Skip to content

[pull] main from microsoft:main#1298

Merged
pull[bot] merged 5 commits into
code:mainfrom
microsoft:main
May 26, 2026
Merged

[pull] main from microsoft:main#1298
pull[bot] merged 5 commits into
code:mainfrom
microsoft:main

Conversation

@pull
Copy link
Copy Markdown

@pull pull Bot commented May 26, 2026

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 : )

benibenj and others added 5 commits May 26, 2026 12:27
* Update @vscode/codicons to version 0.0.46-13 in package.json and package-lock.json

* Add 'developer-tools' icon to codicons library

---------

Co-authored-by: mrleemurray <mrleemurray@users.noreply.github.com>
… provider (#317678)

* feat: add languageDiagnosticsService option for nes/inline completion provider

* test: add test cases
…igh/low eagerness levels (#315043)

* Add Xtab275AggrTagHL prompting strategy

Like Xtab275Aggressiveness but only emits the <|aggressive|> tag for
high/low levels. When the level is medium, uses the plain xtab275 prompt
without any aggressiveness tag.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Rename Xtab275AggrTagHL to Xtab275AggressivenessHighLow

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Refactor: extract getXtab275BasePostScript helper

Eliminates 3x duplication of the xtab275 base postscript text across
Xtab275, Xtab275Aggressiveness, and Xtab275AggressivenessHighLow cases.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Add unit tests for Xtab275AggressivenessHighLow strategy

Tests cover:
- Medium level omits the aggressive tag
- High level includes aggressive tag with 'high'
- Low level includes aggressive tag with 'low'
- High level still includes the xtab275 base postscript
- Contrast test: Xtab275Aggressiveness includes tag for medium

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chore: trigger CI re-run

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
…318148)

Two
 related issues caused even tiny notebook cell outputs (e.g. 5 bytes)
to be replaced with "Output is too large to be used as context".

1. Inverted size check in `RunNotebookCellOutput`: `getCharLimit` converts
   tokens to chars (×4), but it was applied to the byteLength side and
   compared against a token count. Compare byteLength against
   getCharLimit(tokenBudget / sizeLimitRatio) instead — the threshold was
   16× too small.

2. Remove `ReadCellOutput` from `toolsCalledInParallel`. Tools in that set
   are invoked eagerly with a sentinel `{ tokenBudget: 1 }` sizing on the
   premise that they don't consume sizing info. `RunNotebookCellOutput`
   does — it gates output on `sizing.tokenBudget` — so the sentinel made
   every non-empty output trip the size check. Letting it use the normal
   lazy path gives it the endpoint's real prompt budget.
@pull pull Bot locked and limited conversation to collaborators May 26, 2026
@pull pull Bot added the ⤵️ pull label May 26, 2026
@pull pull Bot merged commit 93c53e6 into code:main May 26, 2026
2 checks passed
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants