fix(deepagents): interrupt_on must be a dict, not a list (fault-tolerance.mdx) - #4957
Merged
Naomi Pentrel (npentrel) merged 1 commit intoJul 26, 2026
Conversation
Contributor
|
Thanks for opening a docs PR, Yuva Prathima Sola (@prathima-sola)! When it's ready for review, please add the relevant reviewers:
|
Naomi Pentrel (npentrel)
approved these changes
Jul 26, 2026
Naomi Pentrel (npentrel)
left a comment
Naomi Pentrel (npentrel)
left a comment
Contributor
There was a problem hiding this comment.
Thank you!
Mason Daugherty (mdrxy)
added a commit
that referenced
this pull request
Aug 27, 2026
**Description:** Update approval-modes and goals-and-rubrics to current deepagents-code behavior: Auto GA without experimental gate (0.1.46), YOLO in the Shift+Tab cycle with `startup.yolo_switcher` opt-out (0.1.47), `[startup].recent` mode persistence (0.1.60), headless `-y`/`--yolo` warn-and-ignore (0.1.61), and `goals.auto_accept_criteria` (0.1.46). **Release Note:** Docs refreshed for approval modes and goal criteria auto-accept; the pages were stale on Auto's GA status and mode cycling. References langchain-ai/deepagents releases/issues #4957, #5035, #5665, #5750, #4940. Also reflects current `main`: `Shift+Tab` is the approval-mode cycle, and Auto permits ordinary instrumental steps while keeping high-risk effects explicitly gated. **Test Plan:** Verified every claim against deepagents main source (`approval_mode.py`, `config_manifest.py`, `model_config.py`, `main.py`, `app.py`) and CHANGELOG; `make lint_prose` passes on both changed files. ## Stack This is stack 2/4 and targets #5694 (`mdrxy/docs/dcode-configuration-backfill`). Made by [Open SWE](https://openswe.vercel.app/agents/0b56e89b-6aef-557e-9697-924077253ea3) --------- Co-authored-by: open-swe[bot] <open-swe@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
2 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.
Overview
interrupt_onin the "User-fixable" fault-tolerance example is passed as a list:but
create_deep_agent's real signature takes a dict:Reproduced with the exact snippet (real tools standing in for
send_email_tool/delete_record_tool):
The error gives no indication the actual problem is list-vs-dict, so
anyone copying this snippet hits a confusing failure with no fix path.
Same bug appears in the TypeScript block right below it
(
interruptOn: [...]).Fixed both to the dict form used everywhere else in the docs, and
verified the corrected version constructs the agent with no error.
Type of change
Type: Fix typo/bug/link/formatting
Related issues/PRs
None.