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
140 lines
13 KiB
Gherkin
140 lines
13 KiB
Gherkin
Feature: Agent Tools - Ask-question variants and turn action bar
|
||
As a user
|
||
I want agent tools to render correctly and respond to interaction
|
||
So that I can interact with the AI agent through various tool UIs
|
||
|
||
Background:
|
||
Given I add test ai settings
|
||
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"
|
||
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'] |
|
||
|
||
@agentTool @mockOpenAI
|
||
Scenario: Ask-question — single-select, multi-select, and text input in one session
|
||
# All 6 mock responses are queued in FIFO order; each ask-question consumes 2
|
||
Given I add mock OpenAI responses:
|
||
| response | stream |
|
||
| <tool_use name="ask-question">{"question":"Which approach do you prefer?","inputType":"single-select","options":[{"label":"Approach A: Create separate tiddlers for each topic and link them","description":"This keeps content modular and easy to navigate"},{"label":"Approach B: Create one large tiddler with sections","description":"Simpler structure, all information in one place"}],"allowFreeform":true}</tool_use> | false |
|
||
| 好的，你选择了方法A。我将为每个主题创建独立的tiddler并链接它们。 | false |
|
||
| <tool_use name="ask-question">{"question":"Which tags should I add to the new tiddler?","inputType":"multi-select","options":[{"label":"AI","description":"Artificial Intelligence"},{"label":"Programming","description":"Software development"},{"label":"Notes","description":"Personal notes"}],"allowFreeform":false}</tool_use> | false |
|
||
| 好的，我将为tiddler添加 AI, Programming 两个标签。 | false |
|
||
| <tool_use name="ask-question">{"question":"What title should the new tiddler have?","inputType":"text","allowFreeform":true}</tool_use> | false |
|
||
| 好的，我将创建标题为"My Custom Title"的tiddler。 | false |
|
||
# Create agent
|
||
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']"
|
||
# ── Part 1: single-select ──
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "帮我整理笔记" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see an "ask question container" element with selector "[data-testid='ask-question-container']"
|
||
And I should see "question text and two full-width options" elements with selectors:
|
||
| element description | selector |
|
||
| question text | *:has-text('Which approach do you prefer?') |
|
||
| option A | [data-testid='ask-question-option-0']:has-text('Approach A') |
|
||
| option B | [data-testid='ask-question-option-1']:has-text('Approach B') |
|
||
And I should not see a "raw tool use xml" element with selector "*:has-text('<tool_use')"
|
||
When I click on a "option A button" element with selector "[data-testid='ask-question-option-0']"
|
||
Then I should see an "agent response" element with selector "[data-testid='message-bubble']:has-text('方法A')"
|
||
# ── Part 2: multi-select ──
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "创建一个笔记并添加标签" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see an "ask question container" element with selector "[data-testid='ask-question-container']:has-text('Which tags')"
|
||
And I should see "multi-select options" elements with selectors:
|
||
| element description | selector |
|
||
| option AI | [data-testid='ask-question-option-0']:has-text('AI') |
|
||
| option Programming | [data-testid='ask-question-option-1']:has-text('Programming') |
|
||
| option Notes | [data-testid='ask-question-option-2']:has-text('Notes') |
|
||
When I click on a "AI checkbox" element with selector "[data-testid='ask-question-option-0']"
|
||
And I click on a "Programming checkbox" element with selector "[data-testid='ask-question-option-1']"
|
||
Then I should see a "submit button" element with selector "[data-testid='ask-question-multiselect-submit']"
|
||
When I click on a "submit button" element with selector "[data-testid='ask-question-multiselect-submit']"
|
||
Then I should see an "agent response" element with selector "[data-testid='message-bubble']:has-text('AI')"
|
||
# ── Part 3: text freeform ──
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "创建一个自定义标题的笔记" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see an "ask question container" element with selector "[data-testid='ask-question-container']:has-text('What title')"
|
||
And I should see "freeform input" elements with selectors:
|
||
| element description | selector |
|
||
| text input | [data-testid='ask-question-text-input'] |
|
||
| submit button | [data-testid='ask-question-submit'] |
|
||
When I type "My Custom Title" in "freeform input" element with selector "[data-testid='ask-question-text-input'] textarea:not([readonly])"
|
||
And I click on a "submit button" element with selector "[data-testid='ask-question-submit']"
|
||
Then I should see an "agent response" element with selector "[data-testid='message-bubble']:has-text('My Custom Title')"
|
||
|
||
@agentTool @mockOpenAI
|
||
Scenario: Turn action bar — delete, retry, and rollback-hidden in one session
|
||
# Responses consumed in order: delete-target, retry-first, retry-replacement, rollback-check
|
||
Given I add mock OpenAI responses:
|
||
| response | stream |
|
||
| 这是要删除的回复。 | false |
|
||
| 这是第一次回复。 | false |
|
||
| 这是重试后的回复。 | false |
|
||
| 这是纯文本回复，没有工具调用。 | false |
|
||
# Create agent
|
||
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']"
|
||
# ── Part 1: Delete ── (1 turn → 0 turns, selector unambiguous)
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "测试删除功能" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see 2 messages in chat history
|
||
And I should see an "response" element with selector "[data-testid='message-bubble']:has-text('要删除的回复')"
|
||
When I click on a "delete button" element with selector "[data-testid='turn-action-delete']"
|
||
Then I should not see a "deleted response" element with selector "[data-testid='message-bubble']:has-text('要删除的回复')"
|
||
# ── Part 2: Retry ── (0 turns → 1 turn, selector unambiguous)
|
||
# After delete, old text may be in input — select-all then type to replace
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Meta+a" key
|
||
And I type "测试重试功能" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see 2 messages in chat history
|
||
And I should see an "first response" element with selector "[data-testid='message-bubble']:has-text('第一次回复')"
|
||
When I click on a "retry button" element with selector "[data-testid='turn-action-retry']"
|
||
Then I should see 2 messages in chat history
|
||
And I should see an "retried response" element with selector "[data-testid='message-bubble']:has-text('重试后的回复')"
|
||
# ── Part 3: Rollback hidden ── (1 turn → 2 turns, both plain text)
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "简单问题" 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
|
||
And I should not see a "rollback button" element with selector "[data-testid='turn-action-rollback']"
|
||
And I should not see a "files changed chip" element with selector "[data-testid='turn-files-changed']"
|
||
|
||
@agentTool @mockOpenAI
|
||
Scenario: Agent switcher — switch between Task Agent and Plan Agent
|
||
Given I add mock OpenAI responses:
|
||
| response | stream |
|
||
| Task Agent 模式的回复。 | false |
|
||
| Plan Agent 模式的回复。 | false |
|
||
# Create agent (default = Task Agent)
|
||
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']"
|
||
# Verify switcher shows current agent name
|
||
Then I should see an "agent switcher" element with selector "[data-testid='agent-switcher-button']"
|
||
# Send message with Task Agent
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "Task Agent测试" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see an "task agent response" element with selector "[data-testid='message-bubble']:has-text('Task Agent 模式')"
|
||
# Switch to Plan Agent via the switcher dropdown
|
||
When I click on a "agent switcher button" element with selector "[data-testid='agent-switcher-button']"
|
||
Then I should see an "agent switcher dropdown" element with selector "[data-testid='agent-switcher-dropdown']"
|
||
And I should see a "plan agent option" element with selector "[data-testid='agent-switcher-option-plan-agent']"
|
||
When I click on a "plan agent option" element with selector "[data-testid='agent-switcher-option-plan-agent']"
|
||
# After switching, chat history resets (new agent instance), input should be available
|
||
Then I should see a "message input box" element with selector "[data-testid='agent-message-input']"
|
||
# Send message with Plan Agent
|
||
When I click on a "message input textarea" element with selector "[data-testid='agent-message-input']"
|
||
And I type "Plan Agent测试" in "chat input" element with selector "[data-testid='agent-message-input']"
|
||
And I press "Enter" key
|
||
Then I should see an "plan agent response" element with selector "[data-testid='message-bubble']:has-text('Plan Agent 模式')"
|
||
# Verify wiki-operation tool is NOT in system prompt (Plan mode disables it)
|
||
And the last AI request system prompt should not contain "wiki-operation"
|