* Bring back Copilot panel in chat
* Use ICompletionsContextService
* WIP
* Convert to service accessor
* More accessor work
* Some more accessor adaption
* Remove command from UI
* fix service accessors
---------
Co-authored-by: BeniBenj <besimmonds@microsoft.com>
* Add Anthropic web-search tool support and tool result handling
* Add TODO to handle citations as specialized Citation part
* Update src/extension/byok/vscode-node/anthropicProvider.ts
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Guard against missing pendingServerToolCall.toolId when processing web_search tool results in Anthropic provider
* Report citation metadata as LanguageModelToolResultPart for web_search citations in Anthropic provider
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* add remote rerank service
* setup exp
* fix up style
* remove _fallback as this logic can be handled outside for reranker service
* Apply suggestion from @Copilot
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* rereank in semantic search view
* 💄
* rerank is fire and forget
* 💄
* error logging
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Peng Lyu <penn.lv@gmail.com>
* remove references to old setting `github.copilot.chat.advanced.inlineChat2`
* play with `InlineChatIntent`
* wip
* move things, better/simpler prompt
* cleanup, renames, stuff
* more wip
* done after tool call
* edit and generate stest for new InlineChatIntent
* use codebook for diagnostics
* inline chat fixing stests
* stest run
* remove old Inline2 tests
* remove slash commands for v2, remove the editCodeIntent path for v2
* 💄
* 💄
* Don't use `diagnosticsTimeout` when with inline chat because the new diagnostics will never be read but slow down the result
* fix compile error
* stest run
* update baseline
* prevent some JSON errors from empty output
* unfresh baseline.json
* use `MockGithubAvailableEmbeddingTypesService` in stests
* back to hamfisted skipping of stests
* send telemetry from inline chat intent
* tweak some stests
* Include completions core test during PR build
* Implement a FakeCopilotTokenManager to run completions core test without a GitHub token
* Small naming fix
* Run tests also under Windows
* Fix running Windows tests
* Remove dead request logging code
I don't know what PendingLoggedCompletionRequest was used for but it's not used anymore, and removing it hugely simplifies the log to markdown code
* Clean up postOptions usage
* Update src/extension/prompt/vscode-node/requestLoggerImpl.ts
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update src/extension/prompt/vscode-node/requestLoggerImpl.ts
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Clean up after copilot
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>