15 @@ service WorkspaceService {
 
   // Get diagnostics from the workspace.
   rpc getDiagnostics(GetDiagnosticsRequest) returns (GetDiagnosticsResponse);
-  // Returns workspace items (files/folders) matching a query for mention autocomplete
-  rpc searchWorkspaceItems(SearchWorkspaceItemsRequest) returns (SearchWorkspaceItemsResponse);
 
   // Makes the problems panel/pane visible in the IDE and focuses it.
   rpc openProblemsPanel(OpenProblemsPanelRequest) returns (OpenProblemsPanelResponse);
 
   // Opens the IDE file explorer panel and selects a file or directory.
   rpc openInFileExplorerPanel(OpenInFileExplorerPanelRequest) returns (OpenInFileExplorerPanelResponse); 
+
+  // Opens and focuses the Cline sidebar panel in the host IDE.
+  rpc openClineSidebarPanel(OpenClineSidebarPanelRequest) returns (OpenClineSidebarPanelResponse);
 }
 
 message GetWorkspacePathsRequest {
@@ -86,3 +87,7 @@ message OpenInFileExplorerPanelRequest {
   string path = 1;
 }
 message OpenInFileExplorerPanelResponse {}
+
+// Request/response for opening the Cline sidebar
+message OpenClineSidebarPanelRequest {}
+message OpenClineSidebarPanelResponse {}

scripts/build-proto.mjs

@@ -10,7 +10,6 @@ import * as path from "path"
 import { rmrf } from "./file-utils.mjs"
 import { main as generateHostBridgeClient } from "./generate-host-bridge-client.mjs"
 import { main as generateProtoBusSetup } from "./generate-protobus-setup.mjs"
-import { loadProtoDescriptorSet } from "./proto-utils.mjs"
 
 const require = createRequire(import.meta.url)
 const PROTOC = path.join(require.resolve("grpc-tools"), "../bin/protoc")
@@ -31,14 +30,13 @@ const TS_PROTO_OPTIONS = [
 	"esModuleInterop=true",
 	"outputServices=generic-definitions", // output generic ServiceDefinitions
 	"outputIndex=true", // output an index file for each package which exports all protos in the package.
-	"useOptionals=messages", // Message fields are optional, scalars are not.
+	"useOptionals=none", // scalar and message fields are required unless they are marked as optional.
 	"useDate=false", // Timestamp fields will not be automatically converted to Date.
 ]
 
 async function main() {
 	await cleanup()
 	await compileProtos()
-	await checkProtos()
 	await generateProtoBusSetup()
 	await generateHostBridgeClient()
 }
@@ -187,51 +185,6 @@ function checkAppleSiliconCompatibility() {
 	}
 }
 
-const int64TypeNames = ["TYPE_INT64", "TYPE_UINT64", "TYPE_SINT64", "TYPE_FIXED64", "TYPE_SFIXED64"]
-
-async function checkProtos() {
-	const proto = await loadProtoDescriptorSet()
-	const int64Fields = []
-
-	for (const [packageName, packageDef] of Object.entries(proto)) {
-		for (const [messageName, def] of Object.entries(packageDef)) {
-			// Skip service definitions
-			if (def && typeof def === "object" && "service" in def) {
-				continue
-			}
-			// Check message fields
-			if (def && def.type && def.type.field) {
-				for (const field of def.type.field) {
-					if (int64TypeNames.includes(field.type)) {
-						const name = `${packageName}.${messageName}.${field.name}`
-						int64Fields.push({
-							name: name,
-							type: field.type,
-						})
-					}
-				}
-			}
-		}
-	}
-
-	if (int64Fields.length > 0) {
-		console.log(chalk.yellow(`\nWarning: Found ${int64Fields.length} fields using 64-bit integer types`))
-		for (const field of int64Fields) {
-			const typeNames = {
-				TYPE_INT64: "int64",
-				TYPE_UINT64: "uint64",
-				TYPE_SINT64: "sint64",
-				TYPE_FIXED64: "fixed64",
-				TYPE_SFIXED64: "sfixed64",
-			}
-			log_verbose(chalk.yellow(`  - ${field.name} (${typeNames[field.type]})`))
-		}
-		log_verbose(chalk.yellow("\nWARNING: 64-bit integer fields detected in proto definitions"))
-		log_verbose(chalk.yellow("JavaScript cannot safely represent integers larger than 2^53-1 (Number.MAX_SAFE_INTEGER)."))
-		log_verbose(chalk.yellow("Consider using string representation for large numbers or implementing BigInt support.\n"))
-	}
-}
-
 function log_verbose(s) {
 	if (process.argv.includes("-v") || process.argv.includes("--verbose")) {
 		console.log(s)

scripts/package-standalone.mjs

@@ -6,40 +6,102 @@ import fs from "fs"
 import { cp } from "fs/promises"
 import { glob } from "glob"
 import minimatch from "minimatch"
+import os from "os"
 import path from "path"
+import { rmrf } from "./file-utils.mjs"
 
 const BUILD_DIR = "dist-standalone"
+const BINARIES_DIR = `${BUILD_DIR}/binaries`
 const RUNTIME_DEPS_DIR = "standalone/runtime-files"
+const IS_DEBUG_BUILD = process.env.IS_DEBUG_BUILD === "true"
+
+// This should match the node version packaged with the JetBrains plugin.
+const TARGET_NODE_VERSION = "22.15.0"
+const TARGET_PLATFORMS = [
+	{ platform: "win32", arch: "x64", targetDir: "win-x64" },
+	{ platform: "darwin", arch: "x64", targetDir: "darwin-x64" },
+	{ platform: "darwin", arch: "arm64", targetDir: "darwin-arm64" },
+	{ platform: "linux", arch: "x64", targetDir: "linux-x64" },
+]
+const SUPPORTED_BINARY_MODULES = ["better-sqlite3"]
+
+const UNIVERSAL_BUILD = !process.argv.includes("-s")
+const IS_VERBOSE = process.argv.includes("-v") || process.argv.includes("--verbose")
 
 async function main() {
 	await installNodeDependencies()
+	if (UNIVERSAL_BUILD) {
+		console.log("Building universal package for all platforms...")
+		await packageAllBinaryDeps()
+	} else {
+		console.log(`Building package for ${os.platform()}-${os.arch()}...`)
+	}
 	await zipDistribution()
 }
 
 async function installNodeDependencies() {
+	// Clean modules from any previous builds
+	await rmrf(path.join(BUILD_DIR, "node_modules"))
+	await rmrf(path.join(BINARIES_DIR))
+
 	await cpr(RUNTIME_DEPS_DIR, BUILD_DIR)
 
 	console.log("Running npm install in distribution directory...")
-	const cwd = process.cwd()
-	process.chdir(BUILD_DIR)
+	execSync("npm install", { stdio: "inherit", cwd: BUILD_DIR })
 
-	try {
-		execSync("npm install", { stdio: "inherit" })
-		// Move the vscode directory into node_modules.
-		// It can't be installed using npm because it will create a symlink which cannot be unzipped correctly on windows.
-		fs.renameSync("vscode", path.join("node_modules", "vscode"))
-	} catch (error) {
-		console.error("Error during setup:", error)
+	// Move the vscode directory into node_modules.
+	// It can't be installed using npm because it will create a symlink which cannot be unzipped correctly on windows.
+	fs.renameSync(`${BUILD_DIR}/vscode`, `${BUILD_DIR}/node_modules/vscode`)
+}
+
+/**
+ * Downloads prebuilt binaries for each platform for the modules that include binaries. It uses `npx prebuild-install`
+ * to download the binary.
+ *
+ * The modules are downloaded to dist-standalone/binaries/{os}-{platform}/.
+ * When cline-core is installed, the installer should use the correct module for the current platform.
+ */
+async function packageAllBinaryDeps() {
+	// Check for native .node modules.
+	const allNativeModules = await glob("**/*.node", { cwd: path.join(BUILD_DIR, "node_modules"), nodir: true })
+	const isAllowed = (path) => SUPPORTED_BINARY_MODULES.some((allowed) => path.includes(allowed))
+	const blocked = allNativeModules.filter((x) => !isAllowed(x))
+
+	if (blocked.length > 0) {
+		console.error(`Error: Native node modules cannot be included in the standalone distribution:\n\n${blocked.join("\n")}`)
+		console.error(
+			"\nThese modules must support prebuilt-install and be added to the supported list in scripts/package-standalone.mjs",
+		)
 		process.exit(1)
-	} finally {
-		process.chdir(cwd)
 	}
 
-	// Check for native .node modules.
-	const nativeModules = await glob("**/*.node", { cwd: BUILD_DIR, nodir: true })
-	if (nativeModules.length > 0) {
-		console.error("Native node modules cannot be included in the standalone distribution:\n", nativeModules.join("\n"))
-		process.exit(1)
+	for (const module of SUPPORTED_BINARY_MODULES) {
+		console.log(`Installing binaries for ${module}...`)
+		const src = path.join(BUILD_DIR, "node_modules", module)
+		if (!fs.existsSync(src)) {
+			console.warn(`Warning: Trying to install binaries for the module '${module}', but it is not being used by cline.`)
+			continue
+		}
+
+		for (const { platform, arch, targetDir } of TARGET_PLATFORMS) {
+			const binaryDir = `${BINARIES_DIR}/${targetDir}/node_modules`
+			fs.mkdirSync(binaryDir, { recursive: true })
+
+			// Copy the module from the build dir
+			const dest = path.join(binaryDir, module)
+			await cpr(src, dest)
+
+			// Download the binary libs
+			const v = IS_VERBOSE ? "--verbose" : ""
+			const cmd = `npx prebuild-install --platform=${platform} --arch=${arch} --target=${TARGET_NODE_VERSION} ${v}`
+			log_verbose(`${module}: ${cmd}`)
+			execSync(cmd, { cwd: dest, stdio: "inherit" })
+			log_verbose("")
+		}
+		// Remove the original module with the host platform binaries installed directly into node_modules.
+		log_verbose(`Cleaning up host version of ${module}`)
+		await rmrf(src)
+		log_verbose("")
 	}
 }
 
@@ -47,10 +109,13 @@ async function zipDistribution() {
 	// Zip the build directory (excluding any pre-existing output zip).
 	const zipPath = path.join(BUILD_DIR, "standalone.zip")
 	const output = fs.createWriteStream(zipPath)
-	const archive = archiver("zip", { zlib: { level: 3 } })
+	const startTime = Date.now()
+	const archive = archiver("zip", { zlib: { level: 6 } })
 
 	output.on("close", () => {
-		console.log(`Created ${zipPath} (${(archive.pointer() / 1024 / 1024).toFixed(1)} MB)`)
+		const endTime = Date.now()
+		const duration = (endTime - startTime) / 1000
+		console.log(`Created ${zipPath} (${(archive.pointer() / 1024 / 1024).toFixed(1)} MB) in ${duration.toFixed(2)} seconds`)
 	})
 	archive.on("warning", (err) => {
 		console.warn(`Warning: ${err}`)
@@ -73,7 +138,7 @@ async function zipDistribution() {
 	// Add the whole cline directory under "extension", except the for the ignored files.
 	archive.directory(process.cwd(), "extension", (entry) => {
 		if (isIgnored(entry.name)) {
-			log_verbose("Ignoring", entry.name)
+			//log_verbose("Ignoring", entry.name)
 			return false
 		}
 		return entry
@@ -145,7 +210,7 @@ function createIsIgnored(standaloneIgnores) {
 	let allIgnore = [...defaultIgnore, ...expandedIgnore, ...standaloneIgnores]
 
 	// Map files need to be included in the debug build. Remove .map ignores when IS_DEBUG_BUILD is set
-	if (process.env.IS_DEBUG_BUILD) {
+	if (IS_DEBUG_BUILD) {
 		allIgnore = allIgnore.filter((pattern) => !pattern.endsWith(".map"))
 		console.log("Debug build: Including .map files in package")
 	}
@@ -167,6 +232,7 @@ function createIsIgnored(standaloneIgnores) {
 
 /* cp -r */
 async function cpr(source, dest) {
+	log_verbose(`Copying ${source} -> ${dest}`)
 	await cp(source, dest, {
 		recursive: true,
 		preserveTimestamps: true,
@@ -175,7 +241,7 @@ async function cpr(source, dest) {
 }
 
 function log_verbose(...args) {
-	if (process.argv.includes("-v") || process.argv.includes("--verbose")) {
+	if (IS_VERBOSE) {
 		console.log(...args)
 	}
 }

scripts/test-standalone-core-api-server.ts

@@ -0,0 +1,135 @@
+#!/usr/bin/env npx tsx
+
+/**
+ * Simple Cline gRPC Server
+ *
+ * This script provides a minimal way to run the Cline core gRPC service
+ * without requiring the full installation, while automatically mocking all external services. Simply run:
+ *
+ *   # One-time setup (generates protobuf files)
+ *	 npm run compile-standalone
+ *   npm run test:sca-server
+ *
+ * The following components are started automatically:
+ *   1. HostBridge test server
+ *   2. ClineApiServerMock (mock implementation of the Cline API)
+ *   3. AuthServiceMock (activated if E2E_TEST="true")
+ *
+ * Environment Variables for Customization:
+ *   PROJECT_ROOT - Override project root directory (default: parent of scripts dir)
+ *   CLINE_DIST_DIR - Override distribution directory (default: PROJECT_ROOT/dist-standalone)
+ *   CLINE_CORE_FILE - Override core file name (default: cline-core.js)
+ *   PROTOBUS_PORT - gRPC server port (default: 26040)
+ *   HOSTBRIDGE_PORT - HostBridge server port (default: 26041)
+ *   WORKSPACE_DIR - Working directory (default: current directory)
+ *   E2E_TEST - Enable E2E test mode (default: true)
+ *   CLINE_ENVIRONMENT - Environment setting (default: local)
+ *
+ * Ideal for local development, testing, or lightweight E2E scenarios.
+ */
+
+import { ChildProcess, spawn } from "child_process"
+import * as fs from "fs"
+import * as path from "path"
+import { ClineApiServerMock } from "../src/test/e2e/fixtures/server/index"
+
+// Configuration
+const PROTOBUS_PORT = process.env.PROTOBUS_PORT || "26040"
+const HOSTBRIDGE_PORT = process.env.HOSTBRIDGE_PORT || "26041"
+const WORKSPACE_DIR = process.env.WORKSPACE_DIR || process.cwd()
+const E2E_TEST = process.env.E2E_TEST || "true"
+const CLINE_ENVIRONMENT = process.env.CLINE_ENVIRONMENT || "local"
+
+// Locate the standalone build directory and core file with flexible path resolution
+const projectRoot = process.env.PROJECT_ROOT || path.resolve(__dirname, "..")
+const distDir = process.env.CLINE_DIST_DIR || path.join(projectRoot, "dist-standalone")
+const clineCoreFile = process.env.CLINE_CORE_FILE || "cline-core.js"
+const coreFile = path.join(distDir, clineCoreFile)
+
+async function main(): Promise<void> {
+	console.log("Starting Simple Cline gRPC Server...")
+	console.log(`Workspace: ${WORKSPACE_DIR}`)
+	console.log(`ProtoBus Port: ${PROTOBUS_PORT}`)
+	console.log(`HostBridge Port: ${HOSTBRIDGE_PORT}`)
+
+	console.log(`Looking for standalone build at: ${coreFile}`)
+
+	if (!fs.existsSync(coreFile)) {
+		console.error(`Standalone build not found at: ${coreFile}`)
+		console.error("Available environment variables for customization:")
+		console.error("  PROJECT_ROOT - Override project root directory")
+		console.error("  CLINE_DIST_DIR - Override distribution directory")
+		console.error("  CLINE_CORE_FILE - Override core file name")
+		console.error("")
+		console.error("To build the standalone version, run: npm run compile-standalone")
+		process.exit(1)
+	}
+
+	try {
+		const apiServer = await ClineApiServerMock.startGlobalServer()
+		console.log("Cline API Server started in-process")
+	} catch (error) {
+		console.error("Failed to start Cline API Server:", error)
+		process.exit(1)
+	}
+
+	// Start hostbridge test server in background.
+	// We run it as a child process to emulate how the extension currently operates
+	console.log("Starting HostBridge test server...")
+	const hostbridge: ChildProcess = spawn("npx", ["tsx", path.join(__dirname, "test-hostbridge-server.ts")], {
+		stdio: "pipe",
+		detached: false,
+	})
+
+	// Start the core service
+	// We run it as a child process to emulate how the extension currently operates
+	console.log("Starting Cline Core Service...")
+	const coreService: ChildProcess = spawn("node", [clineCoreFile], {
+		cwd: distDir,
+		env: {
+			...process.env,
+			NODE_PATH: "./node_modules",
+			DEV_WORKSPACE_FOLDER: WORKSPACE_DIR,
+			PROTOBUS_ADDRESS: `127.0.0.1:${PROTOBUS_PORT}`,
+			HOST_BRIDGE_ADDRESS: `localhost:${HOSTBRIDGE_PORT}`,
+			E2E_TEST: E2E_TEST,
+			CLINE_ENVIRONMENT: CLINE_ENVIRONMENT,
+		},
+		stdio: "inherit",
+	})
+
+	// Handle graceful shutdown
+	const shutdown = async (): Promise<void> => {
+		console.log("\n Shutting down services...")
+		hostbridge.kill()
+		coreService.kill()
+		await ClineApiServerMock.stopGlobalServer()
+		process.exit(0)
+	}
+
+	process.on("SIGINT", shutdown)
+	process.on("SIGTERM", shutdown)
+
+	coreService.on("exit", (code) => {
+		console.log(`Core service exited with code ${code}`)
+		hostbridge.kill()
+		process.exit(code || 0)
+	})
+
+	hostbridge.on("exit", (code) => {
+		console.log(`HostBridge exited with code ${code}`)
+		coreService.kill()
+		process.exit(code || 0)
+	})
+
+	console.log("Cline gRPC Server is running!")
+	console.log(`Connect to: 127.0.0.1:${PROTOBUS_PORT}`)
+	console.log("Press Ctrl+C to stop")
+}
+
+if (require.main === module) {
+	main().catch((error) => {
+		console.error("Failed to start simple Cline server:", error)
+		process.exit(1)
+	})
+}

scripts/validate-scenario.sh

@@ -1,151 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Validate a PR-specific scenario exists in src/test/scenarios
-# Rules:
-#  - example.ts is exempt
-#  - Exactly one scenario must match the current PR number
-#  - All non-exempt scenario files must include a valid "GitHub PR" metadata line
-#
-# Usage: ./scripts/validate-scenario.sh <PR_NUMBER>
-
-PR_NUMBER="${1:-}"
-
-SCENARIOS_DIR="src/test/scenarios"
-EXEMPT_BASENAMES=("example.ts")
-
-red()   { printf "\033[31m%s\033[0m\n" "$*"; }
-green() { printf "\033[32m%s\033[0m\n" "$*"; }
-yellow(){ printf "\033[33m%s\033[0m\n" "$*"; }
-
-is_exempt() {
-  local base="$1"
-  for ex in "${EXEMPT_BASENAMES[@]}"; do
-    if [[ "$base" == "$ex" ]]; then
-      return 0
-    fi
-  done
-  return 1
-}
-
-usage() {
-  echo "Usage: $0 <PR_NUMBER>" >&2
-  exit 2
-}
-
-if [[ -z "$PR_NUMBER" ]]; then
-  red "Error: PR number is required."
-  usage
-fi
-
-if ! [[ "$PR_NUMBER" =~ ^[0-9]+$ ]]; then
-  red "Error: PR number must be numeric. Got: '$PR_NUMBER'"
-  exit 2
-fi
-
-if [[ ! -d "$SCENARIOS_DIR" ]]; then
-  red "Error: Scenarios directory not found: $SCENARIOS_DIR"
-  exit 1
-fi
-
-declare -a ALL_FILES=()
-declare -a MISSING_METADATA=()
-declare -a MALFORMED_METADATA=()
-declare -a FOUND_FILES=()
-declare -a FOUND_PRS=()
-
-# Find top-level .ts files in scenarios dir
-while IFS= read -r -d '' file; do
-  ALL_FILES+=("$file")
-done < <(find "$SCENARIOS_DIR" -maxdepth 1 -type f -name "*.ts" -print0 | sort -z)
-
-if [[ ${#ALL_FILES[@]} -eq 0 ]]; then
-  red "Error: No scenario files found in $SCENARIOS_DIR"
-  exit 1
-fi
-
-for file in "${ALL_FILES[@]}"; do
-  base="$(basename "$file")"
-  if is_exempt "$base"; then
-    continue
-  fi
-
-  # Extract metadata line, pattern: // GitHub PR - 123
-  meta_line="$(grep -E -m1 '^[[:space:]]*//[[:space:]]*GitHub[[:space:]]+PR[[:space:]]*-[[:space:]]*[0-9]+[[:space:]]*$' "$file" || true)"
-
-  if [[ -z "$meta_line" ]]; then
-    MISSING_METADATA+=("$file")
-    continue
-  fi
-
-  pr_in_file="$(sed -E 's@.*GitHub[[:space:]]+PR[[:space:]]*-[[:space:]]*([0-9]+).*@\1@' <<< "$meta_line" | tr -d '[:space:]')"
-
-  if ! [[ "$pr_in_file" =~ ^[0-9]+$ ]]; then
-    MALFORMED_METADATA+=("$file")
-    continue
-  fi
-
-  FOUND_FILES+=("$file")
-  FOUND_PRS+=("$pr_in_file")
-done
-
-# Fail if any non-exempt file is missing metadata
-if [[ ${#MISSING_METADATA[@]} -gt 0 ]]; then
-  red "Error: The following scenario files are missing the required metadata line '// GitHub PR - &lt;number&gt;':"
-  for f in "${MISSING_METADATA[@]}"; do
-    echo " - $f"
-  done
-  echo
-  echo "Please add a metadata line like:"
-  echo "  // GitHub PR - $PR_NUMBER"
-  exit 1
-fi
-
-# Fail if any metadata is malformed
-if [[ ${#MALFORMED_METADATA[@]} -gt 0 ]]; then
-  red "Error: The following scenario files have a malformed 'GitHub PR' metadata line:"
-  for f in "${MALFORMED_METADATA[@]}"; do
-    echo " - $f"
-  done
-  echo
-  echo "Expected format:"
-  echo "  // GitHub PR - $PR_NUMBER"
-  exit 1
-fi
-
-# Count matches for this PR
-matches=0
-declare -a MATCHED_FILES=()
-for i in "${!FOUND_FILES[@]}"; do
-  if [[ "${FOUND_PRS[$i]}" == "$PR_NUMBER" ]]; then
-    matches=$((matches + 1))
-    MATCHED_FILES+=("${FOUND_FILES[$i]}")
-  fi
-done
-
-if [[ $matches -eq 0 ]]; then
-  red "Error: No scenario file found for PR #$PR_NUMBER."
-  echo "Scenarios with declared PRs:"
-  if [[ ${#FOUND_FILES[@]} -eq 0 ]]; then
-    echo "  (none)"
-  else
-    for i in "${!FOUND_FILES[@]}"; do
-      echo " - ${FOUND_FILES[$i]}   (PR: ${FOUND_PRS[$i]})"
-    done
-  fi
-  echo
-  echo "Please add a scenario in $SCENARIOS_DIR with a metadata line:"
-  echo "  // GitHub PR - $PR_NUMBER"
-  exit 1
-fi
-
-if [[ $matches -gt 1 ]]; then
-  red "Error: Multiple scenario files found for PR #$PR_NUMBER (exactly one required):"
-  for f in "${MATCHED_FILES[@]}"; do
-    echo " - $f"
-  done
-  exit 1
-fi
-
-green "Success: Exactly one scenario found for PR #$PR_NUMBER:"
-echo " - ${MATCHED_FILES[0]}"

src/api/providers/dify.ts

@@ -0,0 +1,288 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import { ApiHandlerOptions, ModelInfo } from "@shared/api"
+import { ApiHandler } from "../../core/api/index"
+import { ApiStream } from "../../core/api/transform/stream"
+
+export class DifyHandler implements ApiHandler {
+	private options: ApiHandlerOptions
+	private baseUrl: string
+	private apiKey: string
+	private conversationId: string | null = null
+
+	constructor(options: ApiHandlerOptions) {
+		this.options = options
+		this.apiKey = options.difyApiKey || ""
+		this.baseUrl = options.difyBaseUrl || ""
+
+		console.log("[DIFY DEBUG] Constructor called with:", {
+			hasApiKey: !!this.apiKey,
+			baseUrl: this.baseUrl,
+		})
+
+		if (!this.apiKey) {
+			throw new Error("Dify API key is required")
+		}
+		if (!this.baseUrl) {
+			throw new Error("Dify base URL is required")
+		}
+	}
+
+	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		console.log("[DIFY DEBUG] createMessage called with:", {
+			systemPromptLength: systemPrompt?.length || 0,
+			messagesCount: messages?.length || 0,
+		})
+
+		// Convert messages to Dify format
+		const query = this.convertMessagesToQuery(systemPrompt, messages)
+		const requestBody = {
+			inputs: {},
+			query: query,
+			response_mode: "streaming",
+			conversation_id: this.conversationId || "",
+			user: "cline-user", // A unique user identifier
+			files: [],
+		}
+
+		const fullUrl = `${this.baseUrl}/chat-messages`
+		console.log("[DIFY DEBUG] Making request to:", fullUrl)
+		console.log("[DIFY DEBUG] Request body:", JSON.stringify(requestBody, null, 2))
+		console.log("[DIFY DEBUG] Current process environment variables (for proxy debugging):", process.env)
+
+		let response: Response
+		try {
+			response = await fetch(fullUrl, {
+				method: "POST",
+				headers: {
+					Authorization: `Bearer ${this.apiKey}`,
+					"Content-Type": "application/json",
+				},
+				body: JSON.stringify(requestBody),
+			})
+		} catch (error: any) {
+			console.error("[DIFY DEBUG] Network error during fetch:", error)
+			// Log more detailed error information if available (e.g., from undici)
+			const cause = error.cause ? ` | Cause: ${error.cause}` : ""
+			throw new Error(`Dify API network error: ${error.message}${cause}`)
+		}
+
+		console.log("[DIFY DEBUG] Response status:", response.status)
+		const headersObj: Record<string, string> = {}
+		response.headers.forEach((value, key) => {
+			headersObj[key] = value
+		})
+		console.log("[DIFY DEBUG] Response headers:", headersObj)
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			console.error("[DIFY DEBUG] Error response:", errorText)
+			throw new Error(`Dify API error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+
+		if (!response.body) {
+			throw new Error("No response body from Dify API")
+		}
+
+		const reader = response.body.getReader()
+		const decoder = new TextDecoder()
+		let buffer = ""
+		let fullText = ""
+
+		console.log("[DIFY DEBUG] Starting to read streaming response...")
+
+		try {
+			while (true) {
+				const { done, value } = await reader.read()
+				if (done) {
+					console.log("[DIFY DEBUG] Stream ended naturally")
+					break
+				}
+
+				const chunk = decoder.decode(value, { stream: true })
+				console.log("[DIFY DEBUG] Raw chunk received:", JSON.stringify(chunk))
+
+				buffer += chunk
+				const lines = buffer.split("\n")
+
+				// Keep the last incomplete line in the buffer
+				buffer = lines.pop() || ""
+
+				for (const line of lines) {
+					console.log("[DIFY DEBUG] Processing line:", JSON.stringify(line))
+
+					if (line.startsWith("data: ")) {
+						const data = line.slice(6).trim()
+						console.log("[DIFY DEBUG] Extracted data:", JSON.stringify(data))
+
+						if (data === "[DONE]") {
+							console.log("[DIFY DEBUG] Received [DONE] signal")
+							return // Explicitly return on [DONE]
+						}
+
+						if (data === "") {
+							console.log("[DIFY DEBUG] Empty data line, skipping")
+							continue
+						}
+
+						try {
+							const parsed = JSON.parse(data)
+							console.log("[DIFY DEBUG] Parsed JSON:", parsed)
+
+							// Capture conversation_id as soon as it's available
+							if (parsed.conversation_id && !this.conversationId) {
+								this.conversationId = parsed.conversation_id
+								console.log("[DIFY DEBUG] Captured conversation_id:", this.conversationId)
+							}
+
+							// Handle different Dify event types based on actual Dify API
+							if (parsed.event === "message") {
+								console.log("[DIFY DEBUG] Message event, answer:", parsed.answer)
+								// Dify sends the full text in each "answer" chunk, so we replace.
+								if (typeof parsed.answer === "string") {
+									fullText = parsed.answer
+									console.log("[DIFY DEBUG] Updated fullText length:", fullText.length)
+									yield {
+										type: "text",
+										text: fullText,
+									}
+								}
+							} else if (parsed.event === "message_replace") {
+								console.log("[DIFY DEBUG] Replace message event:", parsed)
+								if (parsed.answer) {
+									fullText = parsed.answer // Replace instead of append
+									console.log("[DIFY DEBUG] Replaced fullText length:", fullText.length)
+									yield {
+										type: "text",
+										text: fullText,
+									}
+								}
+							} else if (parsed.event === "message_end") {
+								console.log("[DIFY DEBUG] Message end event", parsed)
+								// Message completed. Yield final text if we have any.
+								if (fullText) {
+									yield {
+										type: "text",
+										text: fullText,
+									}
+								}
+								// Yield usage data if available
+								if (parsed.usage) {
+									yield {
+										type: "usage",
+										inputTokens: parsed.usage.prompt_tokens || 0,
+										outputTokens: parsed.usage.completion_tokens || parsed.usage.total_tokens || 0,
+										totalCost: parsed.usage.total_price || 0,
+									}
+								}
+								return // End of stream
+							} else if (parsed.event === "error") {
+								console.error("[DIFY DEBUG] Error event:", parsed)
+								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
+							} else if (parsed.event === "workflow_started" || parsed.event === "workflow_finished") {
+								console.log("[DIFY DEBUG] Workflow event:", parsed.event)
+								// These are informational events, continue processing
+							} else if (parsed.event === "node_started" || parsed.event === "node_finished") {
+								console.log("[DIFY DEBUG] Node event:", parsed.event, parsed.data)
+								// These are informational events, continue processing
+							} else if (parsed.event === "ping") {
+								console.log("[DIFY DEBUG] Ping event received, keeping connection alive.")
+								// Ping event, do nothing
+							} else {
+								console.log("[DIFY DEBUG] Unknown event type:", parsed.event, "Full object:", parsed)
+								// Try to extract text from other possible fields
+								if (parsed.text) {
+									fullText += parsed.text
+									yield {
+										type: "text",
+										text: fullText,
+									}
+								} else if (parsed.content) {
+									fullText += parsed.content
+									yield {
+										type: "text",
+										text: fullText,
+									}
+								}
+							}
+						} catch (e) {
+							console.warn("[DIFY DEBUG] Failed to parse JSON:", data, "Error:", e)
+						}
+					} else if (line.trim() !== "") {
+						console.log(
+							"[DIFY DEBUG] Non-data line (not starting with 'data:'), trying to parse as direct JSON:",
+							JSON.stringify(line),
+						)
+						// Try to parse as direct JSON (fallback for non-SSE responses, though Dify uses SSE)
+						try {
+							const parsed = JSON.parse(line.trim())
+							console.log("[DIFY DEBUG] Parsed direct JSON:", parsed)
+
+							// Handle the same event types as above
+							if (parsed.event === "message" && parsed.answer) {
+								fullText += parsed.answer
+								yield {
+									type: "text",
+									text: fullText,
+								}
+							} else if (parsed.event === "message_end") {
+								if (fullText) {
+									yield {
+										type: "text",
+										text: fullText,
+									}
+								}
+								return
+							} else if (parsed.event === "error") {
+								console.error("[DIFY DEBUG] Direct JSON Error event:", parsed)
+								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
+							}
+						} catch (e) {
+							// Not JSON, continue
+							console.log("[DIFY DEBUG] Line is not direct JSON, continuing")
+						}
+					}
+				}
+			}
+		} finally {
+			reader.releaseLock()
+			console.log("[DIFY DEBUG] Stream reader released")
+		}
+	}
+
+	private convertMessagesToQuery(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): string {
+		// Dify's context is managed by `conversation_id`. The `query` should be the last user message.
+		// The system prompt is typically configured in the Dify App itself.
+		const lastUserMessage = messages.filter((m) => m.role === "user").pop()
+
+		if (!lastUserMessage) {
+			return "" // Should not happen in normal flow
+		}
+
+		const userQuery = Array.isArray(lastUserMessage.content)
+			? lastUserMessage.content.map((c) => ("text" in c ? c.text : "")).join("\n")
+			: (lastUserMessage.content as string)
+
+		// Only prepend the system prompt if it's the very first message of a new conversation.
+		if (!this.conversationId && systemPrompt) {
+			console.log("[DIFY DEBUG] Prepending system prompt for new conversation.")
+			return `${systemPrompt}\n\n---\n\n${userQuery}`
+		}
+
+		return userQuery
+	}
+
+	getModel(): { id: string; info: ModelInfo } {
+		return {
+			id: "dify-workflow",
+			info: {
+				maxTokens: 8192,
+				contextWindow: 128000,
+				supportsImages: true,
+				supportsPromptCache: false,
+				inputPrice: 0,
+				outputPrice: 0,
+				description: "Dify workflow - model selection is configured in your Dify application",
+			},
+		}
+	}
+}

src/common.ts

@@ -1,19 +1,22 @@
 import * as vscode from "vscode"
 import {
 	migrateCustomInstructionsToGlobalRules,
+	migrateTaskHistoryToFile,
 	migrateWelcomeViewCompleted,
 	migrateWorkspaceToGlobalStorage,
 } from "./core/storage/state-migrations"
 import { WebviewProvider } from "./core/webview"
 import { Logger } from "./services/logging/Logger"
-import { PostHogClientProvider } from "./services/posthog/PostHogClientProvider"
-import { EmptyRequest } from "./shared/proto/cline/common"
 import { WebviewProviderType } from "./shared/webview/types"
 import "./utils/path" // necessary to have access to String.prototype.toPosix
 
 import { HostProvider } from "@/hosts/host-provider"
 import { FileContextTracker } from "./core/context/context-tracking/FileContextTracker"
-import { telemetryService } from "./services/posthog/PostHogClientProvider"
+import { ErrorService } from "./services/error"
+import { featureFlagsService } from "./services/feature-flags"
+import { initializeDistinctId } from "./services/logging/distinctId"
+import { PostHogClientProvider } from "./services/posthog/PostHogClientProvider"
+import { telemetryService } from "./services/telemetry"
 import { ShowMessageType } from "./shared/proto/host/window"
 import { getLatestAnnouncementId } from "./utils/announcements"
 /**
@@ -23,18 +26,14 @@ import { getLatestAnnouncementId } from "./utils/announcements"
  * @returns The webview provider
  */
 export async function initialize(context: vscode.ExtensionContext): Promise<WebviewProvider> {
+	// Set the distinct ID for logging and telemetry
+	await initializeDistinctId(context)
+
 	// Initialize PostHog client provider
-	let distinctId = context.globalState.get<string>("cline.distinctId")
-	if (!distinctId) {
-		try {
-			const response = await HostProvider.env.getMachineId(EmptyRequest.create({}))
-			distinctId = response.value
-		} catch (e) {
-			Logger.warn(`Failed to get machine ID: ${e instanceof Error ? e.message : String(e)}`)
-			// PostHogProvider will fall back to uuid
-		}
-	}
-	PostHogClientProvider.getInstance(distinctId)
+	PostHogClientProvider.getInstance()
+
+	// Setup the ErrorService
+	await ErrorService.initialize()
 
 	// Migrate custom instructions to global Cline rules (one-time cleanup)
 	await migrateCustomInstructionsToGlobalRules(context)
@@ -45,6 +44,9 @@ export async function initialize(context: vscode.ExtensionContext): Promise<Webv
 	// Migrate workspace storage values back to global storage (reverting previous migration)
 	await migrateWorkspaceToGlobalStorage(context)
 
+	// Ensure taskHistory.json exists and migrate legacy state (runs once)
+	await migrateTaskHistoryToFile(context)
+
 	// Clean up orphaned file context warnings (startup cleanup)
 	await FileContextTracker.cleanupOrphanedWarnings(context)
 
@@ -75,7 +77,7 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
 				const message = previousVersion
 					? `Cline has been updated to v${currentVersion}`
 					: `Welcome to Cline v${currentVersion}`
-				await vscode.commands.executeCommand("claude-dev.SidebarProvider.focus")
+				await HostProvider.workspace.openClineSidebarPanel({})
 				await new Promise((resolve) => setTimeout(resolve, 200))
 				HostProvider.window.showMessage({
 					type: ShowMessageType.INFORMATION,
@@ -96,7 +98,9 @@ async function showVersionUpdateAnnouncement(context: vscode.ExtensionContext) {
  */
 export async function tearDown(): Promise<void> {
 	PostHogClientProvider.getInstance().dispose()
-
+	telemetryService.dispose()
+	ErrorService.get().dispose()
+	featureFlagsService.dispose()
 	// Dispose all webview instances
 	await WebviewProvider.disposeAllInstances()
 }

src/core/api/index.ts

@@ -9,6 +9,7 @@ import { CerebrasHandler } from "./providers/cerebras"
 import { ClaudeCodeHandler } from "./providers/claude-code"
 import { ClineHandler } from "./providers/cline"
 import { DeepSeekHandler } from "./providers/deepseek"
+import { DifyHandler } from "./providers/dify"
 import { DoubaoHandler } from "./providers/doubao"
 import { FireworksHandler } from "./providers/fireworks"
 import { GeminiHandler } from "./providers/gemini"
@@ -25,6 +26,7 @@ import { OpenAiHandler } from "./providers/openai"
 import { OpenAiNativeHandler } from "./providers/openai-native"
 import { OpenRouterHandler } from "./providers/openrouter"
 import { QwenHandler } from "./providers/qwen"
+import { QwenCodeHandler } from "./providers/qwen-code"
 import { RequestyHandler } from "./providers/requesty"
 import { SambanovaHandler } from "./providers/sambanova"
 import { SapAiCoreHandler } from "./providers/sapaicore"
@@ -36,6 +38,10 @@ import { XAIHandler } from "./providers/xai"
 import { ZAiHandler } from "./providers/zai"
 import { ApiStream, ApiStreamUsageChunk } from "./transform/stream"
 
+export type CommonApiHandlerOptions = {
+	onRetryAttempt?: ApiConfiguration["onRetryAttempt"]
+}
+
 export interface ApiHandler {
 	createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream
 	getModel(): ApiHandlerModel
@@ -48,9 +54,9 @@ export interface ApiHandlerModel {
 }
 
 export interface ApiProviderInfo {
-	modelId: string
 	providerId: string
-	customPrompt?: string
+	model: ApiHandlerModel
+	customPrompt?: string // "compact"
 }
 
 export interface SingleCompletionHandler {
@@ -65,6 +71,7 @@ function createHandlerForProvider(
 	switch (apiProvider) {
 		case "anthropic":
 			return new AnthropicHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				apiKey: options.apiKey,
 				anthropicBaseUrl: options.anthropicBaseUrl,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
@@ -73,6 +80,7 @@ function createHandlerForProvider(
 			})
 		case "openrouter":
 			return new OpenRouterHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				openRouterApiKey: options.openRouterApiKey,
 				openRouterModelId: mode === "plan" ? options.planModeOpenRouterModelId : options.actModeOpenRouterModelId,
 				openRouterModelInfo: mode === "plan" ? options.planModeOpenRouterModelInfo : options.actModeOpenRouterModelInfo,
@@ -83,6 +91,7 @@ function createHandlerForProvider(
 			})
 		case "bedrock":
 			return new AwsBedrockHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 				awsAccessKey: options.awsAccessKey,
 				awsSecretKey: options.awsSecretKey,
@@ -104,6 +113,7 @@ function createHandlerForProvider(
 			})
 		case "vertex":
 			return new VertexHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				vertexProjectId: options.vertexProjectId,
 				vertexRegion: options.vertexRegion,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
@@ -115,6 +125,7 @@ function createHandlerForProvider(
 			})
 		case "openai":
 			return new OpenAiHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				openAiApiKey: options.openAiApiKey,
 				openAiBaseUrl: options.openAiBaseUrl,
 				azureApiVersion: options.azureApiVersion,
@@ -125,6 +136,7 @@ function createHandlerForProvider(
 			})
 		case "ollama":
 			return new OllamaHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				ollamaBaseUrl: options.ollamaBaseUrl,
 				ollamaApiKey: options.ollamaApiKey,
 				ollamaModelId: mode === "plan" ? options.planModeOllamaModelId : options.actModeOllamaModelId,
@@ -133,12 +145,14 @@ function createHandlerForProvider(
 			})
 		case "lmstudio":
 			return new LmStudioHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				lmStudioBaseUrl: options.lmStudioBaseUrl,
 				lmStudioModelId: mode === "plan" ? options.planModeLmStudioModelId : options.actModeLmStudioModelId,
 				lmStudioMaxTokens: options.lmStudioMaxTokens,
 			})
 		case "gemini":
 			return new GeminiHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				vertexProjectId: options.vertexProjectId,
 				vertexRegion: options.vertexRegion,
 				geminiApiKey: options.geminiApiKey,
@@ -150,17 +164,20 @@ function createHandlerForProvider(
 			})
 		case "openai-native":
 			return new OpenAiNativeHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				openAiNativeApiKey: options.openAiNativeApiKey,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "deepseek":
 			return new DeepSeekHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				deepSeekApiKey: options.deepSeekApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "requesty":
 			return new RequestyHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				requestyBaseUrl: options.requestyBaseUrl,
 				requestyApiKey: options.requestyApiKey,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
@@ -171,16 +188,19 @@ function createHandlerForProvider(
 			})
 		case "fireworks":
 			return new FireworksHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				fireworksApiKey: options.fireworksApiKey,
 				fireworksModelId: mode === "plan" ? options.planModeFireworksModelId : options.actModeFireworksModelId,
 			})
 		case "together":
 			return new TogetherHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				togetherApiKey: options.togetherApiKey,
 				togetherModelId: mode === "plan" ? options.planModeTogetherModelId : options.actModeTogetherModelId,
 			})
 		case "qwen":
 			return new QwenHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				qwenApiKey: options.qwenApiKey,
 				qwenApiLine:
 					options.qwenApiLine === QwenApiRegions.INTERNATIONAL ? QwenApiRegions.INTERNATIONAL : QwenApiRegions.CHINA,
@@ -188,23 +208,33 @@ function createHandlerForProvider(
 				thinkingBudgetTokens:
 					mode === "plan" ? options.planModeThinkingBudgetTokens : options.actModeThinkingBudgetTokens,
 			})
+		case "qwen-code":
+			return new QwenCodeHandler({
+				onRetryAttempt: options.onRetryAttempt,
+				qwenCodeOauthPath: options.qwenCodeOauthPath,
+				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
+			})
 		case "doubao":
 			return new DoubaoHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				doubaoApiKey: options.doubaoApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "mistral":
 			return new MistralHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				mistralApiKey: options.mistralApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "vscode-lm":
 			return new VsCodeLmHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				vsCodeLmModelSelector:
 					mode === "plan" ? options.planModeVsCodeLmModelSelector : options.actModeVsCodeLmModelSelector,
 			})
 		case "cline":
 			return new ClineHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				clineAccountId: options.clineAccountId,
 				ulid: options.ulid,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
@@ -216,6 +246,7 @@ function createHandlerForProvider(
 			})
 		case "litellm":
 			return new LiteLlmHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				liteLlmApiKey: options.liteLlmApiKey,
 				liteLlmBaseUrl: options.liteLlmBaseUrl,
 				liteLlmModelId: mode === "plan" ? options.planModeLiteLlmModelId : options.actModeLiteLlmModelId,
@@ -227,12 +258,14 @@ function createHandlerForProvider(
 			})
 		case "moonshot":
 			return new MoonshotHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				moonshotApiKey: options.moonshotApiKey,
 				moonshotApiLine: options.moonshotApiLine,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "huggingface":
 			return new HuggingFaceHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				huggingFaceApiKey: options.huggingFaceApiKey,
 				huggingFaceModelId: mode === "plan" ? options.planModeHuggingFaceModelId : options.actModeHuggingFaceModelId,
 				huggingFaceModelInfo:
@@ -240,33 +273,39 @@ function createHandlerForProvider(
 			})
 		case "nebius":
 			return new NebiusHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				nebiusApiKey: options.nebiusApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "asksage":
 			return new AskSageHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				asksageApiKey: options.asksageApiKey,
 				asksageApiUrl: options.asksageApiUrl,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "xai":
 			return new XAIHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				xaiApiKey: options.xaiApiKey,
 				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "sambanova":
 			return new SambanovaHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				sambanovaApiKey: options.sambanovaApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "cerebras":
 			return new CerebrasHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				cerebrasApiKey: options.cerebrasApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		case "groq":
 			return new GroqHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				groqApiKey: options.groqApiKey,
 				groqModelId: mode === "plan" ? options.planModeGroqModelId : options.actModeGroqModelId,
 				groqModelInfo: mode === "plan" ? options.planModeGroqModelInfo : options.actModeGroqModelInfo,
@@ -274,6 +313,7 @@ function createHandlerForProvider(
 			})
 		case "baseten":
 			return new BasetenHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				basetenApiKey: options.basetenApiKey,
 				basetenModelId: mode === "plan" ? options.planModeBasetenModelId : options.actModeBasetenModelId,
 				basetenModelInfo: mode === "plan" ? options.planModeBasetenModelInfo : options.actModeBasetenModelInfo,
@@ -281,6 +321,7 @@ function createHandlerForProvider(
 			})
 		case "sapaicore":
 			return new SapAiCoreHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				sapAiCoreClientId: options.sapAiCoreClientId,
 				sapAiCoreClientSecret: options.sapAiCoreClientSecret,
 				sapAiCoreTokenUrl: options.sapAiCoreTokenUrl,
@@ -289,9 +330,13 @@ function createHandlerForProvider(
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 				thinkingBudgetTokens:
 					mode === "plan" ? options.planModeThinkingBudgetTokens : options.actModeThinkingBudgetTokens,
+				reasoningEffort: mode === "plan" ? options.planModeReasoningEffort : options.actModeReasoningEffort,
+				deploymentId: mode === "plan" ? options.planModeSapAiCoreDeploymentId : options.actModeSapAiCoreDeploymentId,
+				sapAiCoreUseOrchestrationMode: options.sapAiCoreUseOrchestrationMode,
 			})
 		case "claude-code":
 			return new ClaudeCodeHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				claudeCodePath: options.claudeCodePath,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 				thinkingBudgetTokens:
@@ -299,14 +344,25 @@ function createHandlerForProvider(
 			})
 		case "huawei-cloud-maas":
 			return new HuaweiCloudMaaSHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				huaweiCloudMaasApiKey: options.huaweiCloudMaasApiKey,
 				huaweiCloudMaasModelId:
 					mode === "plan" ? options.planModeHuaweiCloudMaasModelId : options.actModeHuaweiCloudMaasModelId,
 				huaweiCloudMaasModelInfo:
 					mode === "plan" ? options.planModeHuaweiCloudMaasModelInfo : options.actModeHuaweiCloudMaasModelInfo,
 			})
+		case "dify": // Add Dify.ai handler
+			console.log("[DIFY DEBUG] Instantiating DifyHandler with options:", {
+				difyApiKeyPresent: !!options.difyApiKey,
+				difyBaseUrl: options.difyBaseUrl,
+			})
+			return new DifyHandler({
+				difyApiKey: options.difyApiKey,
+				difyBaseUrl: options.difyBaseUrl,
+			})
 		case "vercel-ai-gateway":
 			return new VercelAIGatewayHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				vercelAiGatewayApiKey: options.vercelAiGatewayApiKey,
 				vercelAiGatewayModelId:
 					mode === "plan" ? options.planModeVercelAiGatewayModelId : options.actModeVercelAiGatewayModelId,
@@ -315,12 +371,14 @@ function createHandlerForProvider(
 			})
 		case "zai":
 			return new ZAiHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				zaiApiLine: options.zaiApiLine,
 				zaiApiKey: options.zaiApiKey,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,
 			})
 		default:
 			return new AnthropicHandler({
+				onRetryAttempt: options.onRetryAttempt,
 				apiKey: options.apiKey,
 				anthropicBaseUrl: options.anthropicBaseUrl,
 				apiModelId: mode === "plan" ? options.planModeApiModelId : options.actModeApiModelId,

src/core/api/providers/__tests__/claude-code.test.ts

@@ -0,0 +1,248 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import { afterEach, beforeEach, describe, it } from "mocha"
+import sinon from "sinon"
+import "should"
+import { ClaudeCodeHandler } from "@core/api/providers/claude-code"
+
+describe("ClaudeCodeHandler", () => {
+	let handler: ClaudeCodeHandler
+	let sandbox: sinon.SinonSandbox
+
+	beforeEach(() => {
+		sandbox = sinon.createSandbox()
+		handler = new ClaudeCodeHandler({
+			claudeCodePath: "/mock/path",
+			apiModelId: "claude-3-5-sonnet-20241022",
+		})
+	})
+
+	afterEach(() => {
+		sandbox.restore()
+	})
+
+	describe("token counting", () => {
+		it("should correctly handle token usage from assistant messages", async () => {
+			// The 'input_tokens' field represents the TOTAL number of input tokens used.
+			// See https://docs.anthropic.com/en/api/messages#usage-object
+
+			// Mock the runClaudeCode function
+			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
+			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
+
+			// Create a proper async generator mock for the Claude Code response
+			async function* mockGenerator() {
+				// First yield the system init
+				yield {
+					type: "system",
+					subtype: "init",
+					apiKeySource: "api",
+				}
+
+				// Yield assistant message with usage data
+				// Example: If base input is 70 tokens, cache read is 20, and cache creation is 10,
+				// then input_tokens from Anthropic API will be 100 (70 + 20 + 10)
+				yield {
+					type: "assistant",
+					message: {
+						content: [
+							{
+								type: "text",
+								text: "Test response",
+							},
+						],
+						usage: {
+							input_tokens: 100, // Total including cache (per Anthropic docs)
+							output_tokens: 50,
+							cache_read_input_tokens: 20, // Already included in input_tokens
+							cache_creation_input_tokens: 10, // Already included in input_tokens
+						},
+						stop_reason: "end_turn",
+					},
+				}
+
+				// Yield result with cost
+				yield {
+					type: "result",
+					result: {},
+					total_cost_usd: 0.005,
+				}
+			}
+
+			runClaudeCodeStub.returns(mockGenerator() as any)
+
+			const systemPrompt = "You are a helpful assistant."
+			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
+
+			const usageData: any[] = []
+
+			// Collect the results
+			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
+				if (chunk.type === "usage") {
+					usageData.push({
+						inputTokens: chunk.inputTokens,
+						outputTokens: chunk.outputTokens,
+						cacheReadTokens: chunk.cacheReadTokens,
+						cacheWriteTokens: chunk.cacheWriteTokens,
+						totalCost: chunk.totalCost,
+					})
+				}
+			}
+
+			// Verify token counting follows Anthropic API specification
+			usageData.should.have.length(1)
+			usageData[0].should.deepEqual({
+				inputTokens: 100, // Total including cache tokens (per Anthropic API docs)
+				outputTokens: 50,
+				cacheReadTokens: 20, // Tracked separately for reporting
+				cacheWriteTokens: 10, // Tracked separately for reporting
+				totalCost: 0.005,
+			})
+
+			// CRITICAL ASSERTION: Verify that input_tokens is NOT inflated by re-adding cache tokens
+			// The bug would have caused inputTokens to be incorrectly calculated as 130 (100 + 20 + 10)
+			// The fix ensures it remains 100, as per Anthropic's specification
+			usageData[0].inputTokens.should.equal(100) // Correct: matches API response
+			usageData[0].inputTokens.should.not.equal(130) // Would be wrong: double-counting cache tokens
+		})
+
+		it("should handle missing usage fields with nullish coalescing", async () => {
+			// Mock the runClaudeCode function
+			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
+			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
+
+			// Create a proper async generator mock with missing/undefined usage fields
+			async function* mockGenerator() {
+				yield {
+					type: "assistant",
+					message: {
+						content: [
+							{
+								type: "text",
+								text: "Test response",
+							},
+						],
+						usage: {
+							input_tokens: 100,
+							output_tokens: 50,
+							// cache fields are undefined/missing
+						},
+						stop_reason: "end_turn",
+					},
+				}
+
+				yield {
+					type: "result",
+					result: {},
+					total_cost_usd: 0.005,
+				}
+			}
+
+			runClaudeCodeStub.returns(mockGenerator() as any)
+
+			const systemPrompt = "You are a helpful assistant."
+			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
+
+			const usageData: any[] = []
+
+			// Collect the results
+			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
+				if (chunk.type === "usage") {
+					usageData.push({
+						inputTokens: chunk.inputTokens,
+						outputTokens: chunk.outputTokens,
+						cacheReadTokens: chunk.cacheReadTokens,
+						cacheWriteTokens: chunk.cacheWriteTokens,
+					})
+				}
+			}
+
+			// Verify that undefined cache tokens default to 0
+			usageData.should.have.length(1)
+			usageData[0].should.deepEqual({
+				inputTokens: 100,
+				outputTokens: 50,
+				cacheReadTokens: 0, // Should default to 0
+				cacheWriteTokens: 0, // Should default to 0
+			})
+		})
+
+		it("should handle completely missing usage object", async () => {
+			// Mock the runClaudeCode function
+			const runClaudeCodeModule = await import("@/integrations/claude-code/run")
+			const runClaudeCodeStub = sandbox.stub(runClaudeCodeModule, "runClaudeCode")
+
+			// Create a proper async generator mock with missing usage object
+			async function* mockGenerator() {
+				yield {
+					type: "assistant",
+					message: {
+						content: [
+							{
+								type: "text",
+								text: "Test response",
+							},
+						],
+						// usage is undefined
+						usage: undefined,
+						stop_reason: "end_turn",
+					},
+				}
+
+				// Need to yield a result chunk to trigger usage data emission
+				yield {
+					type: "result",
+					result: {},
+					total_cost_usd: 0,
+				}
+			}
+
+			runClaudeCodeStub.returns(mockGenerator() as any)
+
+			const systemPrompt = "You are a helpful assistant."
+			const messages: Anthropic.Messages.MessageParam[] = [{ role: "user", content: "Hello" }]
+
+			const usageData: any[] = []
+
+			// Collect the results
+			for await (const chunk of handler.createMessage(systemPrompt, messages)) {
+				if (chunk.type === "usage") {
+					usageData.push({
+						inputTokens: chunk.inputTokens,
+						outputTokens: chunk.outputTokens,
+						cacheReadTokens: chunk.cacheReadTokens,
+						cacheWriteTokens: chunk.cacheWriteTokens,
+					})
+				}
+			}
+
+			// All token counts should default to 0 when usage is undefined
+			usageData.should.have.length(1)
+			usageData[0].should.deepEqual({
+				inputTokens: 0,
+				outputTokens: 0,
+				cacheReadTokens: 0,
+				cacheWriteTokens: 0,
+			})
+		})
+	})
+
+	describe("getModel", () => {
+		it("should return the correct model when specified", () => {
+			const handler = new ClaudeCodeHandler({
+				apiModelId: "claude-3-5-sonnet-20241022",
+			})
+
+			const model = handler.getModel()
+			model.id.should.equal("claude-3-5-sonnet-20241022")
+		})
+
+		it("should return default model when not specified", () => {
+			const handler = new ClaudeCodeHandler({})
+
+			const model = handler.getModel()
+			// The default model should be set
+			model.id.should.be.type("string")
+			model.info.should.be.type("object")
+		})
+	})
+})

src/core/api/providers/__tests__/litellm.test.ts

@@ -0,0 +1,243 @@
+import Anthropic from "@anthropic-ai/sdk"
+import { LiteLlmHandler, type LiteLlmModelInfoResponse } from "@core/api/providers/litellm"
+import { convertToOpenAiMessages } from "@core/api/transform/openai-format"
+import { expect } from "chai"
+import sinon from "sinon"
+
+const fakeClient = {
+	chat: {
+		completions: {
+			create: sinon.stub(),
+		},
+	},
+	baseURL: "fake",
+}
+
+describe("LiteLlmHandler", () => {
+	const originalFetch = global.fetch
+	const mockFetch = sinon.stub()
+
+	const mockModelFetch = (modelInfo: LiteLlmModelInfoResponse["data"][number]) => {
+		mockFetch.resolves({
+			ok: true,
+			json: () =>
+				Promise.resolve({
+					data: [modelInfo],
+				}),
+		})
+	}
+
+	let handler: LiteLlmHandler
+
+	const mockHandlerChat = () => {
+		sinon.stub(handler, "ensureClient" as any).returns(fakeClient)
+	}
+
+	const initializeHandler = (model: string) => {
+		handler = new LiteLlmHandler({
+			liteLlmApiKey: "test-api-key",
+			liteLlmBaseUrl: "http://localhost:4000",
+			liteLlmUsePromptCache: true,
+			liteLlmModelId: model,
+		})
+
+		mockHandlerChat()
+	}
+
+	beforeEach(() => {
+		global.fetch = mockFetch
+
+		// Configure the stub to return a stream that closes immediately with usage data
+		fakeClient.chat.completions.create.resolves(
+			createAsyncIterable([
+				{
+					choices: [{ delta: { content: "test response" } }],
+				},
+				{
+					choices: [{}],
+					usage: {
+						prompt_tokens: 100,
+						completion_tokens: 50,
+						cache_creation_input_tokens: 20,
+						cache_read_input_tokens: 10,
+					},
+				},
+			]),
+		)
+	})
+
+	afterEach(() => {
+		sinon.reset()
+
+		global.fetch = originalFetch
+	})
+
+	const createAsyncIterable = (data: any[] = []) => {
+		return {
+			[Symbol.asyncIterator]: async function* () {
+				yield* data
+			},
+		}
+	}
+
+	describe("prompt cache", () => {
+		const setModelData = (model: string, supportsPromptCaching: boolean) => {
+			mockModelFetch({
+				model_name: model,
+				litellm_params: {
+					model,
+				},
+				model_info: {
+					supports_prompt_caching: supportsPromptCaching,
+					input_cost_per_token: 0.01,
+					output_cost_per_token: 0.02,
+				},
+			})
+		}
+
+		describe("when the model doesn't support prompt caching", () => {
+			const model = "openai/gpt-5"
+
+			beforeEach(() => {
+				initializeHandler(model)
+				setModelData(model, false)
+			})
+
+			it("sends the system prompt and messages with the openai format", async () => {
+				const systemPrompt = "Test System Prompt"
+				const messages: Anthropic.Messages.MessageParam[] = [
+					{
+						role: "user",
+						content: "first message",
+					},
+					{
+						role: "assistant",
+						content: "first response",
+					},
+					{
+						role: "user",
+						content: [
+							{
+								type: "text",
+								text: "test",
+							},
+							{
+								type: "text",
+								text: "second message",
+							},
+						],
+					},
+				]
+
+				for await (const _ of handler.createMessage(systemPrompt, messages)) {
+				}
+
+				sinon.assert.calledOnce(fakeClient.chat.completions.create)
+
+				const callArgs = fakeClient.chat.completions.create.getCall(0).args[0]
+
+				const systemPromptMessage = callArgs.messages.shift()
+				expect(systemPromptMessage).to.deep.equal({
+					role: "system",
+					content: systemPrompt,
+				})
+
+				expect(callArgs.messages).to.deep.equal(convertToOpenAiMessages(messages))
+			})
+		})
+
+		describe("when the model supports prompt caching", () => {
+			const model = "anthropic/claude-sonnet-4-20250514"
+
+			beforeEach(() => {
+				initializeHandler(model)
+
+				setModelData(model, true)
+			})
+
+			it("inserts the cache control in the system prompt and the last two user messages", async () => {
+				const systemPrompt = "Test System Prompt"
+				const messages: Anthropic.Messages.MessageParam[] = [
+					{
+						role: "user",
+						content: "first message",
+					},
+					{
+						role: "assistant",
+						content: "first response",
+					},
+					{
+						role: "user",
+						content: [
+							{
+								type: "text",
+								text: "test",
+							},
+							{
+								type: "text",
+								text: "second message",
+							},
+						],
+					},
+				]
+
+				for await (const _ of handler.createMessage(systemPrompt, messages)) {
+				}
+
+				sinon.assert.calledOnce(fakeClient.chat.completions.create)
+
+				const callArgs = fakeClient.chat.completions.create.getCall(0).args[0]
+
+				expect(callArgs.messages[0]).to.deep.equal({
+					role: "system",
+					content: [
+						{
+							text: systemPrompt,
+							type: "text",
+							cache_control: {
+								type: "ephemeral",
+							},
+						},
+					],
+				})
+
+				const sentMessages = callArgs.messages
+				expect(sentMessages.length).to.equal(4)
+
+				const firstUserMessage = sentMessages[1]
+
+				expect(firstUserMessage).to.deep.equal({
+					role: "user",
+					content: [
+						{
+							type: "text",
+							text: "first message",
+							cache_control: {
+								type: "ephemeral",
+							},
+						},
+					],
+				})
+
+				const lastUserMessage = sentMessages[3]
+				expect(lastUserMessage.content[0]).to.deep.equal({
+					type: "text",
+					text: "test",
+				})
+
+				const lastContentBlock = lastUserMessage.content[lastUserMessage.content.length - 1]
+				expect(lastContentBlock).to.deep.equal({
+					type: "text",
+					text: "second message",
+					cache_control: {
+						type: "ephemeral",
+					},
+				})
+
+				expect(callArgs.model).to.be.a("string")
+				expect(callArgs.stream).to.equal(true)
+				expect(callArgs.stream_options).to.deep.equal({ include_usage: true })
+			})
+		})
+	})
+})

src/core/api/providers/__tests__/sapaicore.test.ts

@@ -0,0 +1,131 @@
+import "should"
+import { Anthropic } from "@anthropic-ai/sdk"
+import { SapAiCoreHandler } from "../sapaicore"
+
+describe("SapAiCoreHandler", () => {
+	let handler: SapAiCoreHandler
+
+	beforeEach(() => {
+		const mockOptions = {
+			sapAiCoreClientId: "test-client-id",
+			sapAiCoreClientSecret: "test-client-secret",
+			sapAiCoreTokenUrl: "https://test.auth.sap.com",
+			sapAiResourceGroup: "default",
+			sapAiCoreBaseUrl: "https://test.api.sap.com",
+			apiModelId: "anthropic--claude-3.5-sonnet",
+		}
+		handler = new SapAiCoreHandler(mockOptions)
+	})
+
+	describe("image processing", () => {
+		// Test image processing through the public interface
+		// This tests the complete flow including processImageContent internally
+
+		it("should handle image processing for Claude 4 models", () => {
+			// Create handler with Claude 4 model
+			const claude4Handler = new SapAiCoreHandler({
+				sapAiCoreClientId: "test-client-id",
+				sapAiCoreClientSecret: "test-client-secret",
+				sapAiCoreTokenUrl: "https://test.auth.sap.com",
+				sapAiResourceGroup: "default",
+				sapAiCoreBaseUrl: "https://test.api.sap.com",
+				apiModelId: "anthropic--claude-4-sonnet",
+			})
+
+			const model = claude4Handler.getModel()
+			model.id.should.equal("anthropic--claude-4-sonnet")
+			model.info.should.have.property("supportsImages", true)
+		})
+
+		it("should create proper user readable request with images", () => {
+			const testImageData =
+				"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8/5+hHgAHggJ/PchI7wAAAABJRU5ErkJggg=="
+
+			const userContent: (Anthropic.TextBlockParam | Anthropic.ImageBlockParam)[] = [
+				{
+					type: "text",
+					text: "Here's an image:",
+				},
+				{
+					type: "image",
+					source: {
+						type: "base64",
+						media_type: "image/png",
+						data: testImageData,
+					},
+				},
+			]
+
+			const result = handler.createUserReadableRequest(userContent)
+
+			result.should.have.property("model")
+			result.should.have.property("max_tokens")
+			result.should.have.property("system")
+			result.should.have.property("messages")
+			result.messages.should.be.Array()
+			result.messages[1].should.have.property("role", "user")
+			result.messages[1].should.have.property("content", userContent)
+		})
+
+		it("should support different Claude model variants", () => {
+			const modelVariants = [
+				"anthropic--claude-4-sonnet",
+				"anthropic--claude-4-opus",
+				"anthropic--claude-3.7-sonnet",
+				"anthropic--claude-3.5-sonnet",
+				"anthropic--claude-3-sonnet",
+				"anthropic--claude-3-haiku",
+				"anthropic--claude-3-opus",
+			]
+
+			modelVariants.forEach((modelId) => {
+				const testHandler = new SapAiCoreHandler({
+					apiModelId: modelId,
+				})
+
+				const model = testHandler.getModel()
+				model.id.should.equal(modelId)
+				model.info.should.have.property("maxTokens")
+				model.info.should.have.property("contextWindow")
+			})
+		})
+	})
+
+	describe("getModel", () => {
+		it("should return default model when no apiModelId is provided", () => {
+			const result = handler.getModel()
+			result.should.have.property("id")
+			result.should.have.property("info")
+			result.info.should.have.property("maxTokens")
+		})
+
+		it("should return specified model when apiModelId is provided", () => {
+			const customHandler = new SapAiCoreHandler({
+				apiModelId: "anthropic--claude-4-sonnet",
+			})
+
+			const result = customHandler.getModel()
+			result.id.should.equal("anthropic--claude-4-sonnet")
+		})
+	})
+
+	describe("createUserReadableRequest", () => {
+		it("should create a readable request format", () => {
+			const userContent: Anthropic.TextBlockParam[] = [
+				{
+					type: "text",
+					text: "Hello, world!",
+				},
+			]
+
+			const result = handler.createUserReadableRequest(userContent)
+
+			result.should.have.property("model")
+			result.should.have.property("max_tokens")
+			result.should.have.property("system")
+			result.should.have.property("messages")
+			result.should.have.property("tools")
+			result.should.have.property("tool_choice")
+		})
+	})
+})

src/core/api/providers/anthropic.ts

@@ -1,11 +1,11 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { Stream as AnthropicStream } from "@anthropic-ai/sdk/streaming"
 import { AnthropicModelId, anthropicDefaultModelId, anthropicModels, CLAUDE_SONNET_4_1M_SUFFIX, ModelInfo } from "@shared/api"
-import { ApiHandler } from "../index"
+import { ApiHandler, CommonApiHandlerOptions } from "../index"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"
 
-interface AnthropicHandlerOptions {
+interface AnthropicHandlerOptions extends CommonApiHandlerOptions {
 	apiKey?: string
 	anthropicBaseUrl?: string
 	apiModelId?: string

src/core/api/providers/asksage.ts

@@ -1,10 +1,10 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { AskSageModelId, askSageDefaultModelId, askSageDefaultURL, askSageModels, ModelInfo } from "@shared/api"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"
 
-interface AskSageHandlerOptions {
+interface AskSageHandlerOptions extends CommonApiHandlerOptions {
 	asksageApiKey?: string
 	asksageApiUrl?: string
 	apiModelId?: string

src/core/api/providers/baseten.ts

@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { BasetenModelId, basetenDefaultModelId, basetenModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface BasetenHandlerOptions {
+interface BasetenHandlerOptions extends CommonApiHandlerOptions {
 	basetenApiKey?: string
 	basetenModelId?: string
 	basetenModelInfo?: ModelInfo

src/core/api/providers/bedrock.ts

@@ -11,12 +11,12 @@ import {
 import { fromNodeProviderChain } from "@aws-sdk/credential-providers"
 import { BedrockModelId, bedrockDefaultModelId, bedrockModels, CLAUDE_SONNET_4_1M_SUFFIX, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"
 
-interface AwsBedrockHandlerOptions {
+interface AwsBedrockHandlerOptions extends CommonApiHandlerOptions {
 	apiModelId?: string
 	awsAccessKey?: string
 	awsSecretKey?: string

src/core/api/providers/cerebras.ts

@@ -1,11 +1,11 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import Cerebras from "@cerebras/cerebras_cloud_sdk"
 import { CerebrasModelId, cerebrasDefaultModelId, cerebrasModels, ModelInfo } from "@shared/api"
-import { ApiHandler } from "../index"
+import { ApiHandler, CommonApiHandlerOptions } from "../index"
 import { withRetry } from "../retry"
 import { ApiStream } from "../transform/stream"
 
-interface CerebrasHandlerOptions {
+interface CerebrasHandlerOptions extends CommonApiHandlerOptions {
 	cerebrasApiKey?: string
 	apiModelId?: string
 }

src/core/api/providers/claude-code.ts

@@ -2,11 +2,11 @@ import type { Anthropic } from "@anthropic-ai/sdk"
 import { filterMessagesForClaudeCode } from "@/integrations/claude-code/message-filter"
 import { runClaudeCode } from "@/integrations/claude-code/run"
 import { ClaudeCodeModelId, claudeCodeDefaultModelId, claudeCodeModels } from "@/shared/api"
-import { type ApiHandler } from ".."
+import { type ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { type ApiStream, ApiStreamUsageChunk } from "../transform/stream"
 
-interface ClaudeCodeHandlerOptions {
+interface ClaudeCodeHandlerOptions extends CommonApiHandlerOptions {
 	claudeCodePath?: string
 	apiModelId?: string
 	thinkingBudgetTokens?: number
@@ -118,10 +118,14 @@ export class ClaudeCodeHandler implements ApiHandler {
 					}
 				}
 
-				usage.inputTokens += message.usage.input_tokens
-				usage.outputTokens += message.usage.output_tokens
-				usage.cacheReadTokens = (usage.cacheReadTokens || 0) + (message.usage.cache_read_input_tokens || 0)
-				usage.cacheWriteTokens = (usage.cacheWriteTokens || 0) + (message.usage.cache_creation_input_tokens || 0)
+				// According to Anthropic's API documentation:
+				// https://docs.anthropic.com/en/api/messages#usage-object
+				// The `input_tokens` field already includes both `cache_read_input_tokens` and `cache_creation_input_tokens`.
+				// Therefore, we should not add cache tokens to the input_tokens count again, as this would result in double-counting.
+				usage.inputTokens = message.usage?.input_tokens ?? 0
+				usage.outputTokens = message.usage?.output_tokens ?? 0
+				usage.cacheReadTokens = message.usage?.cache_read_input_tokens ?? 0
+				usage.cacheWriteTokens = message.usage?.cache_creation_input_tokens ?? 0
 
 				continue
 			}

src/core/api/providers/cline.ts

@@ -8,14 +8,15 @@ import { ClineAccountService } from "@/services/account/ClineAccountService"
 import { AuthService } from "@/services/auth/AuthService"
 import { CLINE_ACCOUNT_AUTH_ERROR_MESSAGE } from "@/shared/ClineAccount"
 import { version as extensionVersion } from "../../../../package.json"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { createOpenRouterStream } from "../transform/openrouter-stream"
 import { ApiStream, ApiStreamUsageChunk } from "../transform/stream"
 import { OpenRouterErrorResponse } from "./types"
 
-interface ClineHandlerOptions {
+interface ClineHandlerOptions extends CommonApiHandlerOptions {
 	ulid?: string
+	taskId?: string
 	reasoningEffort?: string
 	thinkingBudgetTokens?: number
 	openRouterProviderSorting?: string
@@ -137,6 +138,10 @@ export class ClineHandler implements ApiHandler {
 						totalCost = 0
 					}
 
+					if (this.getModel().id === "x-ai/grok-code-fast-1") {
+						totalCost = 0
+					}
+
 					yield {
 						type: "usage",
 						cacheWriteTokens: 0,

src/core/api/providers/deepseek.ts

@@ -2,13 +2,13 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { DeepSeekModelId, deepSeekDefaultModelId, deepSeekModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { convertToR1Format } from "../transform/r1-format"
 import { ApiStream } from "../transform/stream"
 
-interface DeepSeekHandlerOptions {
+interface DeepSeekHandlerOptions extends CommonApiHandlerOptions {
 	deepSeekApiKey?: string
 	apiModelId?: string
 }

src/core/api/providers/dify.ts

@@ -0,0 +1,655 @@
+import { Anthropic } from "@anthropic-ai/sdk"
+import { ApiHandlerOptions, ModelInfo } from "../../../shared/api"
+import { ApiHandler } from "../index"
+import { ApiStream } from "../transform/stream"
+
+// Dify API Response Types
+export interface DifyFileResponse {
+	id: string
+	name: string
+	size: number
+	extension: string
+	mime_type: string
+	created_by: string
+	created_at: number
+}
+
+export interface DifyMessage {
+	id: string
+	conversation_id: string
+	inputs: Record<string, any>
+	query: string
+	message_files: Array<{
+		id: string
+		type: string
+		url: string
+		belongs_to: string
+	}>
+	answer: string
+	created_at: number
+	feedback?: {
+		rating: string
+	}
+	retriever_resources?: any[]
+}
+
+interface DifyHistoryResponse {
+	data: DifyMessage[]
+	has_more: boolean
+	limit: number
+}
+
+interface DifyConversation {
+	id: string
+	name: string
+	inputs: Record<string, any>
+	status: string
+	introduction: string
+	created_at: number
+	updated_at: number
+}
+
+interface DifyConversationsResponse {
+	data: DifyConversation[]
+	has_more: boolean
+	limit: number
+}
+
+interface DifyConversationResponse {
+	id: string
+	name: string
+	inputs: Record<string, any>
+	status: string
+	introduction: string
+	created_at: number
+	updated_at: number
+}
+
+export class DifyHandler implements ApiHandler {
+	private options: ApiHandlerOptions
+	private baseUrl: string
+	private apiKey: string
+	private conversationId: string | null = null
+	private currentTaskId: string | null = null
+	private abortController: AbortController | null = null
+
+	constructor(options: ApiHandlerOptions) {
+		this.options = options
+		this.apiKey = options.difyApiKey || ""
+		this.baseUrl = options.difyBaseUrl || ""
+
+		console.log("[DIFY DEBUG] Constructor called with:", {
+			hasApiKey: !!this.apiKey,
+			baseUrl: this.baseUrl,
+		})
+
+		if (!this.apiKey) {
+			throw new Error("Dify API key is required")
+		}
+		if (!this.baseUrl) {
+			throw new Error("Dify base URL is required")
+		}
+	}
+
+	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
+		console.log("[DIFY DEBUG] createMessage called with:", {
+			systemPromptLength: systemPrompt?.length || 0,
+			messagesCount: messages?.length || 0,
+		})
+
+		// Convert messages to Dify format
+		const query = this.convertMessagesToQuery(systemPrompt, messages)
+		const requestBody = {
+			inputs: {},
+			query: query,
+			response_mode: "streaming",
+			conversation_id: this.conversationId || "",
+			user: "cline-user", // A unique user identifier
+			files: [],
+		}
+
+		const fullUrl = `${this.baseUrl}/chat-messages`
+		console.log("[DIFY DEBUG] Making request to:", fullUrl)
+		console.log("[DIFY DEBUG] Request body:", JSON.stringify(requestBody, null, 2))
+
+		let response: Response
+		try {
+			response = await fetch(fullUrl, {
+				method: "POST",
+				headers: {
+					Authorization: `Bearer ${this.apiKey}`,
+					"Content-Type": "application/json",
+				},
+				body: JSON.stringify(requestBody),
+			})
+		} catch (error: any) {
+			console.error("[DIFY DEBUG] Network error during fetch:", error)
+			const cause = error.cause ? ` | Cause: ${error.cause}` : ""
+			throw new Error(`Dify API network error: ${error.message}${cause}`)
+		}
+
+		console.log("[DIFY DEBUG] Response status:", response.status)
+		const headersObj: Record<string, string> = {}
+		response.headers.forEach((value, key) => {
+			headersObj[key] = value
+		})
+		console.log("[DIFY DEBUG] Response headers:", headersObj)
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			console.error("[DIFY DEBUG] Error response:", errorText)
+			throw new Error(`Dify API error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+
+		if (!response.body) {
+			throw new Error("No response body from Dify API")
+		}
+
+		const reader = response.body.getReader()
+		const decoder = new TextDecoder()
+		let buffer = ""
+		let fullText = ""
+		let hasYieldedContent = false
+		const processedEvents: string[] = []
+		let lastEventTime = Date.now()
+
+		console.log("[DIFY DEBUG] Starting to read streaming response...")
+
+		try {
+			while (true) {
+				const { done, value } = await reader.read()
+				if (done) {
+					console.log("[DIFY DEBUG] Stream ended naturally")
+					console.log(
+						"[DIFY DEBUG] Final state - hasYieldedContent:",
+						hasYieldedContent,
+						"fullText length:",
+						fullText.length,
+						"processedEvents:",
+						processedEvents,
+					)
+					break
+				}
+
+				const chunk = decoder.decode(value, { stream: true })
+				console.log("[DIFY DEBUG] Raw chunk received:", JSON.stringify(chunk))
+
+				buffer += chunk
+				const lines = buffer.split("\n")
+
+				// Keep the last incomplete line in the buffer
+				buffer = lines.pop() || ""
+
+				for (const line of lines) {
+					console.log("[DIFY DEBUG] Processing line:", JSON.stringify(line))
+
+					if (line.startsWith("data: ")) {
+						const data = line.slice(6).trim()
+						console.log("[DIFY DEBUG] Extracted data:", JSON.stringify(data))
+
+						if (data === "[DONE]") {
+							console.log("[DIFY DEBUG] Received [DONE] signal")
+							break
+						}
+
+						if (data === "") {
+							console.log("[DIFY DEBUG] Empty data line, skipping")
+							continue
+						}
+
+						try {
+							const parsed = JSON.parse(data)
+							console.log("[DIFY DEBUG] Parsed JSON:", parsed)
+							processedEvents.push(parsed.event || "unknown")
+							lastEventTime = Date.now()
+
+							// Capture conversation_id as soon as it's available
+							if (parsed.conversation_id && !this.conversationId) {
+								this.conversationId = parsed.conversation_id
+								console.log("[DIFY DEBUG] Captured conversation_id:", this.conversationId)
+							}
+
+							// Handle different Dify event types based on actual Dify API
+							if (parsed.event === "message") {
+								console.log("[DIFY DEBUG] Message event, answer:", parsed.answer)
+								// Dify sends the full text in each "answer" chunk, so we replace.
+								if (typeof parsed.answer === "string") {
+									fullText = parsed.answer
+									console.log("[DIFY DEBUG] Updated fullText length:", fullText.length)
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								}
+							} else if (parsed.event === "message_replace") {
+								console.log("[DIFY DEBUG] Replace message event:", parsed)
+								if (parsed.answer) {
+									fullText = parsed.answer // Replace instead of append
+									console.log("[DIFY DEBUG] Replaced fullText length:", fullText.length)
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								}
+							} else if (parsed.event === "message_end") {
+								console.log("[DIFY DEBUG] Message end event", parsed)
+								// Message completed. Yield final text if we have any.
+								if (fullText) {
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								}
+								// Yield usage data if available
+								if (parsed.usage) {
+									yield {
+										type: "usage",
+										inputTokens: parsed.usage.prompt_tokens || 0,
+										outputTokens: parsed.usage.completion_tokens || parsed.usage.total_tokens || 0,
+										totalCost: parsed.usage.total_price || 0,
+									}
+								}
+								return // End of stream
+							} else if (parsed.event === "error") {
+								console.error("[DIFY DEBUG] Error event:", parsed)
+								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
+							} else if (parsed.event === "workflow_started" || parsed.event === "workflow_finished") {
+								console.log("[DIFY DEBUG] Workflow event:", parsed.event)
+								// These are informational events, continue processing
+							} else if (parsed.event === "node_started" || parsed.event === "node_finished") {
+								console.log("[DIFY DEBUG] Node event:", parsed.event, parsed.data)
+								// These are informational events, continue processing
+							} else if (parsed.event === "ping") {
+								console.log("[DIFY DEBUG] Ping event received, keeping connection alive.")
+								// Ping event, do nothing
+							} else {
+								console.log("[DIFY DEBUG] Unknown event type:", parsed.event, "Full object:", parsed)
+								// Try to extract text from other possible fields
+								if (parsed.text) {
+									fullText += parsed.text
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								} else if (parsed.content) {
+									fullText += parsed.content
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								} else if (parsed.answer) {
+									// Fallback: some events might have answer field even if not "message" type
+									fullText += parsed.answer
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								}
+							}
+						} catch (e) {
+							console.warn("[DIFY DEBUG] Failed to parse JSON:", data, "Error:", e)
+						}
+					} else if (line.trim() !== "") {
+						console.log(
+							"[DIFY DEBUG] Non-data line (not starting with 'data:'), trying to parse as direct JSON:",
+							JSON.stringify(line),
+						)
+						// Try to parse as direct JSON (fallback for non-SSE responses, though Dify uses SSE)
+						try {
+							const parsed = JSON.parse(line.trim())
+							console.log("[DIFY DEBUG] Parsed direct JSON:", parsed)
+							processedEvents.push(parsed.event || "direct-json")
+
+							// Handle the same event types as above
+							if (parsed.event === "message" && parsed.answer) {
+								fullText += parsed.answer
+								yield {
+									type: "text",
+									text: fullText,
+								}
+								hasYieldedContent = true
+							} else if (parsed.event === "message_end") {
+								if (fullText) {
+									yield {
+										type: "text",
+										text: fullText,
+									}
+									hasYieldedContent = true
+								}
+								return
+							} else if (parsed.event === "error") {
+								console.error("[DIFY DEBUG] Direct JSON Error event:", parsed)
+								throw new Error(`Dify API error: ${parsed.message || "Unknown error"}`)
+							} else if (parsed.answer || parsed.text || parsed.content) {
+								// Fallback for any content in direct JSON
+								const content = parsed.answer || parsed.text || parsed.content
+								fullText += content
+								yield {
+									type: "text",
+									text: fullText,
+								}
+								hasYieldedContent = true
+							}
+						} catch (e) {
+							// Not JSON, continue
+							console.log("[DIFY DEBUG] Line is not direct JSON, continuing")
+						}
+					}
+				}
+			}
+
+			// Final check - if we haven't yielded any content, provide diagnostic information
+			if (!hasYieldedContent) {
+				const diagnosticInfo = {
+					processedEvents,
+					finalFullTextLength: fullText.length,
+					finalFullText: fullText,
+					streamDuration: Date.now() - lastEventTime,
+					conversationId: this.conversationId,
+				}
+				console.error("[DIFY DEBUG] No content was yielded! Diagnostic info:", diagnosticInfo)
+
+				// If we have any accumulated text at all, yield it as a fallback
+				if (fullText.trim()) {
+					console.log("[DIFY DEBUG] Yielding accumulated text as fallback:", fullText)
+					yield {
+						type: "text",
+						text: fullText,
+					}
+				} else {
+					// Provide a more informative error
+					throw new Error(
+						`Dify API did not provide any assistant messages. ` +
+							`Events processed: [${processedEvents.join(", ")}]. ` +
+							`Check your Dify application configuration and ensure it's properly set up to return responses. ` +
+							`API URL: ${fullUrl}. Conversation ID: ${this.conversationId || "none"}.`,
+					)
+				}
+			}
+		} finally {
+			reader.releaseLock()
+			console.log("[DIFY DEBUG] Stream reader released")
+		}
+	}
+
+	private convertMessagesToQuery(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): string {
+		// Dify's context is managed by `conversation_id`. The `query` should be the last user message.
+		// The system prompt is typically configured in the Dify App itself.
+		const lastUserMessage = messages.filter((m) => m.role === "user").pop()
+
+		if (!lastUserMessage) {
+			return "" // Should not happen in normal flow
+		}
+
+		const userQuery = Array.isArray(lastUserMessage.content)
+			? lastUserMessage.content.map((c) => ("text" in c ? c.text : "")).join("\n")
+			: (lastUserMessage.content as string)
+
+		// Only prepend the system prompt if it's the very first message of a new conversation.
+		if (!this.conversationId && systemPrompt) {
+			console.log("[DIFY DEBUG] Prepending system prompt for new conversation.")
+			return `${systemPrompt}\n\n---\n\n${userQuery}`
+		}
+
+		return userQuery
+	}
+
+	getModel(): { id: string; info: ModelInfo } {
+		return {
+			id: "dify-workflow",
+			info: {
+				maxTokens: 8192,
+				contextWindow: 128000,
+				supportsImages: true,
+				supportsPromptCache: false,
+				inputPrice: 0,
+				outputPrice: 0,
+				description: "Dify workflow - model selection is configured in your Dify application",
+			},
+		}
+	}
+
+	// Additional Dify API Methods
+
+	/**
+	 * Upload a file for use in conversations
+	 * @param file File buffer to upload
+	 * @param filename Name of the file
+	 * @param user User identifier (defaults to "cline-user")
+	 * @returns Promise with file upload response
+	 */
+	async uploadFile(file: Buffer, filename: string, user: string = "cline-user"): Promise<DifyFileResponse> {
+		const formData = new FormData()
+		formData.append("file", new Blob([new Uint8Array(file)]), filename)
+		formData.append("user", user)
+
+		const response = await fetch(`${this.baseUrl}/files/upload`, {
+			method: "POST",
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+			},
+			body: formData,
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify file upload error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+
+		return response.json()
+	}
+
+	/**
+	 * Stop generation for a specific task
+	 * @param taskId Task ID from streaming response
+	 * @param user User identifier (defaults to "cline-user")
+	 * @returns Promise that resolves when generation is stopped
+	 */
+	async stopGeneration(taskId: string, user: string = "cline-user"): Promise<void> {
+		const response = await fetch(`${this.baseUrl}/chat-messages/${taskId}/stop`, {
+			method: "POST",
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+				"Content-Type": "application/json",
+			},
+			body: JSON.stringify({ user }),
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify stop generation error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+	}
+
+	/**
+	 * Get conversation history messages with pagination
+	 * @param conversationId Conversation ID
+	 * @param user User identifier (defaults to "cline-user")
+	 * @param firstId First message ID for pagination (optional)
+	 * @param limit Number of messages to return (default: 20)
+	 * @returns Promise with conversation history
+	 */
+	async getConversationHistory(
+		conversationId: string,
+		user: string = "cline-user",
+		firstId?: string,
+		limit: number = 20,
+	): Promise<DifyHistoryResponse> {
+		const params = new URLSearchParams({ user, limit: limit.toString() })
+		if (firstId) {
+			params.append("first_id", firstId)
+		}
+
+		const response = await fetch(`${this.baseUrl}/conversations/${conversationId}/messages?${params}`, {
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+			},
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify get conversation history error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+
+		return response.json()
+	}
+
+	/**
+	 * Get list of conversations for a user
+	 * @param user User identifier (defaults to "cline-user")
+	 * @param lastId Last conversation ID for pagination (optional)
+	 * @param limit Number of conversations to return (default: 20)
+	 * @param sortBy Sort field (default: "-updated_at")
+	 * @returns Promise with conversations list
+	 */
+	async getConversations(
+		user: string = "cline-user",
+		lastId?: string,
+		limit: number = 20,
+		sortBy: string = "-updated_at",
+	): Promise<DifyConversationsResponse> {
+		const params = new URLSearchParams({
+			user,
+			limit: limit.toString(),
+			sort_by: sortBy,
+		})
+		if (lastId) {
+			params.append("last_id", lastId)
+		}
+
+		const response = await fetch(`${this.baseUrl}/conversations?${params}`, {
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+			},
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify get conversations error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+
+		return response.json()
+	}
+
+	/**
+	 * Delete a conversation
+	 * @param conversationId Conversation ID to delete
+	 * @param user User identifier (defaults to "cline-user")
+	 * @returns Promise that resolves when conversation is deleted
+	 */
+	async deleteConversation(conversationId: string, user: string = "cline-user"): Promise<void> {
+		const response = await fetch(`${this.baseUrl}/conversations/${conversationId}`, {
+			method: "DELETE",
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+				"Content-Type": "application/json",
+			},
+			body: JSON.stringify({ user }),
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify delete conversation error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+	}
+
+	/**
+	 * Rename a conversation
+	 * @param conversationId Conversation ID to rename
+	 * @param user User identifier (defaults to "cline-user")
+	 * @param name New conversation name (optional if auto_generate is true)
+	 * @param autoGenerate Whether to auto-generate the name (default: false)
+	 * @returns Promise with updated conversation details
+	 */
+	async renameConversation(
+		conversationId: string,
+		user: string = "cline-user",
+		name?: string,
+		autoGenerate: boolean = false,
+	): Promise<DifyConversationResponse> {
+		const body: any = { user, auto_generate: autoGenerate }
+		if (name) {
+			body.name = name
+		}
+
+		const response = await fetch(`${this.baseUrl}/conversations/${conversationId}/name`, {
+			method: "POST",
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+				"Content-Type": "application/json",
+			},
+			body: JSON.stringify(body),
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify rename conversation error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+
+		return response.json()
+	}
+
+	/**
+	 * Submit feedback for a message
+	 * @param messageId Message ID to provide feedback for
+	 * @param rating Rating: "like" or "dislike"
+	 * @param content Optional feedback content
+	 * @param user User identifier (defaults to "cline-user")
+	 * @returns Promise that resolves when feedback is submitted
+	 */
+	async submitMessageFeedback(
+		messageId: string,
+		rating: "like" | "dislike",
+		content?: string,
+		user: string = "cline-user",
+	): Promise<void> {
+		const body: any = { rating, user }
+		if (content) {
+			body.content = content
+		}
+
+		const response = await fetch(`${this.baseUrl}/messages/${messageId}/feedbacks`, {
+			method: "POST",
+			headers: {
+				Authorization: `Bearer ${this.apiKey}`,
+				"Content-Type": "application/json",
+			},
+			body: JSON.stringify(body),
+		})
+
+		if (!response.ok) {
+			const errorText = await response.text()
+			throw new Error(`Dify submit feedback error: ${response.status} ${response.statusText} - ${errorText}`)
+		}
+	}
+
+	/**
+	 * Get current conversation ID
+	 * @returns Current conversation ID or null
+	 */
+	getCurrentConversationId(): string | null {
+		return this.conversationId
+	}
+
+	/**
+	 * Set conversation ID for continuing existing conversations
+	 * @param conversationId Conversation ID to set
+	 */
+	setConversationId(conversationId: string): void {
+		this.conversationId = conversationId
+	}
+
+	/**
+	 * Reset conversation ID to start a new conversation
+	 */
+	resetConversation(): void {
+		this.conversationId = null
+		this.currentTaskId = null
+	}
+}

src/core/api/providers/doubao.ts

@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { DoubaoModelId, doubaoDefaultModelId, doubaoModels, ModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface DoubaoHandlerOptions {
+interface DoubaoHandlerOptions extends CommonApiHandlerOptions {
 	doubaoApiKey?: string
 	apiModelId?: string
 }

src/core/api/providers/fireworks.ts

@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { FireworksModelId, fireworksDefaultModelId, fireworksModels, ModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface FireworksHandlerOptions {
+interface FireworksHandlerOptions extends CommonApiHandlerOptions {
 	fireworksApiKey?: string
 	fireworksModelId?: string
 	fireworksModelMaxCompletionTokens?: number

src/core/api/providers/gemini.ts

@@ -1,17 +1,19 @@
 import type { Anthropic } from "@anthropic-ai/sdk"
 // Restore GenerateContentConfig import and add GenerateContentResponseUsageMetadata
-import { type GenerateContentConfig, type GenerateContentResponseUsageMetadata, GoogleGenAI, Part } from "@google/genai"
-import { telemetryService } from "@services/posthog/PostHogClientProvider"
+import { ApiError, type GenerateContentConfig, type GenerateContentResponseUsageMetadata, GoogleGenAI, Part } from "@google/genai"
 import { GeminiModelId, geminiDefaultModelId, geminiModels, ModelInfo } from "@shared/api"
-import { ApiHandler } from "../"
-import { withRetry } from "../retry"
+import { telemetryService } from "@/services/telemetry"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
+import { RetriableError, withRetry } from "../retry"
 import { convertAnthropicMessageToGemini } from "../transform/gemini-format"
 import { ApiStream } from "../transform/stream"
 
 // Define a default TTL for the cache (e.g., 15 minutes in seconds)
 const _DEFAULT_CACHE_TTL_SECONDS = 900
 
-interface GeminiHandlerOptions {
+const rateLimitPatterns = [/got status: 429/i, /429 Too Many Requests/i, /rate limit exceeded/i, /too many requests/i]
+
+interface GeminiHandlerOptions extends CommonApiHandlerOptions {
 	isVertex?: boolean
 	vertexProjectId?: string
 	vertexRegion?: string
@@ -222,24 +224,40 @@ export class GeminiHandler implements ApiHandler {
 			if (error instanceof Error) {
 				apiError = error.message
 
-				// Gemini doesn't include status codes in their errors
-				// https://github.com/googleapis/js-genai/blob/61f7f27b866c74333ca6331883882489bcb708b9/src/_api_client.ts#L569
-				const rateLimitPatterns = [
-					/got status: 429/i,
-					/429 Too Many Requests/i,
-					/rate limit exceeded/i,
-					/too many requests/i,
-				]
+				if (error instanceof ApiError) {
+					if (error.status === 429) {
+						// The API includes more details in the message
+						// https://github.com/googleapis/js-genai/blob/v1.11.0/src/_api_client.ts#L758
+						const response = this.attemptParse(error.message)
 
-				const isRateLimit =
-					error.name === "ClientError" && rateLimitPatterns.some((pattern) => pattern.test(error.message))
+						if (response && response.error) {
+							const responseBody = this.attemptParse(response.error.message)
 
-				if (isRateLimit) {
-					const rateLimitError = Object.assign(new Error(error.message), {
-						...error,
-						status: 429,
-					})
-					throw rateLimitError
+							if (responseBody.error) {
+								const detail = responseBody.error.details?.find(
+									(d: any) => d["@type"] === "type.googleapis.com/google.rpc.RetryInfo",
+								)
+
+								const detailedError = new RetriableError(
+									apiError,
+									this.parseRetryDelay(detail?.retryDelay) || undefined,
+									{
+										cause: error,
+									},
+								)
+								throw detailedError
+							}
+						}
+
+						throw new RetriableError(apiError, undefined, { cause: error })
+					}
+
+					// Fallback in case Gemini throws a rate limit error without a 429 status code
+					// https://github.com/cline/cline/pull/5205#discussion_r2311761559
+					const isRateLimit = rateLimitPatterns.some((pattern) => pattern.test(error.message))
+					if (isRateLimit) {
+						throw new RetriableError(apiError, undefined, { cause: error })
+					}
 				}
 			} else {
 				apiError = String(error)
@@ -420,4 +438,35 @@ export class GeminiHandler implements ApiHandler {
 
 		return Math.ceil(totalChars / 4)
 	}
+
+	private parseRetryDelay(retryAfter?: string): number {
+		if (!retryAfter) {
+			return 0
+		}
+
+		const unit = retryAfter.at(-1)
+		const value = parseInt(retryAfter, 10)
+
+		if (Number.isNaN(value)) {
+			return 0
+		}
+
+		if (unit === "s") {
+			return value
+		} else if (unit === "m") {
+			return value * 60 // Convert minutes to seconds
+		} else if (unit === "h") {
+			return value * 60 * 60 // Convert hours to seconds
+		}
+
+		return value
+	}
+
+	private attemptParse(str: string) {
+		try {
+			return JSON.parse(str)
+		} catch (_) {
+			return null
+		}
+	}
 }

src/core/api/providers/groq.ts

@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { GroqModelId, groqDefaultModelId, groqModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface GroqHandlerOptions {
+interface GroqHandlerOptions extends CommonApiHandlerOptions {
 	groqApiKey?: string
 	groqModelId?: string
 	groqModelInfo?: ModelInfo

src/core/api/providers/huawei-cloud-maas.ts

@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { HuaweiCloudMaasModelId, huaweiCloudMaasDefaultModelId, huaweiCloudMaasModels, ModelInfo } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface HuaweiCloudMaaSHandlerOptions {
+interface HuaweiCloudMaaSHandlerOptions extends CommonApiHandlerOptions {
 	huaweiCloudMaasApiKey?: string
 	huaweiCloudMaasModelId?: string
 	huaweiCloudMaasModelInfo?: ModelInfo

src/core/api/providers/huggingface.ts

@@ -2,12 +2,12 @@ import { Anthropic } from "@anthropic-ai/sdk"
 import { HuggingFaceModelId, huggingFaceDefaultModelId, huggingFaceModels, ModelInfo } from "@shared/api"
 import { calculateApiCostOpenAI } from "@utils/cost"
 import OpenAI from "openai"
-import { ApiHandler } from "../"
+import { ApiHandler, CommonApiHandlerOptions } from "../"
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface HuggingFaceHandlerOptions {
+interface HuggingFaceHandlerOptions extends CommonApiHandlerOptions {
 	huggingFaceApiKey?: string
 	huggingFaceModelId?: string
 	huggingFaceModelInfo?: ModelInfo

src/core/api/providers/litellm.ts

@@ -1,12 +1,12 @@
 import { Anthropic } from "@anthropic-ai/sdk"
 import { LiteLLMModelInfo, liteLlmDefaultModelId, liteLlmModelInfoSaneDefaults } from "@shared/api"
 import OpenAI from "openai"
-import { ApiHandler } from ".."
+import { ApiHandler, CommonApiHandlerOptions } from ".."
 import { withRetry } from "../retry"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
 
-interface LiteLlmHandlerOptions {
+interface LiteLlmHandlerOptions extends CommonApiHandlerOptions {
 	liteLlmApiKey?: string
 	liteLlmBaseUrl?: string
 	liteLlmModelId?: string
@@ -16,7 +16,7 @@ interface LiteLlmHandlerOptions {
 	ulid?: string
 }
 
-interface LiteLlmModelInfoResponse {
+export interface LiteLlmModelInfoResponse {
 	data: Array<{
 		model_name: string
 		litellm_params: {
@@ -28,6 +28,7 @@ interface LiteLlmModelInfoResponse {
 			output_cost_per_token: number
 			cache_creation_input_token_cost?: number
 			cache_read_input_token_cost?: number
+			supports_prompt_caching?: boolean
 			[key: string]: any
 		}
 	}>
@@ -61,7 +62,17 @@ export class LiteLlmHandler implements ApiHandler {
 		return this.client
 	}
 
-	private async fetchModelInfo(): Promise<LiteLlmModelInfoResponse | undefined> {
+	private async modelInfo(publicModelName: string): Promise<LiteLlmModelInfoResponse["data"][number] | undefined> {
+		const modelInfo = await this.fetchModelsInfo()
+
+		if (!modelInfo?.data) {
+			return undefined
+		}
+
+		return modelInfo.data.find((model) => model.model_name === publicModelName)
+	}
+
+	private async fetchModelsInfo(): Promise<LiteLlmModelInfoResponse | undefined> {
 		// Check if cache is still valid
 		const now = Date.now()
 		if (this.modelInfoCache && now - this.modelInfoCacheTimestamp < this.modelInfoCacheTTL) {
@@ -121,19 +132,14 @@ export class LiteLlmHandler implements ApiHandler {
 		cacheReadCostPerToken?: number
 	}> {
 		try {
-			const modelInfo = await this.fetchModelInfo()
+			const matchingModel = await this.modelInfo(publicModelName)
 
-			if (modelInfo?.data) {
-				// Find the model by public name
-				const matchingModel = modelInfo.data.find((model) => model.model_name === publicModelName)
-
-				if (matchingModel?.model_info) {
-					return {
-						inputCostPerToken: matchingModel.model_info.input_cost_per_token || 0,
-						outputCostPerToken: matchingModel.model_info.output_cost_per_token || 0,
-						cacheCreationCostPerToken: matchingModel.model_info.cache_creation_input_token_cost,
-						cacheReadCostPerToken: matchingModel.model_info.cache_read_input_token_cost,
-					}
+			if (matchingModel) {
+				return {
+					inputCostPerToken: matchingModel.model_info.input_cost_per_token || 0,
+					outputCostPerToken: matchingModel.model_info.output_cost_per_token || 0,
+					cacheCreationCostPerToken: matchingModel.model_info.cache_creation_input_token_cost,
+					cacheReadCostPerToken: matchingModel.model_info.cache_read_input_token_cost,
 				}
 			}
 		} catch (error) {
@@ -177,7 +183,7 @@ export class LiteLlmHandler implements ApiHandler {
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
 		const client = this.ensureClient()
 		const formattedMessages = convertToOpenAiMessages(messages)
-		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam = {
+		const systemMessage: OpenAI.Chat.ChatCompletionSystemMessageParam | Anthropic.Messages.TextBlockParam = {
 			role: "system",
 			content: systemPrompt,
 		}
@@ -195,13 +201,22 @@ export class LiteLlmHandler implements ApiHandler {
 			temperature = undefined // Thinking mode doesn't support temperature
 		}
 
-		// Define cache control object if prompt caching is enabled
-		const cacheControl = this.options.liteLlmUsePromptCache ? { cache_control: { type: "ephemeral" } } : undefined
+		const modelInfo = await this.modelInfo(modelId)
+		const cacheControl =
+			this.options.liteLlmUsePromptCache && Boolean(modelInfo?.model_info.supports_prompt_caching)
+				? { cache_control: { type: "ephemeral" } }
+				: undefined
 
-		// Add cache_control to system message if enabled
-		const enhancedSystemMessage = {
-			...systemMessage,
-			...(cacheControl && cacheControl),
+		if (cacheControl) {
+			// Add cache_control to system message if enabled
+			// https://docs.litellm.ai/docs/providers/anthropic#caching---large-context-caching
+			systemMessage.content = [
+				{
+					text: systemPrompt,
+					type: "text",
+					...cacheControl,
+				},
+			] as Anthropic.Messages.TextBlockParam[]
 		}
 
 		// Find the last two user messages to apply caching
@@ -213,19 +228,49 @@ export class LiteLlmHandler implements ApiHandler {
 		const secondLastUserMsgIndex = userMsgIndices[userMsgIndices.length - 2] ?? -1
 
 		// Apply cache_control to the last two user messages if enabled
-		const enhancedMessages = formattedMessages.map((message, index) => {
-			if ((index === lastUserMsgIndex || index === secondLastUserMsgIndex) && cacheControl) {
-				return {
-					...message,
-					...cacheControl,
+		// https://docs.litellm.ai/docs/providers/anthropic#caching---large-context-caching
+		const enhancedMessages: OpenAI.Chat.ChatCompletionMessageParam[] = formattedMessages.map(
+			(message, index): OpenAI.Chat.ChatCompletionMessageParam => {
+				if ((index === lastUserMsgIndex || index === secondLastUserMsgIndex) && cacheControl) {
+					// Handle both string and array content types
+					if (typeof message.content === "string") {
+						return {
+							...message,
+							content: [
+								{
+									type: "text",
+									text: message.content,
+									...cacheControl,
+								},
+							] as any,
+						}
+					} else if (Array.isArray(message.content)) {
+						// Apply cache control to the last content item in the array
+						return {
+							...message,
+							content: message.content.map((item, contentIndex) =>
+								contentIndex === (message.content?.length || 0) - 1
+									? {
+											...item,
+											...cacheControl,
+										}
+									: item,
+							) as any,
+						}
+					}
+
+					return {
+						...message,
+						...cacheControl,
+					}
 				}
-			}
-			return message
-		})
+				return message
+			},
+		)
 
 		const stream = await client.chat.completions.create({
 			model: this.options.liteLlmModelId || liteLlmDefaultModelId,
-			messages: [enhancedSystemMessage, ...enhancedMessages],
+			messages: [systemMessage, ...enhancedMessages],
 			temperature,
 			stream: true,
 			stream_options: { include_usage: true },
@@ -244,16 +289,16 @@ export class LiteLlmHandler implements ApiHandler {
 				}
 			}
 
-			// Handle reasoning events (thinking)
-			// Thinking is not in the standard types but may be in the response
+			// Handle reasoning events
+			// This is not in the standard types but may be in the response
 			interface ThinkingDelta {
-				thinking?: string
+				reasoning_content?: string
 			}
 
-			if ((delta as ThinkingDelta)?.thinking) {
+			if ((delta as ThinkingDelta)?.reasoning_content) {
 				yield {
 					type: "reasoning",
-					reasoning: (delta as ThinkingDelta).thinking || "",
+					reasoning: (delta as ThinkingDelta).reasoning_content || "",
 				}
 			}