mirror of
https://github.com/tiddly-gittly/TidGi-Desktop.git
synced 2026-03-17 04:11:33 -07:00
64cc965a4a
* Add wiki tiddler attachment support to agent chat Implements the ability to attach wiki tiddlers to agent chat messages. Updates the UI to allow selection of tiddlers from active wiki workspaces, fetches and renders tiddler content as plain text, and appends it to the user message sent to the AI. Includes e2e tests, updates to store actions, service interfaces, and prompt concatenation logic to support this feature. * fix: callback not useCallback cause autocomplete panel flash * Add wiki tiddler attachments to message bubbles Message bubbles now display attached wiki tiddlers as clickable chips, allowing users to navigate directly to the referenced tiddler in the appropriate workspace. Metadata handling and persistence for wiki tiddlers has been updated to include workspaceId, and tests have been added to verify the new UI behavior. The chat view also now closes the TiddlyWiki sidebar for better focus when navigating from a selection. * Support split view navigation for wiki tiddler attachments Adds isSplitView prop to ChatTabContent and related components to distinguish between split view and normal tab modes. Wiki tiddler attachment navigation now uses a different strategy in split view, opening tiddlers directly in the browser view. Updates types and tests to reflect the new behavior, and improves robustness of response handling in several places. * docs: move to .github/instructions/testing.instructions.md * test: view loading slow on mac * refactor(e2e): move wiki load steps to Background in talkWithAI.feature; remove all sidebar close delays and polling, only set state when TiddlyWiki is ready; clean up code and logs for sidebar auto-close in split view * docs: make test inst shorter * lint * refactor(view): slim ViewService, move menu to separate file, orchestrate view logic in WorkspaceViewService, update all callers, fix lint floating promise, all unit and e2e tests pass * fix: add data-testid to attachment listbox for E2E test - Add slotProps to MUI Autocomplete to ensure attachment-listbox is rendered with correct test-id - Fix E2E test timeout when waiting for attachment listbox element * lint * put 'Talk with AI' menu on top and attachment i18n Introduce a reusable createTalkWithAIMenuItems helper to build "Talk with AI" menu entries (default agent + other agents submenu) and integrate it into workspace menu generation. Add new i18n keys for Agent.Attachment and WikiEmbed across locales and update UI to use translation keys (remove hardcoded fallback strings). Improve chat input/attachment behavior: expose a test-id for the attachment listbox, use i18n for labels/placeholders, and tweak input component wiring. Fix Cucumber step handling by normalizing expected newline sequences and safely handling empty message content. Also adjust memo deps in SortableWorkspaceSelectorButton to include id. * feat: enhance AI interaction in workspace context menu with local trigger support * feat: add tool approval and timeout settings - Introduced ToolApprovalConfig and related types for managing tool execution approvals. - Implemented WebFetch and ZxScript tools for fetching web content and executing scripts, respectively. - Added token estimation utilities for context window management. - Enhanced ModelInfo interface with context window size and max output tokens. - Created API Retry Utility for handling transient failures with exponential backoff. - Updated AIAgent preferences section to include Tool Approval & Timeout Settings dialog. - Developed ToolApprovalSettingsDialog for configuring tool-specific approval rules and retry settings. - Modified vitest configuration to support aliasing for easier imports and stubbing. * Refactor agent instance tools and services for improved modularity and maintainability - Extracted type definitions and tool registry from defineTool.ts into separate files (defineToolTypes.ts, toolRegistry.ts) to reduce file size and enhance importability. - Implemented a retry mechanism in ExternalAPIService for stream creation to handle transient failures. - Updated ToolApprovalSettingsDialog to persist settings using localStorage instead of a preference service. - Created agentMessagePersistence.ts and agentRepository.ts to manage agent message and instance CRUD operations, reducing the size of AgentInstanceService. - Added a progress tracker document (AgentTODO.md) for the ongoing enhancement plan of the TidGi Agent. * feat: add AgentSwitcher component for agent definition switching - Implemented AgentSwitcher component with dropdown functionality for selecting agent definitions. - Integrated loading of agent definitions on dropdown open. - Added visual feedback for current selection and disabled state. feat: create ToolResultRenderer for generic tool result messages - Developed ToolResultRenderer to handle rendering of <functions_result> messages. - Included collapsible parameters and result display with error handling. - Added truncation for long results in collapsed view. test: add comprehensive tests for MessageRenderer components - Implemented tests for AskQuestionRenderer, ToolResultRenderer, ToolApprovalRenderer, and BaseMessageRenderer. - Ensured proper rendering and functionality for various message types and states. - Included pattern routing tests for MessageRenderer. feat: introduce TurnActionBar for action management in agent turns - Created TurnActionBar component for managing actions like rollback, retry, delete, and copy. - Integrated visual feedback for file changes and rollback status. - Added functionality for copying agent responses and full conversation to clipboard. feat: implement askQuestionPending for managing user responses - Developed infrastructure for handling pending ask-question requests. - Implemented promise-based blocking until user responds to agent questions. - Added timeout handling for ask-question requests. * feat: Implement background task management for agent instances - Added functionality to restore heartbeat timers and alarms for active agents upon service initialization. - Introduced methods to retrieve active background tasks and cancel them via the UI. - Enhanced alarm clock tool to persist alarm data in the database, ensuring alarms survive app restarts. - Updated agent instance schema to include scheduled alarm data. - Modified prompt concatenation logic to support context window size for message history. - Removed system prompt parameter from model parameters schema and related components. - Improved UI to display and manage background tasks, including heartbeat and alarm details. * feat: Implement Scheduled Tasks Management and Background Task Settings - Add feature for managing scheduled tasks for agents, including viewing, adding, and editing tasks. - Create tests for agent repository and background task settings APIs. - Introduce ScheduledTaskManager for unified scheduling of tasks with interval, at, and cron schedules. - Implement edit-agent-definition tool for modifying agent configurations, including heartbeat and prompt settings. - Ensure tasks persist across app restarts and respect active hours filtering. * Update wiki * fix(security): harden htmlToText against XSS via encoded tags - Use tolerant script/style regex that handles </script > with spaces - Stop decoding </> entities to prevent reintroducing HTML tags - Decode & last to avoid double-unescaping (&lt; < <) - Fixes all 4 CodeQL findings (bad filtering, incomplete sanitization, double escaping, incomplete multi-character sanitization) * fix: lint and format errors (eslint naming, dprint formatting, stub classes) * fix: exclude tidgi.config.json from template copy and fix log marker pattern - Skip tidgi.config.json when copying wiki template to prevent overriding workspace name - Change waitForLogMarker default pattern from 'wiki-' to '*' to match actual log filenames - Filter tidgi.config.json in e2e step too (fs.copy in wiki creation step) * perf(e2e): merge 5 scheduledTask scenarios into 2 to reduce app restarts * perf(e2e): merge crossWindowSync and streamingStatus scenarios to reduce CI time * ci: increase test timeout to 20min for larger e2e scenario count * perf(e2e): merge agent scenarios and enable parallel on CI - Merge agent.feature wiki-search + wiki-operation into one scenario - Merge agent.feature create-agent-from-newtab + create-agent-from-fallback into one - Enable cucumber parallel: 2 on CI (7GB RAM, dynamic ports for mock servers) - Total scenarios: 66 -> 61 * fix: cleanup MCP client processes when deleting or closing agent * ci: disable parallel (CPU contention), increase timeout to 30min for 61 scenarios * perf(e2e): merge 3 preference background-task scenarios into 1, increase timeout to 45min - Preference alarm/heartbeat CRUD merged into single scenario (saves 2 app restarts) - Total scenarios: 59 (was 66) - CI timeout 45min for the expanded e2e suite * fix: restructure e2e scenarios, fix subscription leak and debounce cleanup - Restructure agent/talkWithAI/streamingStatus feature files for reliability - Fix talkWithAI scenarios missing mock server startup and app launch - Remove duplicate subscription in handleSwitchAgent (useEffect already handles it) - Clean up debounced update functions when agent is deleted/closed - Use agentId:messageId key for debounced functions to enable per-agent cleanup * fix(e2e): remove :last-child selectors broken by TurnActionBar, fix tab/dialog selectors, increase CI timeout to 25min * fix: use const for non-reassigned variable (lint) * fix(e2e): fix close-all-tabs opacity issue, scheduledTask undefined steps, MUI multiline textarea targeting * fix(e2e): use tab-list-dropdown to close all tabs, fix selector for actual TabListDropdown component * fix(e2e): add timing waits for BrowserView repositioning and git log UI refresh * fix(e2e): make 'should not see' step wait for element to disappear instead of instant check * fix(e2e): increase executeInBrowserView default timeout from 500ms to 2000ms
132 lines
10 KiB
Gherkin
132 lines
10 KiB
Gherkin
Feature: Agent Workflow - Tool Usage and Multi-Round Conversation
|
||
As a user
|
||
I want to use an intelligent agent to search wiki content
|
||
So that I can get AI-powered explanations of wiki entries
|
||
|
||
Background:
|
||
Given I add test ai settings
|
||
# Start mock OpenAI server with no rules - rules will be added per scenario
|
||
And I have started the mock OpenAI server without rules
|
||
Then I launch the TidGi application
|
||
And I wait for the page to load completely
|
||
And I should see a "page body" element with selector "body"
|
||
# Navigate to agent workspace for all scenarios
|
||
And I click on "agent workspace button and new tab button" elements with selectors:
|
||
| element description | selector |
|
||
| agent workspace | [data-testid='workspace-agent'] |
|
||
| new tab button | [data-tab-id='new-tab-button'] |
|
||
|
||
@agent @mockOpenAI
|
||
Scenario: Wiki-search tool usage
|
||
# Add scenario-specific responses to the mock server
|
||
Given I add mock OpenAI responses:
|
||
| response | stream |
|
||
| <tool_use name="wiki-search">{"workspaceName":"-VPTqPdNOEZHGO5vkwllY","filter":"[title[Index]]"}</tool_use> | false |
|
||
| 在 TiddlyWiki 中，Index 条目提供了编辑卡片的方法说明，点击右上角的编辑按钮可以开始对当前卡片进行编辑。此外，它还引导您访问中文教程页面和官方英文站点以获取更多信息。 | false |
|
||
# Proceed with agent workflow in main window
|
||
# Step 1: Click new tab button
|
||
When I click on a "new tab button" element with selector "[data-tab-id='new-tab-button']"
|
||
And I should see a "search interface" element with selector ".aa-Autocomplete"
|
||
# Step 2: Click search box and wait for autocomplete
|
||
When I click on a "search input box" element with selector ".aa-Input"
|
||
And I should see an "autocomplete panel" element with selector ".aa-Panel"
|
||
# Step 3: Select agent from autocomplete (not new tab)
|
||
When I click on an "agent suggestion" element with selector '[data-autocomplete-source-id="agentsSource"] .aa-ItemWrapper'
|
||
And I should see a "message input box" element with selector "[data-testid='agent-message-input']"
|
||
# Step 4: Send message to agent - using generic steps combination
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
When I type "搜索 wiki 中的 index 条目并解释" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see 4 messages in chat history
|
||
# Verify the last message contains the AI explanation about Index
|
||
And I should see "explanation in last message and explanation about edit" elements with selectors:
|
||
| element description | selector |
|
||
| explanation in last message | [data-testid='message-bubble']:has-text('Index') |
|
||
| explanation about edit | [data-testid='message-bubble']:has-text('编辑') |
|
||
|
||
@agent @mockOpenAI
|
||
Scenario: Wiki operation
|
||
# Add scenario-specific responses to the mock server
|
||
Given I add mock OpenAI responses:
|
||
| response | stream |
|
||
| 先测试失败情况<tool_use name="wiki-operation">{"workspaceName":"test-expected-to-fail","operation":"wiki-add-tiddler","title":"testNote","text":"test"}</tool_use> | false |
|
||
| 然后测试成功情况<tool_use name="wiki-operation">{"workspaceName":"wiki","operation":"wiki-add-tiddler","title":"test","text":"这是测试内容"}</tool_use>使用启动时自动创建的 wiki 工作区 | false |
|
||
| 已成功在工作区 wiki 中创建条目 "test"。 | false |
|
||
# Step 1: Start a fresh tab and run the two-round wiki operation flow
|
||
When I click on a "new tab button" element with selector "[data-tab-id='new-tab-button']"
|
||
And I should see a "search interface" element with selector ".aa-Autocomplete"
|
||
# Step 2: Click search box and wait for autocomplete
|
||
When I click on a "search input box" element with selector ".aa-Input"
|
||
And I should see an "autocomplete panel" element with selector ".aa-Panel"
|
||
# Step 3: Select agent from autocomplete (not new tab)
|
||
When I click on an "agent suggestion" element with selector '[data-autocomplete-source-id="agentsSource"] .aa-ItemWrapper'
|
||
And I should see a "message input box" element with selector "[data-testid='agent-message-input']"
|
||
# First round: try create note using test-expected-to-fail workspace (expected to fail)
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
When I type "在 wiki 里创建一个新笔记，内容为 test" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see 6 messages in chat history
|
||
# Verify error and success messages
|
||
And I should see "workspace not exist error and success in last message and wiki workspace in last message" elements with selectors:
|
||
| element description | selector |
|
||
| workspace not exist error | [data-testid='message-bubble']:has-text('test-expected-to-fail'):has-text('不存在') |
|
||
| success in last message | [data-testid='message-bubble']:has-text('已成功') |
|
||
| wiki workspace in last message | [data-testid='message-bubble']:has-text('wiki') |
|
||
|
||
@agent
|
||
Scenario: Create default agent from New Tab quick access
|
||
When I click on "new tab button and create default agent button" elements with selectors:
|
||
| element description | selector |
|
||
| new tab button | [data-tab-id='new-tab-button'] |
|
||
| create default agent button | [data-testid='create-default-agent-button'] |
|
||
And I should see a "message input box" element with selector "[data-testid='agent-message-input']"
|
||
|
||
@agent
|
||
Scenario: Close all tabs then create default agent from fallback page
|
||
# Ensure starting from black/fallback page with no open tabs
|
||
# Open tab list dropdown and force-click all close buttons (they have opacity: 0)
|
||
Given I click on a "tab list button" element with selector "[data-testid='tab-list-button']"
|
||
And I should see a "tab list dropdown" element with selector "[data-testid='tab-list-dropdown']"
|
||
When I click all "tab close button" elements matching selector "[data-testid^='tab-close-']"
|
||
# When there is no active tab, this is "fallback new tab", it has same thing as new tab.
|
||
And I should see "new tab button and Create Default Agent" elements with selectors:
|
||
| element description | selector |
|
||
| new tab button | [data-tab-id='new-tab-button'] |
|
||
| Create Default Agent | [data-testid='create-default-agent-button'] |
|
||
When I click on a "new tab button" element with selector "[data-tab-id='new-tab-button']"
|
||
And I should see a "Create Default Agent" element with selector "[data-testid='create-default-agent-button']"
|
||
When I click on a "create default agent button" element with selector "[data-testid='create-default-agent-button']"
|
||
And I should see a "message input box" element with selector "[data-testid='agent-message-input']"
|
||
# Open dropdown again and close all tabs
|
||
When I click on a "tab list button" element with selector "[data-testid='tab-list-button']"
|
||
And I should see a "tab list dropdown" element with selector "[data-testid='tab-list-dropdown']"
|
||
Then I click all "tab close button" elements matching selector "[data-testid^='tab-close-']"
|
||
|
||
@agent @mockOpenAI
|
||
Scenario: Streamed assistant response can be cancelled mid-stream and send button returns
|
||
# Add scenario-specific responses to the mock server
|
||
Given I add mock OpenAI responses:
|
||
| response | stream |
|
||
| partial_chunk_1<stream_split>partial_chunk_2<stream_split>partial_chunk_3<stream_split>partial_chunk_4 | true |
|
||
And I click on "new tab button and create default agent button" elements with selectors:
|
||
| element description | selector |
|
||
| new tab button | [data-tab-id='new-tab-button'] |
|
||
| create default agent button | [data-testid='create-default-agent-button'] |
|
||
And I should see a "message input box" element with selector "[data-testid='agent-message-input']"
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
When I type "Start long streaming" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
# Wait for streaming container to appear and contain the first chunk
|
||
Then I should see "assistant streaming container and partial assistant text and cancel icon" elements with selectors:
|
||
| element description | selector |
|
||
| assistant streaming container | [data-testid='assistant-streaming-text'] |
|
||
| partial assistant text | *:has-text('partial_chunk_1') |
|
||
| cancel icon | [data-testid='cancel-icon'] |
|
||
# Click cancel button mid-stream
|
||
When I click on a "cancel button" element with selector "[data-testid='agent-send-button']"
|
||
# Verify send button returned and stream stopped (no further chunks)
|
||
Then I should see "send icon and send button" elements with selectors:
|
||
| element description | selector |
|
||
| send icon | [data-testid='send-icon'] |
|
||
| send button | [data-testid='agent-send-button']|
|
||
And I should not see a "partial chunk 4 text" element with selector "text='partial_chunk_4'"
|