-
Notifications
You must be signed in to change notification settings - Fork 348
feat(thought-stream): interleave tool calls with reasoning on one timeline #1433
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
pedramamini
wants to merge
1
commit into
rc
Choose a base branch
from
feat/1312-tool-activity-timeline
base: rc
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
201 changes: 201 additions & 0 deletions
201
src/__tests__/renderer/hooks/agent/internal/useThoughtStreamToolListener.test.tsx
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,201 @@ | ||
| /** | ||
| * useThoughtStreamToolListener tests | ||
| * | ||
| * The action half of the Thought Stream. What matters here: | ||
| * - Auto Run `-batch-` tool calls ARE captured (the in-chat transcript listener | ||
| * matches `REGEX_AI_TAB` only, so an Auto Run has no other surface at all). | ||
| * - Interactive `-ai-` tool calls are NOT (same scoping as the thinking | ||
| * listener; capturing them is what once made the panel show ordinary chat). | ||
| * - Provider status wording normalizes onto running/completed/failed. | ||
| * - A completion merges into its start rather than appending a second row. | ||
| */ | ||
| import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest'; | ||
| import { renderHook, act } from '@testing-library/react'; | ||
| import { useThoughtStreamToolListener } from '../../../../../renderer/hooks/agent/internal/useThoughtStreamToolListener'; | ||
| import { | ||
| useThoughtStreamStore, | ||
| isToolEvent, | ||
| type ToolActivityEntry, | ||
| } from '../../../../../renderer/stores/thoughtStreamStore'; | ||
|
|
||
| type ToolHandler = ( | ||
| sessionId: string, | ||
| toolEvent: { toolName: string; state?: unknown; timestamp: number; toolCallId?: string } | ||
| ) => void; | ||
|
|
||
| let toolHandler: ToolHandler | undefined; | ||
| const mockUnsubscribe = vi.fn(); | ||
|
|
||
| const SESSION_ID = 'session-abc'; | ||
| const BATCH = `${SESSION_ID}-batch-1700000000000`; | ||
|
|
||
| /** Tool events for a session, in timeline order. */ | ||
| function toolEvents(sessionId = SESSION_ID): ToolActivityEntry[] { | ||
| const entries = useThoughtStreamStore.getState().buffers[sessionId]?.entries ?? []; | ||
| return entries.filter(isToolEvent); | ||
| } | ||
|
|
||
| beforeEach(() => { | ||
| vi.clearAllMocks(); | ||
| toolHandler = undefined; | ||
|
|
||
| (window as any).maestro = { | ||
| ...((window as any).maestro || {}), | ||
| process: { | ||
| ...((window as any).maestro?.process || {}), | ||
| onToolExecution: vi.fn((h: ToolHandler) => { | ||
| toolHandler = h; | ||
| return mockUnsubscribe; | ||
| }), | ||
| }, | ||
| }; | ||
|
|
||
| useThoughtStreamStore.setState({ panelSessionId: null, buffers: {} }); | ||
| }); | ||
|
|
||
| afterEach(() => { | ||
| vi.unstubAllGlobals(); | ||
| }); | ||
|
|
||
| describe('useThoughtStreamToolListener', () => { | ||
| it('captures Auto Run tool calls despite the `-batch-` streaming id', () => { | ||
| // The gap this feature exists to close: `useAgentToolExecutionListener` | ||
| // matches REGEX_AI_TAB, so during an Auto Run every tool call was dropped | ||
| // and no surface anywhere showed what the agent was doing. | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(BATCH, { | ||
| toolName: 'Bash', | ||
| state: { status: 'running', input: { command: 'npm test' } }, | ||
| timestamp: 1000, | ||
| }); | ||
| }); | ||
|
|
||
| const events = toolEvents(); | ||
| expect(events).toHaveLength(1); | ||
| expect(events[0].tool.name).toBe('Bash'); | ||
| expect(events[0].tool.label).toEqual({ verb: 'Ran', target: 'npm test' }); | ||
| expect(events[0].tool.status).toBe('running'); | ||
| }); | ||
|
|
||
| it('does not capture interactive `-ai-` tab tool calls', () => { | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(`${SESSION_ID}-ai-tab1`, { | ||
| toolName: 'Read', | ||
| state: { status: 'completed', input: { file_path: '/tmp/a.ts' } }, | ||
| timestamp: 1000, | ||
| }); | ||
| }); | ||
|
|
||
| expect(useThoughtStreamStore.getState().buffers[SESSION_ID]).toBeUndefined(); | ||
| }); | ||
|
|
||
| it('does not capture synopsis spawns', () => { | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(`${SESSION_ID}-synopsis-1700000000000`, { | ||
| toolName: 'Read', | ||
| state: { status: 'completed' }, | ||
| timestamp: 1000, | ||
| }); | ||
| }); | ||
|
|
||
| expect(useThoughtStreamStore.getState().buffers[SESSION_ID]).toBeUndefined(); | ||
| }); | ||
|
|
||
| it('merges a completion into the call it started, keeping one row', () => { | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(BATCH, { | ||
| toolName: 'Bash', | ||
| state: { status: 'running', input: { command: 'npm test' } }, | ||
| timestamp: 1000, | ||
| toolCallId: 'call-1', | ||
| }); | ||
| toolHandler?.(BATCH, { | ||
| toolName: 'Bash', | ||
| state: { status: 'completed' }, | ||
| timestamp: 8000, | ||
| toolCallId: 'call-1', | ||
| }); | ||
| }); | ||
|
|
||
| const events = toolEvents(); | ||
| expect(events).toHaveLength(1); | ||
| expect(events[0].tool.status).toBe('completed'); | ||
| // The row keeps its START time so it does not jump position on finishing. | ||
| expect(events[0].timestamp).toBe(1000); | ||
| expect(events[0].tool.endedAt).toBe(8000); | ||
| }); | ||
|
|
||
| it('normalizes `error` onto `failed`', () => { | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(BATCH, { | ||
| toolName: 'Bash', | ||
| state: { status: 'error' }, | ||
| timestamp: 1000, | ||
| }); | ||
| }); | ||
|
|
||
| expect(toolEvents()[0].tool.status).toBe('failed'); | ||
| }); | ||
|
|
||
| it('treats a missing status as still running', () => { | ||
| // An unfinished call is the reading that cannot mislead: it resolves | ||
| // itself the moment a completion arrives. | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(BATCH, { toolName: 'Bash', timestamp: 1000 }); | ||
| }); | ||
|
|
||
| expect(toolEvents()[0].tool.status).toBe('running'); | ||
| }); | ||
|
|
||
| it('interleaves with reasoning on ONE timeline, in arrival order', () => { | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
| const { appendThought } = useThoughtStreamStore.getState(); | ||
|
|
||
| act(() => { | ||
| appendThought(SESSION_ID, BATCH, 'let me check the tests '); | ||
| toolHandler?.(BATCH, { | ||
| toolName: 'Bash', | ||
| state: { status: 'completed', input: { command: 'npm test' } }, | ||
| timestamp: 2000, | ||
| }); | ||
| appendThought(SESSION_ID, BATCH, 'they passed'); | ||
| }); | ||
|
|
||
| const entries = useThoughtStreamStore.getState().buffers[SESSION_ID].entries; | ||
| expect(entries.map(isToolEvent)).toEqual([false, true, false]); | ||
| }); | ||
|
|
||
| it('keeps parallel runs in their own buffers', () => { | ||
| renderHook(() => useThoughtStreamToolListener()); | ||
|
|
||
| act(() => { | ||
| toolHandler?.(BATCH, { toolName: 'Bash', state: { status: 'running' }, timestamp: 1 }); | ||
| toolHandler?.('other-session-batch-1700000000000', { | ||
| toolName: 'Read', | ||
| state: { status: 'running' }, | ||
| timestamp: 2, | ||
| }); | ||
| }); | ||
|
|
||
| expect(toolEvents().map((e) => e.tool.name)).toEqual(['Bash']); | ||
| expect(toolEvents('other-session').map((e) => e.tool.name)).toEqual(['Read']); | ||
| }); | ||
|
|
||
| it('unsubscribes on unmount', () => { | ||
| const { unmount } = renderHook(() => useThoughtStreamToolListener()); | ||
| act(() => unmount()); | ||
| expect(mockUnsubscribe).toHaveBeenCalled(); | ||
| }); | ||
| }); |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Add a language identifier to the fenced block.
The opening fence at Line 202 has no language. Markdownlint reports MD040 for this changed block. Use
textto keep the documentation lint-clean.Proposed fix
📝 Committable suggestion
🧰 Tools
🪛 markdownlint-cli2 (0.23.2)
[warning] 202-202: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Source: Linters/SAST tools