| Files | Last commit | Last update |
|---|---|---|
feat(i18n): carry main-process provider-auth errors as codes, not Chinese prose The five remaining Chinese-only strings all live in the main process, where there is no interface language to read: resolveAuthForConfig only ever sees an LLMConfig, and the two OpenAI OAuth sites fire from server.once("error") and a setTimeout callback with no request context at all. So the main process throws a reason code and the renderer turns it into words at the display site — the same shape securityReasonText.ts uses for ExecutionReason. The code rides inside Error.message because it has to cross five different IPC shapes and three of them drop a custom code field: healthCheck:testModel returns {success, error}, llm:generateObject rejects and Electron stringifies only the message, and credentials:oauth:login does send code but the preload return type omits it. The message is the one thing all five deliver verbatim. mapAISDKError needed a guard: its keyword fallback lowercases the message and matches includes("timeout"), which oauthLoginTimeout satisfies — after which toAppError swaps the whole message for "Request timed out" and the code is gone before the renderer sees it. That fallback exists for unstructured messages, so it now steps aside for structured ones. The new test walks every code through toAppError rather than restating the keyword list, so a future ...Network or ...Fetch code cannot reintroduce this quietly. With this, the Chinese-only guard in noInlineBilingual reaches zero. | 2 months ago | |
feat: Exclude test files from quoted literals collection in locale parity tests | 2 months ago | |
feat: add hasAsciiControlCharacters utility and integrate it into file path validation | 2 months ago | |
feat: Refactor session storage and persistence mechanisms - Introduced BufferedCommitQueue for efficient commit handling. - Updated workspaceLoadService to hydrate thread messages and branches more effectively. - Replaced adnifyDirService with workspaceFileRepository in workspaceStateRepository and workspaceStorageRuntime. - Modified workspaceStateService to stage workspace state persistence. - Enhanced shellRegistryService to integrate with persistenceCoordinator. - Added new session persistence types and interfaces for better type safety. - Implemented tests for agentSessionRepository and BufferedCommitQueue. - Removed outdated sessionDataLossGuards and sessionFileStore tests. - Added SQLite session store tests to ensure data integrity and migration handling. - Updated Vite configuration to include sessionStorage.worker for better build management. | 3 months ago | |
refactor: enhance tool routing and semantic navigation logic - Updated prompt templates to clarify tool usage guidelines and improve batch operations. - Refactored tool executors to include compact agent symbols and adjust symbol depth handling. - Removed redundant semantic navigation checks from LoopDetector and introduced ToolRoutingAdvisor for better routing advice. - Added comprehensive tests for ToolRoutingAdvisor to ensure correct routing suggestions and behavior. - Improved read file utilities to handle multiple file paths more effectively and normalize input arguments. - Updated localization files to include new routing feedback messages and suggestions. - Removed outdated tests related to semantic navigation in LoopDetector and added new tests for routing advisor functionality. | 2 months ago | |
feat: enhance URL validation in asset capability and update related tests | 2 months ago | |
feat(dojo): add read-only mentor mode with restricted tool access | 30 days ago | |
fix(git): batch discard changes safely | 2 months ago | |
feat(java): add support for Java language with Eclipse JDT LS integration | 2 months ago | |
refactor(json): one escape-aware JSON scanner and one tool-call markup vocabulary Streamed tool-call arguments are incomplete JSON by nature, so the same two questions ('where does this brace close', 'what closers are missing') were answered by four hand-written scan loops plus a naive regex counter inside experimental_repairToolCall. That counter knew nothing about strings or escapes: {"path":"a}b"} was judged short one brace, and it appended closers per bracket type rather than in stack order, so [{"a":1 was repaired into [{"a":1]} — balanced by count, still unparseable. - shared/utils/jsonScan: scanJson / findJsonValueEnd / sliceJsonValue / closeUnterminatedJson, used by the main-process adapter, the renderer argument parser and the tool-call repair path. - shared/utils/toolCallMarkup: the leaked-markup tag list both sides share, with the JSON-payload subset the main-process adapter converts spelled out next to the full list the renderer strips, so the split is documented instead of implied. - Deleted three unreferenced modules: renderer/utils/partialJson.ts, its test (named *.test.run.ts, so it never matched the vitest glob and reimplemented the function under test anyway), and shared/utils/jsonUtils.ts (375 lines, no importers outside the barrel). 19 new scanner tests. | 2 months ago | |
perf(streaming): replace the IPC debounce with one shared leading-edge throttle The main-process sendEvent coalescer was a debounce, not a throttle: every appended event cleared and rescheduled the 30ms timer, so a continuous token stream was postponed until the stream ended and then arrived in one burst. The PTY batcher in secureTerminal.ts had the same defect in the other direction - its comment claimed "first chunk is delivered immediately" while the code was trailing-edge, making the first chunk wait a full 16ms. Extract one keyed leading-edge throttle with accumulation into src/shared/utils/keyedLeadingEdgeThrottle.ts and use it in both places. The existing generic throttle() in debounce.ts cannot be reused for streams because it keeps only the last call's arguments, which would drop tokens; accumulate is what makes it stream-safe. Three invariants are pinned by tests/shared/keyedLeadingEdgeThrottle.test.ts: first chunk has zero latency, a scheduled window is never postponed by later pushes, and an empty window resets the key so the first chunk after a pause is again immediate. flush keeps the ordering guarantee for tool-boundary events; release drops pending data without emitting. This also removes the per-request entry leak: the old eventBuffer/flushTimers maps were only pruned inside flushEvents, so abort and error paths left entries behind. Idle windows now delete the key themselves. Main bounds IPC frequency (16ms); the renderer's StreamingBuffer remains the sole authority on visual pacing (33ms, aligned to rAF). The golden test's four affected assertions were updated deliberately - the leading edge means the first buffered event now ships in its own envelope. The recorded-debounce case is replaced by two positive pacing cases: sparse tokens each ship immediately, and a token stream denser than the window coalesces into 16ms batches instead of growing without bound. | 2 months ago | |
feat: implement LSP text edits and agent symbol handling - Add textEdits.ts for applying LSP text edits and collecting workspace edits. - Introduce AgentSymbol interface in types/index.ts for agent-facing symbol descriptors. - Create tests for buildSubAgentExecutionSteps to validate execution states and tool handling. - Add tests for parseSymbolToolResult to ensure correct extraction of symbol paths and locations. - Enhance document read tools tests to cover new LSP functionalities and symbol searching. - Implement loop detection tests for semantic navigation and document reading. - Establish integration tests for LSP bundled servers to verify symbol retrieval. - Create tests for document ownership management in the main process. - Add LSP protocol helper tests to validate JSON-RPC interactions. - Implement server routing tests for LSP project configurations. - Add tests for agent symbols to ensure correct symbol pathing and extraction. - Validate language support contract for LSP routing and extensions. - Create tests for LSP text edits to ensure correct application and error handling. | 2 months ago | |
feat: enhance AI attribution and session file management - Introduced caching for commit reports in AiAttributionService to optimize read operations. - Improved session file handling in SessionFileStore with concurrent read and write capabilities. - Added utility functions for managing read concurrency and pending operations. - Updated model routing to support multimodal configurations and fallback mechanisms. - Enhanced image reading services with dedicated tests for visual analysis and routing. - Implemented sanitization for tool outputs to ensure clean and safe content delivery. - Added comprehensive tests for new features and existing functionalities across various services. | 3 months ago | |
feat(preview): add local preview probing and webview types - Introduced previewProbe and previewOpenExternal methods in ElectronAPI for local preview functionality. - Created PreviewWebviewElement interface to define the webview element used in the preview panel. - Implemented LocalPreviewOrigin parsing and normalization logic in discovery.ts to handle local URLs. - Added PreviewProbeResult interface to standardize the results of probing local URLs. - Developed tests for the new preview discovery service and session management to ensure functionality. - Enhanced existing tests for the BM25 index and thread hydration logic to improve coverage and reliability. | 3 months ago | |
feat: add Node.js package manager support and enhance task discovery in TerminalPanel | 2 months ago | |
feat: Enhance read_file tool schema to merge path and paths, improving usability - Updated the read_file schema to allow both path and paths to coexist without conflict, treating them as a union. - Implemented logic to normalize input, ensuring that empty paths do not persist and that valid single or multi-file requests are processed correctly. - Added comprehensive tests to cover various scenarios, including regression tests for previously failing cases. - Introduced memory leak detection improvements in PerformanceMonitor, with new thresholds and conditions to avoid false positives during startup. - Added synchronous log flushing in Logger to ensure critical logs are not lost during process exit. - Enhanced AiAttributionService to improve commit analysis and caching of existing notes. | 2 months ago | |
feat(security): enhance workspace trust and approval mechanisms - Added support for language settings in security manager to handle approvals in English and Chinese. - Implemented workspace trust settings allowing dangerous operations without additional approval in trusted workspaces. - Updated security approval requests to include localized reasons for actions. - Enhanced file and terminal command handling to respect workspace trust settings. - Introduced new API methods for handling security approval requests in the renderer. - Improved tests to cover new workspace trust logic and ensure correct behavior for dangerous operations. | 2 months ago | |
feat: implement LSP text edits and agent symbol handling - Add textEdits.ts for applying LSP text edits and collecting workspace edits. - Introduce AgentSymbol interface in types/index.ts for agent-facing symbol descriptors. - Create tests for buildSubAgentExecutionSteps to validate execution states and tool handling. - Add tests for parseSymbolToolResult to ensure correct extraction of symbol paths and locations. - Enhance document read tools tests to cover new LSP functionalities and symbol searching. - Implement loop detection tests for semantic navigation and document reading. - Establish integration tests for LSP bundled servers to verify symbol retrieval. - Create tests for document ownership management in the main process. - Add LSP protocol helper tests to validate JSON-RPC interactions. - Implement server routing tests for LSP project configurations. - Add tests for agent symbols to ensure correct symbol pathing and extraction. - Validate language support contract for LSP routing and extensions. - Create tests for LSP text edits to ensure correct application and error handling. | 2 months ago | |
feat: update ModelSelector and ReasoningParticleSlider components for improved UI and functionality - Enhanced ModelSelector button styles and interactions for better user experience. - Refactored ReasoningParticleSlider to include ergonomic dial arc and improved accessibility features. - Adjusted default agent configuration to disable auto-context by default. - Updated theme management to toggle dark and light classes based on theme type. - Added new tool group 'ask_user' for enhanced interaction capabilities. - Improved tests to validate tool availability for agents and sub-agents. | 1 month ago | |
refactor(agent): centralize tool output bounding; never cut JSON mid-structure Tool results are the only channel that pours arbitrarily large external data into the model context. The bounding logic was scattered across several places that contradicted each other, which left structured results actually broken. Adds shared/utils/toolOutput.ts as the single convergence point: - boundJsonOutput walks a degradation ladder (full -> drop bodies -> drop positions -> counts/names only); every rung is valid JSON and carries a hint telling the model how to recover what was dropped - boundTextOutput keeps the head or tail per the tool's declared signal end, surrogate-pair safe - boundFileExcerpt keeps only the head and reports the next start_line - clampOutputBudget is the sole authority on the budget Fixes: - find_symbol / get_document_symbols / find_references / get_diagnostics / navigate_symbol returned JSON that was sliced head+tail into syntactic wreckage; JSON.parse failed on both the model side and the UI side, where the symbol preview silently degraded to an empty list - read_file was truncated twice (executor at 12000, boundary at 10000). Multi file reads were worse: each file was cut to the full budget, concatenated, then sliced once more as a whole, leaving everything after the first file in fragments. The budget is now divided before concatenation, not after - search_files and symbol candidate enumeration dropped results silently, so the model could not tell "nothing found" from "not finished looking" - read_terminal_output / send_terminal_input / stop_terminal had definitions and executors but belonged to no tool group, while the background-process result text explicitly instructs the model to call them Removals (no compatibility shims): - TOOL_TRUNCATE_DEFAULTS, which never took effect: its maxLength was always overridden by maxToolResultChars. Its entries for long-removed tools go too - detectContentStrategy, which guessed head/tail ratios by regex-matching the content: a source file that merely mentioned "error" got cut from the front - maxSingleFileChars, which duplicated the boundary budget (also from defaults/types/settings and the settings UI) - partialJson.ts returns to its single responsibility: streaming JSON parsing Also: - get_document_symbols renames path to relative_path, matching the rest of the LSP family; this also fixes symbol and diagnostics cards that had been rendering <unknown path> - get_document_symbols gains max_symbols and find_references gains max_references, aligning with find_symbol's max_matches; hitting any cap now always reports the true total - find_references resolves containing symbols only for the references it will actually return, no longer paying a full file read plus documentSymbol for references it discards | 2 months ago |
| Files | Last commit | Last update |
|---|---|---|
| 2 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 3 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 30 days ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 3 months ago | ||
| 3 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 2 months ago | ||
| 1 month ago | ||
| 2 months ago |