Conversation
…0774) * workbench: fix workspace folder path handling in settings reader - Fixes handling of workspace folders that have null or undefined URI paths in the settings folder observer. Adds fallback path handling using URI.with() method for folders without explicit paths. Fixes #310367 (Commit message generated by Copilot) * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <copilot@github.com>
…y-breakpoint-address-lookup fix(debug): identify instruction breakpoints by resolved address to allow removal when instructionReference changes (#289678)
* remove setting SubagentToolCustomAgents, enabled by default * update * fix tests
* chat customizations: add ChatResourceEnablement * update * filter by sessionTypes Co-authored-by: Copilot <copilot@github.com> * inline ChatResourceEnablement Co-authored-by: Copilot <copilot@github.com> * update Co-authored-by: Copilot <copilot@github.com> * update * revert version change --------- Co-authored-by: Copilot <copilot@github.com>
…10793) * nes: cache: add a test to show how rebasing fails * feat: add reverse-agreement rebase for NES cache behind experiment flag When the user types more text than the model predicted at the same position (e.g., model: '{', user: '{\n\t'), the rebase engine now recognizes that the model's edit is consumed by the user's typing and offers the remaining unconsumed model edits as rebased suggestions. The new behavior is gated behind the 'reverseAgreement' experiment flag in NesRebaseConfigs (config key: chat.advanced.inlineEdits.reverseAgreement, default: false). Adds 10 unit tests covering positive, negative, and edge cases.
…ider override, iterate candidates Bug fixes only (no telemetry changes): 1. Filter available_models through knownEndpoints before sending to router 2. Remove same-provider override from router path - trust router ranking 3. Iterate all candidate_models via _findFirstAvailableModel 4. Warn-level logs for sync mismatches
Emits a new telemetry event after all client-side model overrides are applied. Properties: candidateModel, actualModel, overrideReason (none/clientOverride), conversationId. Tests cover: match, vision fallback override, router failure.
* Build system for agent sessions * Discovery fixes * better npe fix. --------- Co-authored-by: Peng Lyu <penn.lv@gmail.com>
Previously isNESForAnotherDoc was only set inside addNotebookTelemetry, so non-notebook cross-file NES always reported false. - Set the flag on the main edit path for all cases (notebook and non-notebook) - Set the flag on the jump-to-position path when targetDocumentId differs - Set the flag and status 'noEdit:crossFileTargetNotFound' when cross-file target document is not found in the workspace - Remove redundant setIsNESForOtherEditor call from addNotebookTelemetry
…hecks (#310800) * fix: prevent update server from bogus 'unknown' commit in overwrite checks When update metadata is missing (e.g. interrupted install recovery via _applySpecificUpdate), the fallback IUpdate uses version: 'unknown'. This value flows into checkForOverwriteUpdates, which polls every 5 minutes and passes it as the commit to buildUpdateFeedUrl, producing requests to /api/update/{platform}/{quality}/unknown. Skip the overwrite check when pendingUpdateCommit is missing or 'unknown' to break the cycle. * fix: construct commit for install recovery
…310805) fix 3rd round of agents app issues
…ns app (#310812) I realized after implementing this that we avoid showing diffs for in-progress sessions https://github.com/microsoft/vscode/blob/3267a57dc5ace468c668880fca8bb5cb73467e63/src/vs/sessions/contrib/sessions/browser/views/sessionsList.ts#L262-L264 But if that ever was to change this'd work nicely. And I think it should change :)
Does proper markdown linking
remove 'included' property from input latency telemetry configuration
(Written by Copilot)
- Use single for-loop to partition available_models into routableModels and droppedModels (bhavyaus review) - Fix test: when ALL available_models are unknown, _selectDefaultModel throws since none match knownEndpoints — test now expects throw instead of gpt-4o
…emetry Add automode.routerModelSelection telemetry with actualModel
…ndidate-models-fallback # Conflicts: # extensions/copilot/src/platform/endpoint/node/test/automodeService.spec.ts
* mobile friendly agent sessions view * no need for auto hide. * 💄
…e-models-fallback Fix router model selection: filter available_models, remove same-provider override, iterate candidates
We only want to set the zindex if we're inside a modal
Fix z-index for webviews with modals
…310830) * feat: add GitHub Copilot upgrader skill and CLI integration documentation * Updates * Update extensions/copilot/src/extension/chatSessions/copilotcli/AGENTS.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…d customizations UI (#310824) * agents: restore built-in skills and merge into provider-based customizations UI Built-in skills bundled under `vs/sessions/skills/` stopped appearing in the Agents window's AI customization UI after PR #310000 deleted AgenticPromptsService. The CLI extension's itemProvider was also re-discovering the bundled copies from `out/vs/sessions/skills/` and tagging them as user-storage, which placed them in the wrong group. Fix in two parts: 1. Re-introduce a minimal AgenticPromptsService (sessions layer) that discovers SKILL.md files under FileAccess.asFileUri('vs/sessions/skills'), parses each via the public parseNew(), validates name === folderName, and exposes them via findAgentSkills(), listPromptFiles(), and listPromptFilesForStorage(skill, BUILTIN_STORAGE). Registered as IPromptsService for the Agents window. 2. In ProviderCustomizationItemSource.fetchItems(skill), merge the authoritative built-in entries with the harness's itemProvider output: - dedup provider items by URI against built-ins (drops the out/-tree duplicates) - append built-ins with groupKey: BUILTIN_STORAGE so the UI renders them under the Built-in group - apply the existing 'UI Integration' badge via IAICustomizationWorkspaceService.getSkillUIIntegrations() Safe for regular workbench: base PromptsService throws on BUILTIN_STORAGE and the merge step catches and returns items unchanged. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * agents: preserve BUILTIN_STORAGE on built-in skills so edit/save-as-copy flow activates The management editor's 'edit built-in and save as user/workspace copy' flow is gated on item.storage === BUILTIN_STORAGE. The normalizer was unconditionally rewriting that to PromptsStorage.extension when groupKey === BUILTIN_STORAGE (historical: built-ins came from the extension contribution pipeline). For provider-supplied built-ins, preserve BUILTIN_STORAGE on the normalized item so the editor becomes editable and the save handler prompts for a workspace/user target on save. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * agents: hide built-in skill when a workspace/user override with the same name exists Move the built-in skill merge to run on normalized list items so we can filter out built-ins whose name is already represented by a PromptsStorage.local or PromptsStorage.user entry. The built-in row disappears as soon as the user saves a workspace/user copy via the save ' flow.as Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * agents: address Copilot review feedback - Respect getDisabledPromptFiles when merging built-in skills into the UI so a user-disabled built-in shows disabled (not enabled). - Restrict the 'existing names' override set in findAgentSkills to user/workspace skills only, so an extension-contributed skill with the same name no longer suppresses the built-in. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…es (#310377) Bumps [dompurify](https://github.com/cure53/DOMPurify) from 3.3.2 to 3.4.0. - [Release notes](https://github.com/cure53/DOMPurify/releases) - [Commits](cure53/DOMPurify@3.3.2...3.4.0) --- updated-dependencies: - dependency-name: dompurify dependency-version: 3.4.0 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* Add Developer: Sync Account Policy command Adds a manual command to force-resync account policy data, bypassing the 1-hour staleness cache used by the background poller. Plumbs forceRefresh through getTokenEntitlements and getMcpRegistryProvider so a forced sync truly hits the network for all three sub-fetches. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address review: await dialog calls and use detail param for error --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…ershell (#310839) * Fix to put fix in treeSitterCommandParser * be better with comments
* Log agent host catch failures (Written by Copilot) * Use observable models for agent host providers (Written by Copilot) * Fix root agents changed test narrowing (Written by Copilot) --------- Co-authored-by: Copilot <copilot@github.com>
Bumps [hono](https://github.com/honojs/hono) from 4.12.12 to 4.12.14. - [Release notes](https://github.com/honojs/hono/releases) - [Commits](honojs/hono@v4.12.12...v4.12.14) --- updated-dependencies: - dependency-name: hono dependency-version: 4.12.14 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Bumps [hono](https://github.com/honojs/hono) from 4.12.12 to 4.12.14. - [Release notes](https://github.com/honojs/hono/releases) - [Commits](honojs/hono@v4.12.12...v4.12.14) --- updated-dependencies: - dependency-name: hono dependency-version: 4.12.14 dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* add agentName to telemetry Co-authored-by: Copilot <copilot@github.com> * comment update --------- Co-authored-by: Copilot <copilot@github.com>
Make sure we clear notebook styles
Partially revert 96a69e3 This re-introduces a issue with sessions not being cleaned up but fixes the more important regression
…0889) Simplify compaction fallback: use Simple mode on budget exceeded, skip Full When the main prompt render exceeds the token budget and falls back to foreground summarization (renderWithSummarization), skip Full mode and go straight to Simple mode via forceSimpleSummary. This saves a wasted LLM request since Full would likely also fail under the same budget pressure, and Simple is guaranteed to fit via hard tool-result truncation. - Add forceSimpleSummary prop to AgentPromptProps and SummarizedAgentHistoryProps - Honor forceSimpleSummary in getSummaryWithFallback (unless config forces Full) - Remove summarizationSource prop and source telemetry field (no longer needed) - Clean up stale GDPR annotations for removed source field - /compact and background standard-mode paths keep existing Full → Simple chain
Fix chat sessions not preserved
…rExcludeRegexes Restrict autoImportSpecifierExcludeRegexes to trusted workspaces
* Plumb agent host model configuration through sessions (Written by Copilot) * Remove deprecated stuff * tweak * sync protocol * Resolve merge fallout for model config branch Restore the shared agent host diff helper to match main and adapt protocol file-edit diffs locally in the agent host session providers. (Written by Copilot) * Fix agent host session diff typings Restore the session diff compatibility export and allow the agent host session list to display both live protocol file edits and compact metadata diffs. (Written by Copilot) * Update session diffs for protocol file edit shape Return aggregated session diffs using the current IFileEdit protocol shape and update the focused tests accordingly. (Written by Copilot) --------- Co-authored-by: Copilot <copilot@github.com>
(Written by Copilot)
* Fix agent host worktree terminal cwd (Written by Copilot) * Fix worktree terminal cwd test on Windows (Written by Copilot)
The AGENT_HOST_SCHEME guard in getActiveSessionFolderData only covered the repository fallback branch. When a remote agent host session provides a workingDirectory (worktree), it was added as a workspace folder unconditionally. This caused PromptFilesLocator to probe all customization sub-paths (.claude/agents, .claude/rules, .agents, etc.) over RPC, producing noisy warnings for directories that don't exist. Hoist the guard above both branches so any agent-host URI is excluded. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…nt (#310908) Callers can now opt into Anthropic features (context editing, tool search, etc.) by setting modelCapabilities on the request itself, as introduced in #308387. The base endpoint no longer needs to inject beta headers — the Claude agent controls its own headers. Reverts the merge logic from microsoft/vscode-copilot-chat#4945.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )