feat(code): suggest compacting large resumed threads - #5318
Merged
Johannes du Plessis (johannes117) merged 9 commits intoAug 5, 2026
Conversation
github-actions
Bot
added
dcode
Johannes du Plessis (johannes117)
added a commit
that referenced
this pull request
Aug 5, 2026
Related #5318 Runtime-model compaction now preserves configured archive routing by constructing the summarizer before applying `_ArchiveReadGuard`. ## Before: <img width="863" height="275" alt="Screenshot 2026-08-05 at 11 52 41 AM" src="https://github.com/user-attachments/assets/a3836fd1-c414-46d0-881f-02d18db77755" /> ## After: <img width="649" height="217" alt="Screenshot 2026-08-05 at 12 04 13 PM" src="https://github.com/user-attachments/assets/59d53b35-0d7e-4f08-8c05-2f49172a2f61" />
Resuming a thread sends nothing to the model, so the oversized-context prompt does not need to block the resume. Ask once the thread is live instead, via `_maybe_compact_after_resume` called from the three `SessionStartCause.RESUME` sites, and drop the launch-time cancel path that only existed because the prompt used to gate the resume. Removes `_cancel_initial_resume` and its server respawn, the `compact_on_resume` parameter on `_switch_agent`, the startup history prefetch, and the `_resume_thread` reordering those required. The threshold check now reads `_context_tokens`, which the history load already populates. Both `/threads -r` branches now run off Textual's message pump; the same-agent branch previously awaited the cwd modal inline, where it could never receive the keys that would resolve it.
![open-swe[bot]](https://avatars.githubusercontent.com/in/1395372?s=60&v=4){kind=small}
A launch that resumes and passes an initial prompt skips the history load, so nothing populated `_context_tokens` and the compaction check always fell through -- on the one path where the cost is immediate, since the prompt is submitted against the full restored context moments later. Seed the count from the checkpoint via `_restore_resumed_context_tokens` before the prompt runs. Also wrap the detached same-agent `/threads -r` continuation in `_resume_same_agent_thread`. `_resume_thread` reports its own failures once the switch is under way, but its pre-switch phase runs outside that boundary, and `_schedule_off_message_pump` only logs -- so a failure there ended the command with no visible outcome.
Alexander Olsen (aolsenjazz)
approved these changes
Aug 5, 2026
Johannes du Plessis (johannes117)
enabled auto-merge (squash)
August 5, 2026 23:58
Johannes du Plessis (johannes117)
deleted the
johannes117/code/compact-on-resume
branch
August 5, 2026 23:58
Mason Daugherty (mdrxy)
pushed a commit
that referenced
this pull request
Aug 6, 2026
> [!CAUTION] > Merging this PR will automatically publish to **PyPI** and create a **GitHub release**. For the full release process, see [`.github/RELEASING.md`](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md). --- _Release notes preview: keep this section in sync with the package `CHANGELOG.md`. Publish reads the merged CHANGELOG via `release.yml`, not this PR description — keep them aligned anyway so the PR stays an accurate historical record for reviewers and anyone returning later._ --- ## [0.1.53](deepagents-code==0.1.52...deepagents-code==0.1.53) (2026-08-06) ### Features - Added pricing coverage with Baseten built-in overrides and local fallback overrides when `genai-prices` is missing data ([#5312](#5312), [#5304](#5304)). - Suggest compacting large resumed threads ([#5318](#5318)). - Added terminal program trace metadata ([#5329](#5329)). ### Bug Fixes - Preserved runtime offload archive routing ([#5328](#5328)). - Always restart after a successful startup auto-update ([#5317](#5317)). - Fixed leaked turn coroutines and SQLite handles ([#5218](#5218)). - Keep MCP shutdown-race tracebacks from appearing in the terminal ([#5325](#5325)). - Open the `/auto model` selector immediately while connecting ([#5341](#5341)). - Route failures to `PostToolUseFailure` ([#5315](#5315)). - Use dismissed copy for ask-user prompts ([#5331](#5331)). _End release notes preview._ --- > [!NOTE] > A **New Contributors** section is appended to the GitHub release notes automatically at publish time (see [Release Pipeline](https://github.com/langchain-ai/deepagents/blob/main/.github/RELEASING.md#release-pipeline), step 2). --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: langchain-oss-automated-triage[bot] <248757908+langchain-oss-automated-triage[bot]@users.noreply.github.com>
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
3 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.
Large-context threads now offer compaction before resume, with options to continue without compacting or cancel.
The threshold defaults to 400,000 tokens and is configurable with
[threads].compact_on_resume_threshold.Screenshots