feat(code): tri-state DEEPAGENTS_CODE_ONBOARDING env var - #5301
Merged
Conversation
The onboarding override was debug-only and could only force the flow on, so a fresh instance (container image, CI, provisioned workstation) had no way to opt out of the first-run tutorial without pre-seeding the internal completion marker. Rename the variable and let a falsy value disable the flow outright while an unset value keeps first-run behavior. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
github-actions
Bot
added
dcode
Mason Daugherty (mdrxy)
marked this pull request as ready for review
August 4, 2026 14:52
![open-swe[bot]](https://avatars.githubusercontent.com/in/1395372?s=60&v=4){kind=small}
…n `config` An explicitly empty value classifies as falsy in `should_run_onboarding`, so the manifest option now declares `empty_env_is_false` to keep `config get startup.onboarding` in agreement with the runtime.
Mason Daugherty (mdrxy)
pushed a commit
to langchain-ai/docs
that referenced
this pull request
Aug 4, 2026
Fixes DOC-1484 ## Summary - Adds `DEEPAGENTS_CODE_ONBOARDING` to the environment variable reference in `src/oss/deepagents/code/configuration.mdx` - Documents all three states: truthy (force onboarding on every startup), falsy (suppress onboarding — useful for CI/containers), and unset (default first-run behavior via completion marker) - Notes that the former `DEEPAGENTS_CODE_DEBUG_ONBOARDING` variable is no longer recognized ## Links - Linear: https://linear.app/langchain/issue/DOC-1484/document-tri-state-deepagents-code-onboarding-environment-variable - Slack: https://langchain.slack.com/archives/C09G1T60QV9/p1785856462705709 - Source PR: langchain-ai/deepagents#5301 ## Verification Not run; docs-only copy change to a reference field block. ## Reviewers Requested review from: @npentrel, @lnhsingh --------- Co-authored-by: Docs Bot <brace@langchain.dev>
Johannes du Plessis (johannes117)
pushed a commit
that referenced
this pull request
Aug 4, 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._ --- ## [0.1.52](deepagents-code==0.1.51...deepagents-code==0.1.52) (2026-08-04) ### Features - Hooks v2 is now generally available, with support for loading hooks from installed plugins. ([#5307](#5307), [#5198](#5198)) - Auto approval classifier configuration now supports selecting the classifier model and setting a review timeout. ([#5205](#5205), [#5302](#5302)) - HITL rejection reasons are now framed for the model, and the approval menu makes reject-with-feedback easier to discover. ([#5259](#5259), [#5260](#5260)) - Added a tri-state `DEEPAGENTS_CODE_ONBOARDING` environment variable. ([#5301](#5301)) - The `/model` footer Ctrl+N hint now follows the current display mode. ([#5247](#5247)) - The price catalog now refreshes hourly in the background. ([#5264](#5264)) - Updated recommendations to include DeepSeek V4 Flash 0731. ([#5244](#5244)) ### Bug Fixes - Fixed several Hooks v2 lifecycle issues: session-end teardown is now bounded, hooks refresh after cwd switches, malformed hook resumes are handled, hook stops surface without agent errors, and unused `SessionEndCause` members were removed. ([#5248](#5248), [#5249](#5249), [#5233](#5233), [#5276](#5276), [#5240](#5240)) - `PreCompact` now fires before auto-compaction. ([#5277](#5277)) _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
1 participant
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.
DEEPAGENTS_CODE_DEBUG_ONBOARDINGis nowDEEPAGENTS_CODE_ONBOARDING, and it works in both directions: set it to a falsy value to skip the first-run onboarding flow entirely (useful for fresh containers, CI, and provisioned machines), a truthy value to force it open on every interactive startup, or leave it unset for the existing first-run behavior.Previously the only knob was a debug-only override that could force onboarding on. There was no supported way to turn it off, so anyone provisioning a fresh instance had to pre-seed the internal completion marker file — an implementation detail that is not part of the documented surface.
should_run_onboardingnow reads the variable through the existingclassify_env_boolhelper so it resolves three ways: truthy forces the flow, falsy suppresses it, and unset (or an unrecognized token, which is logged) defers to the completion marker as before. Suppressing the flow does not write the marker, so removing the variable restores first-run behavior rather than silently consuming it.The config manifest entry moves from
debug.onboardingtostartup.onboardingand drops its static default, soconfigreports it as unset rather than implying a hardcodedfalse. It stays env-only, matching what the runtime actually reads.The old variable name is removed rather than aliased: it was documented as a debug-only knob, and keeping a second spelling would leave two names with different semantics.
Made by Open SWE