The CodeHighlightPlugin's selection restoration could create an invalid
Lexical selection targeting a LineBreakNode with type 'element'. Since
LineBreakNode is not an ElementNode, Lexical threw during reconciliation
and the LexicalErrorBoundary replaced the editor with an error state.
The fix ensures findPoint never targets a LineBreakNode directly.
Instead it falls back to an element-level selection on the parent
CodeNode using the child index, which is always a valid target.
Extracted the selection helpers (getCodeNodeAbsoluteOffset,
findCodeNodeSelectionPoint, restoreCodeNodeSelection) into
markdownEditor.ts for testability and added regression tests.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Display compact status cards in the chat transcript showing each
sub-agent's name, current activity (Thinking, Using grep, etc.),
and elapsed time. Cards appear while sub-agents are running and
clear when the session goes idle.
- Extend SessionEventRecord with description, error, toolCallId,
and model fields for subagent events
- Forward additional subagent fields in handleTurnScopedEvent
- Add subagentTracker reducer to derive active subagent state from
session events, including agent-activity correlation
- Create SubagentActivityCard component with spinner, status icon,
agent name, activity label, and live elapsed timer
- Wire activeSubagents state in App.tsx and pass to ChatPane
- Add 16 unit tests for the subagent tracker
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When the agent produces multiple intermediate responses during a turn,
each gets a unique messageId but all stay pending until finalizeTurn().
This caused multiple stacked 'Thinking' bubbles in the chat transcript.
Now, when a new messageId arrives in applyTurnDelta, any previously
pending assistant messages are marked complete and message-complete
events are emitted before the new message-delta. The renderer reducer
mirrors this logic for defensive consistency.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Change the bottom action bar from absolute positioning to normal
document flow so it sits below the editable area instead of floating
on top. Reduce editable bottom padding since buttons no longer overlap.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Declutter the pill row above the chat composer by relocating Terminal
and Prompts pills from the session-config rows into the composer's
bottom action bar (left side). The session-config row now only shows
session-scoped controls: Tools, Approval, Model, and Thinking.
The relocated pills use a lighter, borderless style matching the
inner-composer aesthetic alongside the existing Attach, Plan mode,
and Send buttons.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- add a PTY manager with platform shell resolution and streamed data/exit events
- expose terminal lifecycle and terminal height IPC through preload and app service
- persist terminal panel height in workspace settings and document the backend contract
- add backend tests and validate native packaging with bun run package
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Thread mcpProbingServerIds from workspace state through App → ChatPane → InlineApprovalPill
- Show animated spinner and 'probing…' label on pill button while any MCP server is being probed
- Show per-server probing indicator in popover: spinning icon, 'probing…' badge, hidden toggle
- Render approval pill during probing even when no MCP tools are known yet
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
mergeDiscoveredToolingState now carries over probedTools from existing
servers when the config fingerprint is unchanged. The equality check in
syncProjectDiscoveredTooling also strips probedTools before comparing,
so runtime-only probe data never triggers a spurious state replacement.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The SDK's listTools() calls cacheToolMetadata() which compiles
outputSchema validators. Servers with \ in their schemas (e.g.,
icm-mcp) cause a JSON schema resolution error. Fall back to a raw
JSON-RPC tools/list request that skips schema compilation, since we
only need tool names and descriptions for the approval pill.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Some MCP servers (e.g., eschat.microsoft.com/mcp) serve their
OAuth Protected Resource Metadata at the origin without the path
suffix. Add a third candidate URL that strips the path, matching
VS Code's discovery behavior.
Tried in order:
1. RFC 9728: {origin}/.well-known/{suffix}{path}
2. Appended: {origin}{path}/.well-known/{suffix}
3. Origin-only: {origin}/.well-known/{suffix}
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Tokens are in-memory and empty at startup, so HTTP servers requiring
OAuth return 401 during initial probing. After the user completes
OAuth (either via session auth prompt or proactive auth), re-probe
the authenticated server so its tools appear in the approval pill
without requiring an app restart.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When SSE fallback gets 405 (confirming a Streamable HTTP server),
surface the original Streamable HTTP error instead of the misleading
SSE 405. Extract HTTP status codes from SDK error objects to produce
clearer log messages like 'HTTP 401: Streamable HTTP error: ...'.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Many MCP servers only support legacy SSE despite being configured as
generic HTTP endpoints. Follow the MCP SDK's recommended fallback
pattern: try Streamable HTTP first, then retry with SSE on failure.
This matches VS Code's behavior for these servers.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When multiple MCP servers expose the same tool names (e.g., several
kusto-mcp instances), each server's group now shows its tools instead
of only the first server getting the tools and others showing 0/0.
Deduplicate the effectiveAutoApprovedCount to avoid double-counting
shared tools in the pill header.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Change the approval group header from <button> to a <div> with
role='button' and keyboard handling to avoid nesting the GroupToggle
<button> inside another <button>, which is invalid HTML.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Increase default probe timeout from 10s to 30s to handle slow
package managers (uvx, npx) that install on first run
- Add console logging for probe success/failure to aid debugging
- Probe manually configured MCP servers (not just discovered ones)
so all servers with wildcard tools get their tools discovered
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When MCP server configs declare wildcard tools (empty tools array),
the Copilot SDK has no API to list individual tool names. Add direct
MCP protocol probing using @modelcontextprotocol/sdk to discover
available tools from each accepted server.
- Add McpToolProber service supporting stdio/SSE/HTTP transports
- Probe accepted MCP servers on project load, acceptance, and rescan
- Store probed tools on DiscoveredMcpServer and McpServerDefinition
- Use probed tools in listApprovalToolDefinitions when declared tools
are empty, so the approval pill shows individual tool toggles
- Remove unused isMcpServerApprovalKey helper
- Fix effectiveAutoApprovedCount Math.max workaround in ChatPane
- Add comprehensive tests for probed tool behavior
- Update ARCHITECTURE.md tooling integration section
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
MCP servers configured with empty tools arrays (wildcard) now appear in the
auto-approval pill with a server-level toggle. When toggled, a server-level
approval key (mcp_server:<name>) is added to autoApprovedToolNames. The
sidecar matches this key against PermissionRequestMcp.ServerName to auto-
approve all tools from that server without needing individual tool names.
- Add buildMcpServerApprovalKey/isMcpServerApprovalKey helpers
- Create approval groups for all MCP servers including empty-tools ones
- Add serverApprovalKey to ApprovalToolGroup for server-level toggles
- Update sidecar RequiresToolCallApproval to check server-level keys
- Include server-level keys in listApprovalToolNames for pruning safety
- Add tests for both shared domain and sidecar approval matching
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Group MCP tools by server and LSP tools by profile in the approval popover
instead of showing a flat list. Each server/profile group gets a collapsible
header with a batch toggle to approve/unapprove all tools at once. Add a
search filter (visible when >10 tools) and partial-state indicators for
groups with mixed approval. Add groupApprovalToolsByProvider shared helper
with tests.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add Copilot Customization section to ProjectSettingsPanel with instruction file
previews, agent profile enable/disable toggles, and prompt file listing. Add
InlinePromptPill to chat input for selecting and sending prompt files with
variable substitution. Wire rescan and agent profile IPC in App.tsx. Update
website with Copilot Customization feature card.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Move project-specific settings (discovered MCP servers) out of the
global Settings panel and into a dedicated ProjectSettingsPanel overlay.
Users can now access any project's settings via a gear icon on the
sidebar project header, or by clicking the pending-discovery badge.
- Add ProjectSettingsPanel component with project info, discovered MCP
server management (accept/dismiss/rescan), and project removal
- Add gear icon and clickable discovery badge to Sidebar ProjectGroup
- Remove project-specific discovery props from SettingsPanel (now
shows only user-level discovered servers)
- Wire ProjectSettingsPanel overlay in App.tsx with auto-close on
project removal
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Remove the packaging-only create-dmg dependency in favor of native hdiutil, and make the hook runner working-directory test assert behavior without depending on macOS temp-path canonicalization.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Use the repository's default Electron import pattern in the MCP OAuth service, make the attachment-path test platform-neutral, and ensure the hook runner cwd/env test drains stdin before asserting shell output.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add 5 new feature cards: Visual Pattern Editor, Extensible Tooling, Tooling
Discovery, Plan Review & Agent Questions, and Run Timeline. Expand Real
Project Context (git awareness), Persistent Sessions (search/duplicate),
and Get Started step 1 (Copilot diagnostics). Enrich tech banner with
React Flow and Open Source. Feature grid goes from 8 to 13 cards.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Give each scratchpad session its own working directory, migrate existing scratchpad sessions on workspace load, and route sidecar turns through the session-specific cwd. Add regression coverage for create, duplicate, delete, and migration flows, and document the new persistence model.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Replace raw SDK identifiers with human-friendly labels (e.g.
sessionStart → Session start) and drop the meaningless UUID detail.
Labels now read like 'Session start hook started' instead of
'Hook sessionStart started'.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Stop forwarding hook lifecycle events when a project has no configured
.github/hooks/*.json commands so the UI only receives meaningful hook
activity. Also expose the configured-hook state on the bundle, cover the
suppression wiring with tests, and document the updated event semantics.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Append phase text (started/completed) to hook event labels so
start and end phases are visually distinct instead of appearing
as duplicates.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Replace the old disconnected-node addAgentNodeToGraph with the
mode-aware addAgentToGraph so new agents are automatically wired
into the graph topology. Replace the graph-nuking removeAgent
path with removeAgentFromGraph for surgical node removal. Split
emitChange into graph-preserving and mode-change paths so editing
agent properties no longer discards custom positions and edges.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add mode-aware graph mutation helpers for pattern topology so backend
code can add and remove agents without forcing a full graph rebuild.
Also preserve an existing pattern graph in savePattern instead of
re-syncing it from defaults, and cover the new behavior with shared
and main-process tests.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When multiple tool calls of the same permission category (e.g. three
concurrent view/read calls) arrive simultaneously, approving one now
cascades to all queued approvals sharing the same category key. This
eliminates repeated approval prompts for parallel tool calls.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Add an AlwaysApprove flag to resolve-approval commands and cache
approved tool keys for the current request so repeated runtime
permissions are auto-approved immediately within the same turn.
The cache is cleared when the turn finishes to avoid leaking across
future requests.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
AryxCopilotAgent was converting ALL Copilot tool requests (ask_user,
MCP tools, etc.) into FunctionCallContent. The Agent Framework's
AIAgentHostExecutor tracks every FunctionCallContent as an outstanding
request. Since SDK-handled tools like ask_user never produce a
matching FunctionResultContent, HasOutstandingRequests stayed true and
TurnToken was never emitted — stalling group-chat advancement after
an ask_user interaction.
Now only handoff_to_* tool requests are projected as FunctionCallContent.
All other tool calls remain invisible to the Agent Framework executor,
matching the upstream GitHubCopilotAgent behaviour.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Replace the broken forced-tool workaround with a repo-local Copilot
agent adapter that merges runtime handoff instructions and tool
declarations into Copilot sessions and projects Copilot tool requests
back into Agent Framework function-call updates.
Also add regression coverage for the adapter and document the runtime
integration detail in the architecture guide.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Constrain the initial handoff triage agent so it cannot use regular
session tooling and must use a handoff tool on its first invocation.
This prevents the model from narrating delegation in plain text while
never actually transferring control.
Also add regression tests for the new entry-agent constraints.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
