- Added flushing of assistant text during provider completion to ensure no output is lost on transport failure.
- Updated checkpoint blob synchronization tests to validate behavior under various conditions, including terminal and non-terminal states.
- Introduced new functions for managing checkpoint terminal actions, improving clarity and maintainability of the code.
- Implemented additional tests for imported blob handling and conversation state restoration, ensuring robustness in data integrity across operations.
- Renamed test function to better reflect its purpose.
- Enhanced model details structure by adding DisplayName and DisplayNameShort fields in buildCLIModelDetails.
- Updated test cases to validate the new fields and ensure correct functionality.
- Updated README.md to provide clearer project information, features, and quick start instructions.
- Added a function to mask the user's account identifier in CursorAccountCard.vue for enhanced privacy.
- Adjusted localization files to remove outdated entries and improve clarity across multiple languages.
- Refactored MainLayout.vue to streamline author information handling and improve user experience.
Implemented the buildShellToolCallDeltaMessage function to map client shell output to the delta format for Cursor's terminal bubble. This includes handling both stdout and stderr events. Updated the service to publish these messages when processing execution results. Additionally, added a test for enabling terminal output UI streaming in the bootstrap statsig configuration.
- Fetch and normalize OpenAI and Anthropic model lists through the proxy service.
- Add searchable multi-model selection with localized UI and persisted adapter mappings.
- Cover endpoint resolution, authentication, pagination, and response parsing.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Added support for checkpointing phases and blob management in the forwarder.
- Introduced new types and methods for handling checkpoint blobs, including queuing and publishing checkpoints.
- Enhanced the projector to build checkpoint projections with content-addressed blobs.
- Implemented tests to ensure proper checkpoint blob synchronization and handling of cancellation scenarios.
- Refactored response handling in newProtoMessage to utilize agentv1 for GetUsableModelsResponse and GetDefaultModelForCliResponse.
- Added new tests for buildCLIModelDetails and encodeCLIModels to ensure correct model details and encoding.
- Updated buildUsableModelsPayload and buildDefaultModelForCliPayload to leverage buildCLIModelDetails for improved model data structure.
- Integrated a tooltip with a button to open the contributor's GitHub profile in the CursorAccountCard component.
- Updated the layout of the account card for better visual organization.
- Removed routing mode options from the configuration view and adjusted related translations in multiple languages.
- Cleaned up unused routing mode logic in the app state management.
Project sidecar context history into Cursor-compatible JSONL transcripts so previous conversations remain readable when referenced from new chats. Backfill existing sessions on startup and preserve Cursor-managed turn status entries during atomic updates.
Desktop Cursor works through the local proxy because it drives the agent
over BidiAppend/RunSSE plus the already-mocked unary endpoints. The
cursor-agent CLI speaks the same agent protocol but calls additional
unary endpoints that had no local handlers, so every request fell into a
wildcard route and came back as HTTP 404, which the Connect client maps
to '[unimplemented] HTTP 404'.
Three independent breaks, one visible symptom:
1. Startup: ServerConfigService/GetServerConfig (only the AiService
variant was mocked), DashboardService/GetTeamAdminSettingsOrEmptyIfNotInTeam
and DashboardService/ListMarketplaces were missing, so the CLI aborted
during session init.
2. Git workspaces: the CLI resolves the repo path-encryption key from
indexingConfig.default{User,Team}PathEncryptionKey in GetServerConfig
when no IDE-stored repo keys exist. The mock returned no indexingConfig,
so repository identity init failed with 'No encryption key found'.
3. Tool execution: every fs tool executor (Ls/Grep/Glob/Shell) consults
the ignore service, which calls getRepoBlockExcludeGlobs() ->
DashboardService/GetTeamReposOrEmptyIfNotInTeam. The 404 propagated as
the tool result error, so model answers arrived but every tool call
returned '[unimplemented] HTTP 404'. Non-git workspaces skip the
repo-block path, which is why tools only failed inside git repos.
Also close the remaining tolerated 404 noise so a CLI session produces
zero unimplemented responses: model listing (GetUsableModels,
GetDefaultModelForCli, GetDefaultModel), dashboard/plugin housekeeping
(GetGlobalCommands, GetEffectiveUserPlugins, RegisterMarketplaceAndPlugins,
GetCliDownloadUrl) and telemetry (AnalyticsService/SubmitLogs,
AnalyticsService/TrackEvents, OTLP /v1/traces).
Additional logging: PolicyMiddleware now includes the request path in the
per-request log line, which is what made this diagnosable from app.log.
Store checkpoint turns as validated blobs and restore prefetched parent turns so forked conversations retain their replay history and rewind prefix.
Co-authored-by: Cursor <cursoragent@cursor.com>
Route the MiniMax OpenAI-compatible endpoint (global api.minimax.io and
China api.minimaxi.com hosts, plus the MiniMax-M3/MiniMax-M2.7 model ids)
to the thinking_type disable branch so that disabling thinking writes
thinking:{type:"disabled"} and drops reasoning_effort, matching the
existing MiMo/deepseek/glm behavior.
Cursor may reuse the same request_id for a later turn and restart
append_seqno from 1. Accept seq=1 after progress as a sequence restart
when idle so tool results are not discarded as stale forever.
leokun