fix: improve LM Studio connection handling and documentation#67
Open
vlordier wants to merge 6 commits intoLiquid4All:mainfrom
Open
fix: improve LM Studio connection handling and documentation#67vlordier wants to merge 6 commits intoLiquid4All:mainfrom
vlordier wants to merge 6 commits intoLiquid4All:mainfrom
Conversation
- Tool Result Compression: smart summarization for large tool outputs (directory listings, search results, JSON data) - Request Deduplication: 500ms debounce on send button to prevent duplicate requests from rapid clicks - Config Hot Reload: poll config file for changes, reload without restart, show toast notification - Error Boundary: timeout wrapper (120s) around tool execution, graceful error messages instead of crashing agent loop
- Add 13 tests for settings.rs (AppSettings, SamplingConfig, config hot reload) - Add 12 tests for chat.rs compression functions (truncate, compress directory, search, JSON) - Total tests: 392 (up from 365) - Coverage: 42.5% (up from 39.5%)
- Add ModelStatus tests (serialization, healthy/unhealthy states) - Add SamplingOverrides serialization tests - Add InferenceClient tests for: - LM Studio URL construction and model selection - Tool call format (NativeJson vs Pythonic) - Fallback chain exhaustion (AllModelsUnavailable) - is_retriable for various HTTP status codes - Error repair from malformed tool calls - Total tests: 417 (up from 392)
- Add tests for data_dir(), cache_dir(), resolve_db_path() - Add rotate_log_file() tests (creates rotated copies, handles missing files) - Add filter_by_enabled_servers() tests (filters correctly, handles missing/invalid config) - Add resolve_vision_model() tests (returns None without config) - Add filter_tools_by_allowlist() test (doesn't panic without config) - Add load_override_file() tests (parses config, returns empty for missing) - Total tests: 430 (up from 417) - Coverage: 43.3% (up from 42.5%)
- Add helpful debug message when LM Studio port connection fails - Distinguish between connection errors and timeouts in health_check
- Document default LM Studio port (1234) in environment configuration
There was a problem hiding this comment.
Pull request overview
This is a large PR that adds the full LocalCowork application — a Tauri-based desktop app with an on-device AI agent, MCP server management, inference client, and React frontend. The PR description mentions improving LM Studio connection handling and documentation, but the actual changes are far broader, introducing the entire application codebase.
Changes:
- Added the complete Tauri backend including MCP client, inference engine, agent core (conversation management, tool routing, permissions, orchestration), and IPC commands
- Added React frontend components (settings store, chat input, app shell) and Tauri configuration
- Added LM Studio endpoint documentation to
.env.example
Reviewed changes
Copilot reviewed 49 out of 56 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
src/stores/settingsStore.ts |
Zustand store for settings panel state and actions |
src/components/Chat/MessageInput.tsx |
Chat message input with debouncing |
src/App.tsx |
Root app component with config watching and layout |
src-tauri/tauri.conf.json |
Tauri window and bundle configuration |
src-tauri/src/mcp_client/* |
MCP client: types, transport, lifecycle, discovery, registry, errors |
src-tauri/src/inference/* |
Inference client: config, streaming, types, tool call parsing, errors |
src-tauri/src/agent_core/* |
Agent core: conversation, tool router, permissions, orchestrator, tokens |
src-tauri/src/commands/* |
Tauri IPC commands for chat, filesystem, hardware, model download, etc. |
src-tauri/Cargo.toml |
Rust dependencies and build configuration |
examples/localcowork/.env.example |
Added LM Studio default endpoint documentation |
| Other config files | Entitlements, capabilities, build scripts |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+142
to
+143
| if (interval) { | ||
| clearInterval(interval); |
There was a problem hiding this comment.
stopConfigWatch destructures configWatchInterval from state but then references an undefined variable interval on line 142-143. This will throw a ReferenceError at runtime when attempting to stop the config watch. The variable name should be configWatchInterval instead of interval.
Suggested change
| if (interval) { | |
| clearInterval(interval); | |
| if (configWatchInterval) { | |
| clearInterval(configWatchInterval); |
| // fs was overridden | ||
| assert_eq!(merged["fs"].command, "node"); | ||
| // ocr was NOT overridden — preserved from discovery | ||
| assert_eq!(merged["ocr"].command, "npx"); |
There was a problem hiding this comment.
This assertion will fail on Windows because default_npx_command() returns "npx.cmd" on Windows, not "npx". The test should compare against default_npx_command() (as done in test_discover_ts_server) instead of the hard-coded string "npx".
Suggested change
| assert_eq!(merged["ocr"].command, "npx"); | |
| assert_eq!(merged["ocr"].command, super::default_npx_command()); |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary
Improves on PR #53 (LM Studio support):
Changes
Testing