- Replaced getTool with getExecutableTool in CursorExecBridgeOptions to prioritize mounted-device permission wrappers over canonical tools.
- Updated createAgentSession to check isAutoQaEnabled against restricted tool filtering when configuring system prompts.
- Added test coverage verifying execution overrides preserve approval gates and restricted sessions omit auto-qa guidance.
When Cursor packs toolCallStarted and toolCallCompleted into one HTTP/2
chunk, the bridge tool_execution_end (synchronous callback, fired
mid-parse) reaches the interactive controller before the streamed
toolcall_start (queued on AssistantMessageEventStream, delivered a
microtask later). The controller found no pendingTools entry, dropped
the completion, and the card created afterwards animated forever.
Two halves, each necessary:
- Hold an early todo completion in #orphanedToolCompletions and replay
it when the streamed block creates its component.
- Guard card creation from cumulative message_update frames with the
turn-scoped #toolTimelineComponents map. Without this, the update
after the replay re-lists the same toolCall block, finds pendingTools
empty again, and spawns a second, permanently pending card. This is
also why emitting a synthetic tool_execution_start from the bridge
(previous attempt, reverted) could not work.
Both maps are cleared together at the existing transcript-anchor reset
sites. The normal ordering (start first) is covered by a control test.
Two review findings on the native todo sync.
- TodoItem.dependencies is a graph the local model cannot store: rows
are keyed by content, carry no id, and hold no edges. An imported
dependent row files as plain pending and nextActionableTask then
offers work the server considers blocked. Refuse snapshots with an
edge pointing at an unfinished row; edges whose blockers already
finished constrain nothing and still mirror.
- The todo failure warning interpolated the provider error verbatim.
Collapse and truncate it at the render boundary.
Also documents two known, unfixed defects: an async cursorOnToolResult
transformer resolving after the buffer drain, and the todo card
lifecycle race. Emitting a synthetic tool_execution_start for the
latter was measured and rejected -- the completion deletes the entry it
creates, so the late streamed block adds a second card.
An empty `read_todos` with `total_count=0` (proto3 unset or genuinely
empty) was accepted and mirrored as an authoritative wipe. Refuse empty
reads; clearing the list stays on `update_todos`.
Benign refusal text is now "Todo snapshot not mirrored" instead of
"No todo changes", which falsely described a server-accepted update that
only the local mirror declined.
`CursorTodoSyncHandler`, `buildTodoToolResult`, `extractTodoError`, and
the host `todoSync` each enumerate why a snapshot may be `null`. All
four listed only filtered and truncated reads, so a duplicate-content
refusal read as undocumented -- easy to mistake for an error, or to
"fix" by mirroring it again.
Only a successful snapshot settled a native todo block. A `read_todos`
narrowed by a filter and a server `UpdateTodosError` both went
unanswered: no `tool_execution_end`, so the card animated forever, and
no `toolResult`, so `buildSessionContext` stripped the block on rebuild.
Every completed native todo call now settles. The refusal path carries
no `details.phases` -- `event-controller` feeds that straight into
`setTodos`, so echoing the current list back would let a call that
changed nothing overwrite live panel state. A server error is carried
through as a failed result instead of collapsing into the benign no-op.
Each regression is covered by a test verified to fail without its fix.
The previous commit paired every server-resolved todo block with a
result, but built that result in the provider from the flat snapshot.
`todoToolRenderer.renderResult` reconstructs the list exclusively from
`details.phases`, so the block survived the dangling-strip only to replay
as `Todo 0 tasks`.
Only the host computes that grouping -- the provider sees a flat list --
so `todoSync` now returns the result it already assembled and the
provider persists it verbatim. A refused snapshot never reaches the host,
so the provider's summary-only fallback still covers that path, and
exactly one result is emitted either way.
Separately, `Agent`'s Cursor buffering wrapper pushed its entry only
after awaiting the optional `cursorOnToolResult` transformer. The
provider dispatches decoded messages with `void handleServerMessage(...)`,
so a `message_end` from the same chunk could drain the buffer while a
transformer was still pending, dropping the result. The entry is now
reserved synchronously and patched in place when the transformer
resolves, keeping buffer order and still applying the customization.
Production is unaffected -- `sdk.ts` sets no transformer -- but the
option is supported and its contract returns a Promise.
Tests: a delayed-transformer case that loses the result without the
buffering change, and a replay case driving the persisted result through
`buildSessionContext` and asserting `details.phases` rebuilds a non-empty
list -- the id-pair assertion alone did not catch the empty render.
Review follow-up on two defects in the native todo bridge.
`tool_execution_end` was emitted under a freshly generated UUID, but the
interactive transcript files the visible block under the streamed
`callId` and only clears it when the ids match. The card therefore stayed
pending and animating for the rest of the session. The settled call id is
now passed to `todoSync`, making the parameter required so no caller can
silently reintroduce a mismatch.
Nothing produced a `toolResult` for these blocks either: `todoSync` only
appended a custom entry and emitted a transient event. Since
`buildSessionContext` strips any `toolCall` with no matching result, the
interaction vanished from every rebuilt transcript -- reload, branch
switch, or Ctrl+L -- leaving a "tool call elided" placeholder. A paired
result now travels the same `onToolResult` channel the other
server-resolved Cursor calls already use, including when the snapshot is
refused: the call happened, it just changed no local state.
Cursor resolves its native `update_todos`/`read_todos` tools server-side,
so the todo list never followed the model's intent locally.
Two defects, both silent:
- `agent.v1.ToolCall` is a protobuf oneof. A decoded message exposes the
selected variant as `tool: { case, value }` and has no flattened
`updateTodosToolCall` property, so the bridge recognized no native todo
call at all on the wire path.
- The synthesized `todo` block was emitted as locally runnable carrying a
`{todos}` payload the local tool's schema rejects, turning every update
into a validation error and driving a spurious continuation turn.
Todo calls are now read through the oneof, both native blocks are stamped
resolved, and local state is mirrored only from the server's confirmed
success snapshot. Partial `read_todos` responses -- narrowed by
`status_filter`/`id_filter`, or short of the server's own `total_count` --
are subsets, not the list, and are refused rather than deleting the tasks
they omit. `TODO_STATUS_CANCELLED` maps to `abandoned` instead of
reverting the task to `pending`.
The exec bridge mirrors each snapshot into session state, refreshes the
interactive panel via a synthetic `tool_execution_end`, and persists to
the session branch so the list survives reloads, rewinds, compaction, and
session switches. Existing phase grouping is preserved.
Regression tests drive the bridge with wire-encoded protobuf, which is
the only shape production ever sees; all six fail without this change.
Union-resolved test conflict with PR #5651's mounted-tool bridge tests;
extended the local BlockState helper with resolvedMcpToolCallIds added
by #5651's exec-resolved stamping.
CursorExecHandlers.executeDelete removes files directly via fs.rmSync,
bypassing the tool map that every other exec handler consults. A background
advisor with the default read-only set (advise/read/grep/glob) could delete
workspace files from a Cursor deleteArgs frame despite holding no mutating
tool.
Add an allowNativeDelete option (default allowed, preserving the primary
agent's behavior) and set it for the advisor only when it was granted a
file-mutating tool (write/edit).
Fixes#5680
Forwarded the session xd registry into Cursor provider tool contexts.
Routed Cursor MCP execution through the mounted registry fallback and added regression coverage for built-in devices and external MCP tools.
Fixes#5650
Cursor exec bridges derived failure state only from thrown exceptions, so structured AgentToolResult.isError failures were emitted as successes. Propagate the returned flag through standard and streaming shell execution, with regression coverage for both paths.
- Replaced `grep`, `glob`, and `ast_grep` `paths` inputs with optional single `path` strings while preserving default workspace-root behavior.
- Added shared `toPathList` normalization for legacy arrays and JSON-encoded arrays across tool execution and TUI renderers.
- Updated prompts, fixtures, shims, transcript summaries, and tests to send and display the new `path` argument.
- Updated collab-web search tool cards to read `path` while falling back to legacy `paths` for historical transcripts.
- Recorded the contiguous coding-agent changelog run for the tool-path breaking change and adjacent TTS entries.
- Renamed the `find` and `search` tools to `glob` and `grep` respectively across the codebase to improve command clarity.
- Implemented full-stack support for the renamed tools, including CLI arguments, system prompts, SDK exports, and tool registration.
- Added automated migration logic in `settings` to transform legacy `find` and `search` configuration keys to their new equivalents.
- Updated the `collab-web` renderer registry to ensure backwards compatibility with legacy tool outputs.
- Implement JSON repair and strict argument validation to sanitize raw payloads and redact sensitive information from agent event logs.
- Add automatic authentication fallback for benchmark model resolution to ensure consistent performance testing across providers.
- Refactor search tool API parameters by replacing `i` with a case-sensitive `case` boolean flag for clarity.
- Update session history formatting to ensure empty objects are consistently serialized as `{}` instead of empty strings.
- Switched search/ast_grep/ast_edit/find inputs from scalar path fields to required `paths` arrays.
- Reworked path resolution to normalize and expand each `paths` entry via explicit helpers in `src/tools/path-utils.ts`.
- Updated search and find tool-call rendering to display explicit `paths` values in mode overlays and export views.
- Updated tool prompt docs and examples to document `paths` array inputs for search, grep, find, and AST tools.
- Raised the default search match limit from 20 to 500 and updated limit-reached messaging.
- Renamed MCP tool IDs from `mcp_<server>_<tool>` to `mcp__<server>_<tool>`, and changed built-in `grep` to `search`.
- Updated `parseMCPToolName()` and bridge helpers to require and trim the `mcp__` prefix.
- Updated cursor, manager, and session discovery flows to require `mcp__`-prefixed tool names.
- Updated MCP tests and assertion fixtures to use `mcp__`-prefixed tool IDs and expected system prompts.
- Renamed the built-in `grep` content-search tool to `search` across settings, schemas, and SDK exports.
- Switched execution wiring so `Task`, `Plan`, cursor, and shell mapping now invoke `search` instead of `grep`.
- Updated prompts, plan-mode docs, and example tool lists to replace `grep`/`ls` references with `search` guidance.
- Aligned `Grep*`/`grep` event, renderer, and hook types to `Search*`/`search` across runtime and tests.
- Documented and fixed `search` result rendering budget behavior and added internal-URL/path-list transcript notes.
- Consolidated grep, ast-grep, and ast-edit on required `path`, replacing `glob`/`lang`/`sel` with inline file, dir, glob, list, and URL targets.
- Changed ast-grep and grep schemas to require a single `pat` string and use `skip` pagination instead of array patterns or offsets.
- Updated argument validation to reject empty `path` and invalid `skip`, and routed grep context to session settings only.
- Updated tool prompts and tests to reflect new path globbing semantics and `first N` truncation output text.
- Canonicalized file and CLI defaults from `read` to `open` across tool registration and prompts.
- Added `resolveToolAlias()` and applied alias-normalized tool selection so legacy `read` maps to `open`.
- Updated runtime, UI, and export layers to treat `open` as first-class while preserving `read` compatibility.
- Renamed read prompt docs to `open.md`/`open-chunk.md` and refreshed system guidance to recommend `open`.
- Updated tool-related tests and expectations from `read` to `open` (including test fixtures and aliases).
- Added `/rename <title>` slash command to set explicit session names and update header/tab titles.
- Added `session_name` status segment with hash-derived accent color for session titles.
- Fixed shell execution failure sanitization to preserve all `execResult` fields after redacting stderr.
- Fixed tool execution completion output to pass original `toolResult` text instead of sanitized `content`.
- agent-loop: sanitize text content in tool_execution result/partialResult
- ai/cursor: fix ANSI escape handling, add incomplete escape detection
- coding-agent/cursor: fix per-delta sanitization with tracked state
- print-mode: flush stderr before exit to prevent data loss
- add unit tests for bash execution clamp display line
- Add stdout/stderr flush timers in ai provider to handle buffering
- Sanitize text content in tool execution results before emitting events
- Add @oh-my-pi/pi-natives workspace dependency
- Sanitize partialResult in onUpdate callback
- Sanitize text before onStdout in onUpdate
- Sanitize result in tool_execution_end event
- Return sanitized result from shell method
- Sanitize partialResult in onUpdate callback
- Sanitize result in tool_execution_end event
- Return sanitized result from executeTool
- Prevents terminal escape sequences from leaking through event stream
- Added support for four new exec message types: listMcpResources, readMcpResource, recordScreen, and computerUse.
- Imported four new result schemas to handle responses for MCP resource operations and computer use capabilities.
- Updated bash execution handler to use standardized 'cwd' parameter name instead of 'workdir'.
- Removed `output_mode` parameter from grep tool, consolidating all output to content mode with file grouping and match headers.
- Renamed grep context parameters from `context_pre`/`context_post` to `pre`/`post` for improved clarity.
- Removed `n` (line numbers) parameter from grep tool as line numbers are now always displayed.
- Reformatted grep output to display numbered matches with file paths, line numbers, and context lines with consistent alignment.
- Introduced `SearchParams` struct in Rust grep implementation to simplify parameter passing and improve code maintainability.
- Made `normalize_env_key` function const-eligible for compile-time evaluation in shell module.
- Consolidated directory listing functionality from dedicated `ls` tool into the `read` tool.
- Removed the `ls` tool and all related exports, types, and configurations from the public API.
- Updated `read` tool to return formatted directory listings with modification times instead of redirecting to `ls` tool.
- Removed `bashInterceptor.simpleLs` setting and related interception logic from bash tool.
- Removed `ls.enabled` setting and related tool registration logic.
- Removed test cases for the `ls` tool and updated tool type definitions to remove `LsToolResultEvent`.
- Removed incorrect millisecond-to-second auto-conversion logic in timeout handling across cursor, fetch, gemini-image, and ssh tools.
- Fixed timeout parameter interpretation to respect user-provided values without automatic unit conversion heuristics.
- Renamed `head_limit` to `limit` in grep and find tools for consistency.
- Added `context` as optional alias for the `c` parameter in grep.
- Made hidden files inclusion configurable in find with `hidden` parameter.
- Integrated .gitignore and .ignore file support in find tool.
- Updated plan mode documentation for self-contained plan files.
- Removed Prettier configuration files (.prettierignore and .prettierrc) and migrated formatting to Biome.
- Updated Biome configuration from version 2.3.11 to 2.3.12 and changed arrowParentheses rule from 'always' to 'asNeeded'.
- Pinned @biomejs/biome dependency to exact version 2.3.12 in package.json and bun.lock.
- Applied consistent arrow function formatting across 489 files by removing unnecessary parentheses around single parameters.
- Removed blank lines after comment blocks and reorganized imports for consistency across the codebase.
- Converted readdirSync, readFileSync, and statSync to async readdir, readFile, stat across skills and agent discovery.
- Made scanDirectoryForSkills async and refactored custom directory scanning to use Promise.all for concurrent processing.
- Updated agent discovery to use fs/promises for async file reading and refactored helper patterns.
- Added AgentParsingError exception class for better error handling during agent parsing.
- Added filesystem error type guards (isEnoent, isEacces, isPerm, etc.) to pi-utils for safe error checking.
- Added color manipulation utilities to pi-utils for accessibility features.
- Added color-blind mode setting to settings manager.
- Migrated plugins, settings, and config modules from sync to async file operations.
- Updated error handling to use new pi-utils type guards for type-safe checking.
- Removed WASM generation script; use Bun `wasm?raw` loader for imports.
- Added bunfig.toml with loaders for `.md`, `.py`, and `.wasm?raw` text imports.
- Added types/assets/index.d.ts for global TypeScript module declarations.
- Unified TypeScript configuration with tsgo-based checking across monorepo.
- Removed build and WASM steps from install and publish pipelines.
- Added tsconfig.publish.json files to all packages with optimized publish-time configuration.
- Updated all package.json scripts with prepublishOnly hooks for correct type checking during publish.
- Added @oh-my-pi/omp-stats path mappings to root tsconfig.json for consistent imports.
- Added WASM generation script for photon module and integrated into install:dev script.
can1357