Commit Graph

85 Commits

Author SHA1 Message Date
Karthik Nadig 86e5f95490 Add question functionality and related types for chat interactions (#3157)
* Add question carousel functionality and related types for chat interactions

* feat: enhance logging for question carousel processing and answer conversion

* feat: enhance answer processing in AskQuestionsTool to support freeform text input

* cleanup: remove unused AskQuestionResult type from IQuestionAnswer

* clenaup: restore package.json

* feat: enhance AskQuestionsTool to handle no stream scenario and improve carousel answer conversion
2026-01-26 19:23:30 +00:00
Ulugbek Abdullaev 311d7fab8b update to latest vscode sources (#3118) 2026-01-26 09:52:58 +00:00
Johannes Rieken e8e9b03ba7 Tweak prompt selection and also remind model to do all edits in a single tool call (#3125)
* Tweak prompt selection and also remind model to do all edits in a single tool call

* (fix) correct tool name

* stest

* more stest drama
2026-01-26 08:36:17 +00:00
Johannes Rieken 1b8308f1fd Inline chat handles empty selections explicitly (#2535)
* handle empty selection better in inline chat

* stests

* add unit tests

* Update src/extension/prompts/node/inline/inlineChat2Prompt.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* stests

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-11 13:50:17 +00:00
Ulugbek Abdullaev 3417fc6d7c update cache (#2533) 2025-12-11 10:36:12 +00:00
Matt Bierner 3c8134184b Enable no-unexternalized-strings in repo (#2448)
Enables the same `no-unexternalized-strings` with have in `vscode` in this repo. This make sure we have a more consistent style across repos and when generating edits
2025-12-05 18:45:12 +00:00
Johannes Rieken 02d7754061 * drive inline chat feedback telemetry from CopilotInteractiveEditorResponse (#2435)
* `CopilotInteractiveEditorResponse.kind` is always 'ok' -> remove it

fixes https://github.com/microsoft/vscode/issues/280959
2025-12-05 13:26:45 +00:00
Ulugbek Abdullaev aee2abe2e1 nes: joint: don't enforce cache delay if document hasn't changed (#2409) 2025-12-04 22:13:16 +00:00
Johannes Rieken 36f0ab1f6f inline chat fixes (#2348)
* make sure the exit-tool is called when nothing else has been called

fixes https://github.com/microsoft/vscode/issues/280775

* tweak inline prompt for better prefix-caching

https://github.com/microsoft/vscode-internalbacklog/issues/6337
2025-12-03 10:14:20 +00:00
Ulugbek Abdullaev 3c78ed81dd nes: support /models on proxy and model picker (#2325) 2025-12-02 14:14:53 +00:00
Johannes Rieken 0231290715 keep intent detection for inline v1 intact (#2264) 2025-11-28 14:29:05 +00:00
Ulugbek Abdullaev 71803ce30f nes: support jump-to label (#2248)
* nes: update to latest core API for completions

* nes: support jump-to
2025-11-27 18:41:52 +00:00
Johannes Rieken bfc3fe5285 check edit tool results for errors and try again if editing failed (#2246)
* check edit tool results for errors and try again if editing failed

https://github.com/microsoft/vscode/issues/275056

* Update src/extension/prompts/node/inline/inlineChat2Prompt.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix prompt

* update-baseline

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-27 17:09:20 +00:00
Johannes Rieken a951ba62d1 fix https://github.com/microsoft/vscode/issues/277850 (#2079) 2025-11-19 15:17:31 +00:00
Johannes Rieken 34393c52c7 Always use github.copilot.editingSessionEditor, enable slash-command based on v2-config (#2060)
* Always use `github.copilot.editingSessionEditor`, enable slash-command based on v2-config

This makes all requests go to the `InlineChatIntent` and it decides (based on the v2-config) if it uses the "old world" for making inline chat requests happen

* re-run tests
2025-11-18 16:57:12 +00:00
Sandeep Somavarapu fedde4f1f1 clean up: (#2040)
* clean up:
- simplify namespaces
- simplify defining settings

* fix unused configs
2025-11-17 14:32:52 +00:00
Johannes Rieken a3a3829ee3 remove temporal context experiment (#1957)
fixes https://github.com/microsoft/vscode-copilot/issues/17115
fixes https://github.com/microsoft/vscode-copilot/issues/12756
fixes https://github.com/microsoft/vscode-copilot/issues/11674
2025-11-12 16:52:08 +00:00
Johannes Rieken 72dc56bdf3 Use cacheBreakpoint for inline chat prompt (#1954) 2025-11-12 16:15:07 +00:00
Don Jayamanne d0f16d6dc2 Remove zeromq and related unwanted notebook execution tests (#1941) 2025-11-12 04:31:49 +00:00
Ulugbek Abdullaev 1bd445ec60 update cache (#1822) 2025-11-07 10:39:59 +00:00
Ulugbek Abdullaev 4e4997c6d8 update cache (#1824) 2025-11-06 14:04:19 +00:00
Ulugbek Abdullaev f082551888 nes: remove old settings to configure model (#1823) 2025-11-06 14:04:18 +00:00
Ladislau Szomoru 2c92092e40 Git - add repository/branch name to the commit message generation context (#1756) 2025-11-02 19:26:50 +00:00
Ulugbek Abdullaev fe96b6d014 update cache (#1705) 2025-10-30 13:09:03 +00:00
Ulugbek Abdullaev 66fc3dc3fd update cache (#1688) 2025-10-29 11:39:45 +00:00
Johannes Rieken fcbff5831a InlineChatIntent (#1549)
* 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
2025-10-29 10:44:00 +00:00
Kyle Cutler d316af6ada Support generating PR descriptions based on a template (#1431)
* Support generating PR descriptions based on a template

* Try fix tests

* Comment

* Update cache
2025-10-27 14:07:07 +00:00
Kyle Cutler 7be42d291f Regenerate model metadata cache and fix outdated s-test (#1551)
Co-authored-by: Ulugbek Abdullaev <ulugbekna@gmail.com>
2025-10-24 15:49:26 +00:00
Ulugbek Abdullaev e7f5034823 nes: debt: remove python server-powered NES (#1435) 2025-10-20 18:06:27 +00:00
Ulugbek Abdullaev 10ffc78324 update cache (#1396)
* update cache

* update cache
2025-10-17 12:35:42 +00:00
Pierce Boggan 0af1ef6fce Model should self-identify if asked (#1267)
* Update model response guidelines in agent prompts

- Modified the response instructions in `agentPrompt.tsx` to clarify when to state the model name.
- Enhanced the `CopilotIdentityRules` class in `copilotIdentity.tsx` to include model name responses.

| File                             | Changes                                                                 |
|----------------------------------|-------------------------------------------------------------------------|
| `agentPrompt.tsx`               | Updated guidance on stating model name when asked.                     |
| `copilotIdentity.tsx`           | Added model name response instructions in identity rules.               |

* Update guidance on model name disclosure in agent prompts

- Revised instruction to clarify that the model name should not be volunteered unless explicitly asked by the user.

| File                                   | Changes Made                                      |
|----------------------------------------|--------------------------------------------------|
| src/extension/prompts/node/agent/agentPrompt.tsx | Updated reminder text regarding model name disclosure. |

* Update agent prompts to include model disclosure

- Added instruction to state the model being used when asked about it in multiple agent prompt snapshots.

| File Path                                                                 | Changes Made                                                                 |
|---------------------------------------------------------------------------|------------------------------------------------------------------------------|
| src/extension/prompts/node/agent/test/__snapshots__/agentPrompt.spec.tsx.snap | Updated responses to include model disclosure when asked about the model.    |

* Add SQLite cache file for simulation layer

This commit introduces a new SQLite cache file for the simulation layer to enhance data retrieval efficiency.

| File                                                                 | Changes                       |
|----------------------------------------------------------------------|-------------------------------|
| test/simulation/cache/layers/2171978e-88a1-4218-afac-dc1fe7ecc095.sqlite | New file created with versioning info |

* Add SQLite cache file for simulation layer

This commit introduces a new SQLite cache file to enhance the simulation layer's performance.

| File                                                                 | Changes                |
|----------------------------------------------------------------------|------------------------|
| test/simulation/cache/layers/94afd615-5805-4860-a1ba-3f9ebbf7b9a4.sqlite | New file added 📁      |

* remove bad cache layers

* npm run simulate

* update baseline

---------

Co-authored-by: João Moreno <joaomoreno@users.noreply.github.com>
2025-10-16 18:21:10 +00:00
Megan Rogge 5e1320a89d rm start debugging intent (#1323)
* rm start debugging intent

* rm test

* rm something

* update baseline

* Apply suggestion from @meganrogge
2025-10-15 21:34:59 +00:00
Ladislau Szomoru 063d9a6842 Git - switch commit message generation to gpt5-mini (#1249) 2025-10-07 07:57:48 +00:00
Rob Lourens 5eaa17af31 gpt-5-codex prompt improvements (#1177)
* gpt-5-codex prompt improvements

* update baseline
2025-09-28 22:56:41 +00:00
Rob Lourens 61325a7d80 Adopt isSubAgent tool call hint (#1173)
See microsoft/vscode#266588
2025-09-27 04:51:14 +00:00
Rob Lourens 9ce9f6cb2b Reduce INTERNAL_RESTRICTED (#1029)
* Reduce INTERNAL_RESTRICTED
and delete edits linkification setting

* Update
2025-09-12 04:43:26 +00:00
Matt Bierner d7c09e68fe Don't index files outside of the workspace (#957)
For https://github.com/microsoft/vscode/issues/261532

Makes sure callers don't accidentally try indexing files outside of the workspace
2025-09-09 01:35:22 +00:00
Matt Bierner bf8ec6c11d Explicitly dispose of the SimulationWorkspace (#929)
Looking into why this is being retained as well during testing but hopefully this reduces the memory usage
2025-09-06 05:03:08 +00:00
Alexandru Dima b7795e5434 Disallow importing straight from /extHostTypes/ and avoid instanceof check in ExtHostDocumentData (#878)
* Disallow importing straight from /extHostTypes/ and avoid instanceof check in ExtHostDocumentData

* Relax MarkdownString

* Undo most of the changes
2025-09-02 20:36:51 +00:00
Bhavya U fb0ad7f194 Add support for fetching release notes by version and update VscodePrompt to handle multiple versions (#859)
* Add support for fetching release notes by version and update VscodePrompt to handle multiple versions

* Skip metaprompt test suite for vscode panel

* Remove obsolete vscode metaprompt panel test data

* Remove skipped metaprompt panel test cases from baseline.json
2025-09-01 01:32:11 +00:00
Alexandru Dima 8956a62b06 Reuse more code from vscode (#836) 2025-08-29 16:30:23 +00:00
Alexandru Dima 6ddc031f00 Reduce code in /shims/ and rely on code coming in from vscode (#784)
* Reduce code in /shims/ and rely on code coming in from vscode

* update snapshots as a consequence of using MarkdownString from vscode
2025-08-29 14:10:37 +00:00
Benjamin Christopher Simmonds e992aa7164 Add excludes and groupId (#777)
* Add excludes and groupId

* 💄
2025-08-26 22:38:36 +00:00
Don Jayamanne 1a94dd33d4 Provide notebook contents on creation (#766)
* Provide contents of notebooks when notebook is created using create file

* Update baseline
2025-08-26 06:36:43 +00:00
Aaron Munger b3868ec970 debug chat replay with replay intent (#693)
* stub out new participant for replay

* add debugger to step through replay file

* parse and debug json replay

* make edits from the replay

* create absolute path

* update for the latest json format

* show tool calls with tool call renderer

* use singleton object for response queue

* cleanup

* formatting

* baseline update

* baseline update again

* just disable tool from normal agent calls

* reverting stest changes

* nes: clean up enforcing minimum response delay and cancellation handling (#746)

* nes: do not enforce minimum response delay for NES in 2 cases  (#748)

* nes: clean up enforcing minimum response delay and cancellation handling

* nes: do not enforce minimum response delay for NES in 2 cases

    1. for NES that's a subsequent edit (ie non-first edit in a set of multiple edits that come from a single model request)
    2. for NES that was cached and is returned again after rebasing on user edits

* Move to latest completion core (#749)

* update baseline

* use existing util

---------

Co-authored-by: Ulugbek Abdullaev <ulugbekna@gmail.com>
Co-authored-by: Dirk Bäumer <dirkb@microsoft.com>
2025-08-25 17:59:45 +00:00
Ulugbek Abdullaev 54cb26922e nes: feat: enable emit-fast-cursor-change by default (#743) 2025-08-25 09:45:36 +00:00
Don Jayamanne 1e35a2482b Additional telemetry for Notebook NES (#740)
* Additional telemetry for Notebook NES

* Updates
2025-08-25 02:11:39 +00:00
Rob Lourens 3177ea45f9 Add 'duration' to simulator request logs (#732)
even when cache is disabled
2025-08-23 18:55:58 +00:00
Henning Dieterichs 5a50ffb962 Copies sources from vscode (#688)
* Copy sources from vscode

* NodeJS.Timeout -> TimeoutHandle

* Fixes copy sources fallout

* Fixes snapshots
2025-08-20 09:46:00 +00:00
Rob Lourens 912e4ce46f Set max_tokens on intentDetection to avoid runaway responses (#648)
* Set max_tokens on intentDetection to avoid runaway responses

* Update baseline
2025-08-18 20:01:51 +00:00