* Plan mode for background agents
* Updates
* Fix cache directory name and correct markdown syntax in PlanAgentProvider
* feat: add Plan Mode support for Copilot CLI agents
* fix: update configuration check for CLI Plan Mode in ChatSessionsContrib
* Ensure we log the error
* fix tests
* Remove Ask User Question tool in favor of Core tool
Fixes https://github.com/microsoft/vscode/issues/296134
* feedback
* remove duplicate & restore toolset
* feedback
* revert change in anthropic.ts because ask_questions is what is used in Claude
* Add support for local repository memory and update telemetry events
* Update memory command labels for clarity in the UI
* update test
* Add repository memory section to snapshot tests for clarity
* Add compaction support for Responses API context management
* compaction update
* compaction update
* cleaning up for PR
* Updating model list that can be enabled for compaction and enabling experimentation config
* cleaning up variable names
* updates based on review comments
* correcting the failed tests
* skip summarization when compaction is enabled
* fixing unit tests
* updating threshold value for compaction
* fixing test failures
* Add memory viewing command and update chat panel session resource definitions
* refactor: rename memory commands and add clear memories functionality
* add memory show and clear commands to chat tools
* refactor: improve memory clearing logic and add user feedback for no memories found
* Add Explore agent provider for code research subagent
* Update exploreAgent model description
* Make Explore subagent conditional via PlanAgentExploreSubagentEnabled config
* Fix CI
* Fix tests
* Tweak prompt based on cross-model review
* Address PR feedback: clarify model selection logic
---------
Co-authored-by: Don Jayamanne <don.jayamanne@outlook.com>
Co-authored-by: Harald Kirschner <digitarald@gmail.com>
* change to settings.json to trigger search subagent with proxy
* updating to dogfood other search models
* update to add config with proxy model name
* update advanced settings in package.json
* add to package.nls.json
* Add background compaction feature for conversation history summarization
* Improve background compaction handling by allowing retries on failure and enhancing error logging
* Add TTL caching for cloud agent /enabled and session provider options
Further reduce GitHub API requests from the cloud agent sessions provider. (extension of 89771ff43a)
- Add TtlCache and SingleSlotTtlCache utilities for TTL-based caching
- Cache /enabled results for 30 minutes (only enabled=true; disabled results
always re-fetch so users aren't stuck after enabling CCA)
- Cache the full provideChatSessionProviderOptions result for 15 minutes,
covering custom agents, models, and partner agents in a single cache entry
- refresh() no longer clears TTL caches; only auth changes and the new
"Clear Cloud Agent Caches" command force-clear them
- Register "GitHub Copilot: Clear Cloud Agent Caches" command as an escape hatch
- Add unit tests for TtlCache and SingleSlotTtlCache
* Apply suggestions from code review
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Initial code migration
* Migrate unit tests
* Fix command titles
* Use DI patterns
* add tests
* Fix createReadonlyUri to use fileUri.path for correct URI generation
* Fix makeTextResult to ensure fallback string conversion for non-string data
* Add debounce cleanup for diagnostics and selection change notifications
* Increase JSON body size limit to 10MB for MCP requests
* Normalize diagnostic severity to lowercase in getDiagnostics tool
* Refactor logging level in DiffStateManager to use trace for detailed debug information
* Handle errors when updating hasActiveDiff context in DiffStateManager
* Refactor showNotification tool: reorder imports and remove unnecessary logging
* Refactor closeDiff tests: replace createMockServer with MockMcpServer and update result parsing
* Remove showNotification tool and its associated tests
* Add mock implementations for Disposable and Uri in test files
* Fix unit tests!
* feat: Add CLI integration configuration and update command titles in package.json
* refactor: Improve debounce handling for diagnostics and selection change notifications
* refactor: Enhance initialization logic and configuration handling in CopilotCLIContrib
* Revert change
* fix: Disable CLI integration by default in configuration
---------
Co-authored-by: Don Jayamanne <don.jayamanne@outlook.com>
* enhance model capabilities with adaptive thinking and effort configuration
* Add effort
* clean up
* Enhance model capabilities by adding support for Claude Opus 4.6 in tool search and context editing
* Add chat.additionalReadAccessPaths setting for read-only access to external folders
Implements a new setting that allows users to specify folders outside the
workspace that Copilot Chat read-only tools (read_file, list_dir) can
access without requiring confirmation.
- Add github.copilot.chat.additionalReadAccessPaths setting (string array)
- Gate additional access behind a readOnly flag on assertFileOkForTool,
isFileExternalAndNeedsConfirmation, and isDirExternalAndNeedsConfirmation
- Edit tools remain workspace-restricted (isFileOkForTool does not pass readOnly)
- .copilotignore rules are still respected for additional paths
Closesmicrosoft/vscode#293386
* Addresses PR feedback
* Remove `@workspace` chat participant
For https://github.com/microsoft/vscode/issues/292972
Removes the `@workspace` chat participant since this is now an outdated (and confusing) way to use code search. For now we'll keep the commands but I've moved them under the default agent instead
* Updating tests too and fixing some references
* add a search agent endpoint & call it
* toggle between main and proxy
* add toggle that checks for manually set setting for agentic proxy
* update to use agentic proxy
* update package jsons to reflect new setting
* search subagent should be enabled for proxy to be enabled
* change to settings.json to trigger search subagent with proxy
* make config settings non-advanced
* remove search subagent settings
* Disable beta features for inline-chat in messages API usage
* Disable all beta features for non agent location
* Refactor: Update conversation agent checks to include MessagesProxy location
* Update Anthropic thinking budget to max output tokens
* Update test
* update telemetry for context editing with additional metrics
* fix: refine deferred loading logic for allowed conversation agents
* Remove 'experimental' tag from Messages API and budgetTokens descriptions in configuration
* Add Anthropic configuration options for Messages API and budget tokens
* added experimental search model toggling
* configure tool call limit
* update to make model configurable, default to chat endpoint
* add model name and tool call limit exp variables
* fix merge conflict comma bug
* update default values so tests pass
* update to have try/catch if modelName not available
* Improve logging
* Add setting for testing failure cases
* Add welcome view for failed GitHub login
* Use Sign In command
* Polish and fix test failure
Alex Ross
Don Jayamanne
Tyler James Leonhardt
Bhavya U
Copilot
Justin Chen
dileepyavan
Harald Kirschner
Ladislau Szomoru
Johannes Rieken
Anisha Agarwal
Josh Spicer
Matthew Rayermann
Logan Ramos
Benjamin Christopher Simmonds
Peng Lyu
Alex Weininger
Rob Lourens
Ayush Singh
Henning Dieterichs
Christof Marti
Matt Bierner
Eleanor Boyd
SteVen Batten