Tool and parameter descriptions were handed to the LLM in Chinese on every
runtime regardless of locale: the English metadata table in
packages/tools/src/tool-metadata.ts had no caller, the desktop translateTool
looked up i18n keys that exist in no locale file, and the MCP server had no
locale at all.
Fill the table for every tool whose definition text is Chinese (37 entries,
only translating what the definitions write in Chinese so the two copies
cannot drift), and route the four consumers through getLocalizedToolMetadata:
the cross-chat agent adapters, the CLI Web agent adapter, the desktop shared
tool adapter (replacing the dead translateTool), and the MCP server, which
now resolves its locale from config.locale.lang or the system locale for both
the standalone binary and the chatlab mcp subcommand.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Preserve partial output and token usage in CLI turns and edited UI rounds while leaving ordinary failures and cancellation unchanged. Use OutputLimitError across agent runners so incomplete turns remain visibly unsuccessful but can be reloaded and continued.
Cover real stream handling, SQLite persistence, reload, CLI continuation, and unsuccessful one-shot JSON output.
Retain cumulative Agent usage from status events and emit it in the terminal done event after an error so truncated Desktop replies keep their token totals.
Cover the real Desktop Agent and stream runner alongside CLI and global entries, including partial output, completion state, and persisted usage.
Remove the proactive-memory preference and its cross-platform runtime plumbing so memory behavior has one clear contract. Normalize away the obsolete setting and keep source type limited to provenance.
Resolve private ranking display names, apply privacy preprocessing consistently across cached recaps and structural labels, and bound model-visible overview payloads to the configured tool budget.
Count complete tool payloads with the runtime tokenizer so Chinese evidence respects the configured model context budget.\n\nResolve contact sources incrementally with cancellation checks and targeted member lookups to keep long cross-chat investigations responsive.
Replace message content and structured user entity references in one database statement. Treat omitted references as an explicit clear so edited prompts cannot replay stale identities.
Use native Window Controls Overlay geometry and sampled background colors so caption hover and drag regions track the system title bar.
Forward original Windows close-handler errors to the shared logger so failures retain their stack traces.
Remove the one-time close prompt and remembered-choice path so Windows close behavior is always explicit and predictable. New installations now minimize to the system tray by default, while users can still choose to quit from settings.
Close the uncached readonly adapter after every Desktop export so Windows can delete the session without restarting. Add regression coverage for the successful export lifecycle.
Match ownerless QQ exports safely across UID and UIN drift, preserve merged message scopes through single and batch imports, and apply only sender mappings proven by overlapping platform message IDs. Reject incomplete group mappings to avoid member identity corruption.
Preserve batch support through telemetry, forward item-scoped progress across Desktop and CLI Web, and retain original backend failure details for diagnostics and unfinished results.
Add self-hosted Umami reporting alongside existing telemetry across Desktop and CLI Web.
Track normalized startup, import, feature, and AI usage with a stable anonymous ID and strict privacy allowlists. Keep incremental usage platform-independent and preserve accurate failure classifications and platform metadata across import paths.
digua
Chris ChengandClaude Opus 5
Sanssssssssssssssss
digua