mirror of
https://github.com/tiddly-gittly/TidGi-Desktop.git
synced 2025-12-05 18:20:39 -08:00
9a6f3480f5
* Add watch-filesystem-adaptor plugin and worker IPC Introduces the watch-filesystem-adaptor TiddlyWiki plugin, enabling tag-based routing of tiddlers to sub-wikis by querying workspace info via worker thread IPC. Adds workerServiceCaller utility for worker-to-main service calls, updates workerAdapter and bindServiceAndProxy to support explicit service registration for workers, and documents the new IPC architecture. Updates wikiWorker and startNodeJSWiki to preload workspace ID and load the new plugin. Also updates the plugin build script to compile and copy the new plugin. * test: wiki operation steps * Add per-wiki labeled logging and console hijack Introduces labeled loggers for each wiki, writing logs to separate files. Adds a logFor method to NativeService for logging with labels, updates interfaces, and hijacks worker thread console methods to redirect logs to main process for wiki-specific logging. Refactors workspaceID usage to workspace object for improved context. * Update log handling for wiki worker and tests Enhanced logging tests to check all log files, including wiki logs. Adjusted logger to write wiki worker logs to the main log directory. Updated e2e app script comment for correct usage. * Enable worker thread access to main process services Introduces a proxy system allowing worker threads to call main process services with full type safety and observable support. Adds worker-side service proxy creation, auto-attaches proxies to global.service, and updates service registration to use IPC descriptors. Documentation is added for usage and architecture. * Update ErrorDuringStart.md * chore: upgrade ipc cat and allow clean vite cache * Refactor wiki worker initialization and service readiness Moved wiki worker implementation from wikiWorker.ts to wikiWorker/index.ts and deleted the old file. Added servicesReady.ts to manage worker service readiness and callbacks, and integrated notifyServicesReady into the worker lifecycle. Updated console hijack logic to wait for service readiness before hijacking. Improved worker management in Wiki service to support detaching workers and notifying readiness. * Refactor wiki logging to use centralized logger Removed per-wiki loggers and console hijacking in favor of a single labeled logger. All wiki logs, including errors, are now written to a unified log file. Updated worker and service code to route logs through the main logger and removed obsolete log file naming and management logic. * fix: ipc cat log error * Refactor wiki test paths and improve file save logic Updated test step to use wikiTestRootPath for directory replacements and added wikiTestRootPath to paths.ts for clarity. Improved error handling and directory logic in watch-filesystem-adaptor.ts, including saving tiddlers directly to sub-wiki folders, more informative logging, and ensuring cleanup after file writes is properly awaited. * rename * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * feat: basic watch-fs * feat: check file not exist * refactor: use exponential-backoff * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * Initial commit when init a new git. * fix: cleanup * Refactor test setup and cleanup to separate file Moved Before and After hooks from application.ts to a new cleanup.ts file for better organization and separation of concerns. Also removed unused imports and related code from application.ts. Minor type simplification in agent.ts for row parsing. * test: modify and rename * feat: enableFileSystemWatch * refactor: unused utils.ts * Update watch-filesystem-adaptor.ts * refactor: use node-sentinel-file-watcher * refactor: extract to two classes * The logFor method lacks JSDoc describing the level parameter's * Update startNodeJSWiki.ts * fix: napi build * Update electron-rebuild command in workflows Changed the electron-rebuild command in release and test GitHub Actions workflows to use a comma-separated list for native modules instead of multiple -w flags. This simplifies the rebuild step for better-sqlite3 and nsfw modules. * lint * not build nsfw, try use prebuild * Update package.json * Update workerAdapter.ts * remove subWikiPlugin.ts as we use new filesystem adaptor that supports tag based sub wiki * fix: build * fix: wrong type * lint * remove `act(...)` warnings * uninstall chokidar * refactor and test * lint * remove unused logic, as we already use ipc syncadaptor, not afriad of wiki status change * Update translation.json * test: increast timeout in CI * Update application.ts * fix: AI's wrong cleanup logic hidden by as unknown as * fix: AI's wrong as unknown as * Update agent.feature * Update wikiSearchPlugin.ts * fix: A dynamic import callback was not specified.
114 lines
8.8 KiB
Gherkin
114 lines
8.8 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
|
||
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"
|
||
# Ensure we are in the correct workspace before each scenario to avoid wrong starting state
|
||
And I click on "agent workspace button and new tab button" elements with selectors:
|
||
| [data-testid='workspace-agent'] |
|
||
| [data-tab-id='new-tab-button'] |
|
||
|
||
@agent @mockOpenAI
|
||
Scenario: Wiki-search tool usage
|
||
Given I have started the mock OpenAI server
|
||
| 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:
|
||
| [data-testid='message-bubble']:last-child:has-text('Index') |
|
||
| [data-testid='message-bubble']:last-child:has-text('编辑') |
|
||
|
||
@agent @mockOpenAI
|
||
Scenario: Wiki operation
|
||
Given I have started the mock OpenAI server
|
||
| 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 there's an error message about workspace not found (in one of the middle messages)
|
||
And I should see a "workspace not exist error" element with selector "[data-testid='message-bubble']:has-text('test-expected-to-fail'):has-text('不存在')"
|
||
# Verify the last message contains success confirmation
|
||
And I should see "success in last message and wiki workspace in last message" elements with selectors:
|
||
| [data-testid='message-bubble']:last-child:has-text('已成功') |
|
||
| [data-testid='message-bubble']:last-child: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:
|
||
| [data-tab-id='new-tab-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
|
||
Given I click on a "new tab button" element with selector "[data-tab-id='new-tab-button']"
|
||
When I click all "tab" elements matching selector "[data-testid='tab']"
|
||
When I click all "close tab button" elements matching selector "[data-testid='tab-close-button']"
|
||
And I should see a "new tab button" element with selector "[data-tab-id='new-tab-button']"
|
||
# When there is no active tab, this is "fallback new tab", it has same thing as new tab.
|
||
And I should see a "Create Default Agent" element with selector "[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']"
|
||
Then I click all "close tab button" elements matching selector "[data-testid='tab-close-button']"
|
||
|
||
@agent @mockOpenAI
|
||
Scenario: Streamed assistant response can be cancelled mid-stream and send button returns
|
||
Given I have started the mock OpenAI server
|
||
| 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:
|
||
| [data-tab-id='new-tab-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:
|
||
| [data-testid='assistant-streaming-text'] |
|
||
| *:has-text('partial_chunk_1') |
|
||
| [data-testid='cancel-icon'] |
|
||
# Click cancel button mid-stream
|
||
When I click on a "cancel button" element with selector "[data-testid='agent-send-button']"
|
||
And I should see a "send icon" element with selector "[data-testid='send-icon']"
|
||
# Verify send button returned and stream stopped (no further chunks)
|
||
Then I should see a "send button" element with selector "[data-testid='agent-send-button']"
|
||
And I should not see a "partial chunk 4 text" element with selector "text='partial_chunk_4'"
|