run_in_terminal: promote sync command to background after idle silence#316166
Merged
Conversation
added 2 commits
May 11, 2026 18:05
If a synchronous run_in_terminal call produces no output for N ms, win the foreground race with a new idleSilence candidate that mirrors the existing timeout handler: promote the execution to background, return the terminal ID + output collected so far, append a steering hint. The process is never killed. Gated on chat.tools.terminal.idleSilenceTimeoutMs (default 60000, 0 disables). Listener and scheduler are owned by the existing raceCleanup DisposableStore so they go away when another candidate wins. Async (waitStrategy === 'idle') path is unchanged. Fixes #315884
Replace the boolean mentionTimeout parameter on _buildInputNeededSteeringText with a 'none' | 'timeout' | 'idleSilence' discriminator so the idle-silence promotion result no longer reuses the timeout wording. Add focused unit tests covering each mode.
Collaborator
Author
|
/requires-eval-assessment terminalbench2 gpt-5.4,claude-opus-4.6,claude-opus-4.7 |
meganrogge
added
the
~requires-eval-assessment
meganrogge
changed the title
Contributor
|
⏳ Queued vscode build for
|
Contributor
There was a problem hiding this comment.
Pull request overview
This PR extends the terminal chat agent “run in terminal” tool to support an idle-silence path: when a foreground/sync command produces no output for a configurable duration, the tool returns early, moves the execution to a background terminal, and provides updated steering guidance to the model.
Changes:
- Add a new configuration setting
chat.tools.terminal.idleSilenceTimeoutMsto control idle-silence promotion timing (0 disables). - Implement idle-silence promotion logic in
RunInTerminalTooland adjust input-needed steering text to distinguish'none' | 'timeout' | 'idleSilence'. - Add unit tests validating the steering text content across the new “hung hint” modes.
Show a summary per file
| File | Description |
|---|---|
| src/vs/workbench/contrib/terminalContrib/chatAgentTools/test/electron-browser/runInTerminalTool.test.ts | Adds tests for steering text behavior across none/timeout/idle-silence modes. |
| src/vs/workbench/contrib/terminalContrib/chatAgentTools/common/terminalChatAgentToolsConfiguration.ts | Introduces the new idleSilenceTimeoutMs setting with schema/description. |
| src/vs/workbench/contrib/terminalContrib/chatAgentTools/browser/tools/runInTerminalTool.ts | Implements idle-silence promotion and updates steering text API/call sites. |
Copilot's findings
- Files reviewed: 3/3 changed files
- Comments generated: 2
Contributor
|
Base:
|
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
meganrogge
added
~requires-eval-assessment
Contributor
|
⏳ Queued vscode build for
|
meganrogge
removed
the
~requires-eval-assessment
Resolve conflict in runInTerminalTool.ts: keep idleSilence race type + try/finally cleanup. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
meganrogge
added
the
~requires-eval-assessment
Contributor
|
⏳ Queued vscode build for
|
Contributor
|
🚀 Queued eval-assessment publish build for
|
Contributor
|
🔬 Queued eval-assessment benchmark for
Results will be posted back here when the run completes. |
Contributor
|
✅ Eval-assessment build published.
|
vs-code-engineering
Bot
removed
the
~requires-eval-assessment
The revert in main (#316165) removed the idle-silence feature. This merge keeps all idle-silence changes from the branch: race candidate, config setting, steering text refactor, and tests. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
meganrogge
added
the
~requires-eval-assessment
Contributor
|
⏳ Queued vscode build for
|
Contributor
|
🚀 Queued eval-assessment publish build for
|
Contributor
|
🔬 Queued eval-assessment benchmark for
Results will be posted back here when the run completes. |
Contributor
|
✅ Eval-assessment build published.
|
vs-code-engineering
Bot
removed
the
~requires-eval-assessment
Contributor
|
📊 Eval-assessment benchmark complete.
🧪 Results |
mjbvz
approved these changes
May 13, 2026
Contributor
|
📊 Eval-assessment benchmark complete.
🧪 Results |
Contributor
|
📊 Eval-assessment benchmark complete.
🧪 Results |
NikolaRHristov
pushed a commit
to CodeEditorLand/Editor
that referenced
this pull request
May 13, 2026
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Re-land of #315885 on a standalone branch for isolated eval testing.
What this does
If a synchronous
run_in_terminalcall produces no terminal output for N ms (default 60s), a newidleSilencerace candidate wins the foreground race and promotes the execution to background. The process is never killed — the model gets the terminal ID + output so far and canget_terminal_output,send_to_terminal, orkill_terminal.Changes (3 files)
runInTerminalTool.ts: NewidleSilencerace candidate usingRunOnceScheduler+onDatalistener. Refactors_buildInputNeededSteeringTextfrommentionTimeout: booleantohungHint: 'none' | 'timeout' | 'idleSilence'discriminator with per-mode wording.terminalChatAgentToolsConfiguration.ts: New settingchat.tools.terminal.idleSilenceTimeoutMs(default 60000, 0 disables, experimental).runInTerminalTool.test.ts: 3 unit tests for steering text across all hint modes.Why this is safe
npm install,cargo build, etc.) reset the timer and never trip.OutputMonitoridle detection.raceCleanupDisposableStore— disposed when any other race candidate wins.