- Add AssessmentBadge component with hover tooltips explaining thresholds
- Add Key Takeaways summary section surfacing top actionable findings
- Add cost attribution stacked bar and per-token calculation breakdowns
- Add clickable navigation from takeaways and tool errors to detail sections
- Add theme-aware assessment colors via CSS variables for light/dark mode
- Collapse lower-priority sections by default for progressive disclosure
- Replace all hardcoded color hex values with CSS variable references
- Fix missing Fragment key in CostSection model table
- Add defensive division-by-zero guard in stacked bar calculation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add interpretive assessment layer to session reports. Every metric section
now shows color-coded severity badges (green/amber/red) computed from
configurable thresholds, replacing raw numbers with instant signal.
Includes centralized reportAssessments utility, model mismatch detection,
switch pattern recognition, and 44 new tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add 7 missing sections and fix 4 incomplete ones that the Python
analyzer generates but the TypeScript port was missing:
New sections: skillsInvoked, bashCommands, lifecycleTasks,
userQuestions, outOfScopeFindings, agentTree, subagentsList
Fixed: compaction (was just count, now has summaryCount + note),
serviceTiers removed (not available in parsed types),
compactionCount replaced with compaction object
Adds InsightsSection UI component and 8 new tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added SearchTextCache for LRU caching of extracted search text with mtime invalidation.
- Introduced SearchTextExtractor for lightweight extraction of searchable text from session messages.
- Updated SessionSearcher to utilize the new extractor and cache for improved search performance.
- Added tests for SearchTextCache and SearchTextExtractor to ensure functionality and correctness.
Subagent badges now show distinct colors instead of generic gray.
Colors are resolved from the project's .claude/agents/*.md frontmatter
(color field), with deterministic hash-based fallback for unconfigured types.
New AgentConfigReader service reads agent definitions via IPC, cached
per project root to avoid redundant disk reads on session refreshes.
Team member colors remain unaffected (team branch has priority).
Add an export button to the TabBar header that lets users export
the current session as Markdown, JSON, or Plain Text. The button
appears between Search and Notifications, only for session tabs.
- sessionExporter.ts: formatters for all three formats + download trigger
- ExportDropdown.tsx: dropdown UI component with format selection
- TabBar.tsx: integration with conditional rendering for session tabs
- 51 new tests covering all formatters, edge cases, and download
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sessions without the cwd field (older JSONL format) were creating a
separate subproject group, even when all sessions with cwd shared the
same value. The orphan subproject got a relative fallback path that
failed git identity resolution, causing zero sessions to load on select.
Now only counts distinct real cwds when deciding whether to split,
treating cwd-less sessions as belonging to the same project.
- Updated `markAllNotificationsRead` and `clearNotifications` functions to support optional filtering by trigger name, allowing for more granular control over notification management.
- Adjusted the `NotificationsView` component to reflect the new scoped functionality, including updates to button labels and unread count displays based on active filters.
- Added tests to verify the behavior of scoped actions for marking notifications as read and clearing notifications.
User messages in subagent JSONLs lack the isMeta field, defaulting to false.
An unconditional `continue` in the !isMeta branch skipped tool result
collection for these messages, causing all subagent tools to show
"No result received". Now we check for tool_result blocks before continuing,
allowing them to fall through to the result collection logic.
- Added logic to await the first main-thread assistant message after a UserGroup to accurately count AIGroup messages.
- Updated tests to reflect the new message counting behavior, ensuring correct results in session file analysis.
- Implemented a new IPC handler to find Windows UNC paths for WSL Claude root candidates.
- Introduced utility functions to list WSL distributions and resolve their home paths.
- Updated the configuration handlers to include the new functionality for detecting WSL Claude roots.
- Enhanced the UI to allow users to select WSL Claude root paths, including handling cases where the projects directory is missing.
- Refactored related components to integrate the new WSL functionality seamlessly.
- Introduced functionality to select and manage the local Claude root folder, allowing users to specify a custom path.
- Added IPC handlers for selecting the Claude root folder and retrieving its information.
- Enhanced configuration validation to ensure the specified Claude root path is an absolute path.
- Updated the ServiceContext to reconfigure based on changes to the Claude root path, improving context management.
- Refactored related components to support the new Claude root path features, including updates to the UI and state management.
- Wrapped the cleanup of the temporary directory in a try-finally block to ensure it executes even if an error occurs during the test.
- Added retry logic to the directory removal process to handle potential ENOTEMPTY errors on Windows, enhancing test reliability.
This commit enhances the robustness of the test by ensuring proper cleanup and error handling.
- Enhanced the decodePath and isValidEncodedPath functions to handle legacy Windows format, allowing paths like "C--Users-name-project" to be correctly decoded and validated.
- Updated tests to cover the new legacy format, ensuring proper functionality and validation.
This commit improves compatibility with legacy path formats, enhancing the utility of the path decoder.
- Updated the README to reflect new features in Claude Code, including the ability to spawn subagents via the Task tool and coordinate teams with improved visibility.
- Added details on the rendering of subagent sessions as expandable inline cards, including execution traces, metrics, and tool calls.
- Enhanced description of teammate messages, highlighting color-coded cards and team lifecycle visibility.
- Clarified session summary metrics to differentiate between teammate and subagent counts for better user insights.
This commit significantly improves the documentation of team and subagent visualization features, providing users with a clearer understanding of the capabilities and enhancements in the application.
- Add getFileSystemProvider() getter to ProjectScanner
- Update SessionParser.parseSessionFile() to pass provider to parseJsonlFile()
- Update SessionParser.parseSubagentFile() to pass provider to parseJsonlFile()
- Update SubagentResolver.parseSubagentFile() to pass provider to parseJsonlFile()
- Update SessionParser test mock to include getFileSystemProvider method
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Added notarization team ID configuration for macOS builds.
- Corrected expected output in pathDecoder tests to reflect accurate project name extraction.
- Simplified the CI workflow by consolidating the validate job to run only on Ubuntu.
- Introduced a new test job that runs on both Ubuntu and Windows, including steps for dependency installation and testing.
- Updated the release workflow to directly publish macOS and Windows packages without intermediate artifact uploads.
- Improved the test cleanup process to include a delay and enhanced error handling for file removal on Windows.
- Added notarization configuration for macOS builds to support app distribution.
- Updated CI workflow to run on Ubuntu instead of macOS for improved compatibility.
- Modified test cleanup process to include retry logic for file removal.
- Refactored path handling in tests to use path.join for better cross-platform compatibility.
