feat(code): first-class [retries] config - #3772
Merged
Merged
Conversation
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
[retries] config in config.toml[retries] config
1 task
Mason Daugherty (mdrxy)
marked this pull request as ready for review
June 10, 2026 21:16
Mason Daugherty (mdrxy)
added a commit
to langchain-ai/docs
that referenced
this pull request
Jun 10, 2026
Depends on langchain-ai/deepagents#3772 ## Description Documents the top-level `[retries]` section for Deep Agents Code, including global and per-provider examples, the precedence ladder, and `[retries.<provider>].param` for arbitrary providers or integrations whose retry constructor kwarg is not `max_retries`. ## Release Note none ## Test Plan - [ ] Reviewed the rendered MDX diff for the updated `Retries` subsection. Made by [Open SWE](https://openswe.vercel.app) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Mason Daugherty (mdrxy)
added a commit
that referenced
this pull request
Jun 11, 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). --- _Everything below this line will be the GitHub release body._ --- ## [0.1.13](deepagents-code==0.1.12...deepagents-code==0.1.13) (2026-06-11) ### Features * Pluggable third-party sandbox backends ([#3842](#3842)) ([2b635a7](2b635a7)) * Auto-install ripgrep on first run ([#3348](#3348)) ([fecf22b](fecf22b)) * `config` command and canonical config manifest ([#3763](#3763)) ([79899a3](79899a3)) * Confirm modal for `/install --package` ([#3840](#3840)) ([3d75026](3d75026)) * Copy focused input selection on `Ctrl+C` ([#3841](#3841)) ([99f782c](99f782c)) * `[retries]` config ([#3772](#3772)) ([9334d91](9334d91)) * Show connection state in the status bar ([#3710](#3710)) ([3e3e8fe](3e3e8fe)) * Surface LangSmith tracing projects in `LocalContextMiddleware` ([#3836](#3836)) ([676abec](676abec)) ### Bug Fixes * Add debug-log guidance for truncated startup errors ([#3849](#3849)) ([cd1ef30](cd1ef30)) * Drop lock-key events so Caps Lock in iTerm2 doesn't type ([#3855](#3855)) ([110f1a7](110f1a7)) * Hand pointer over splash tracing project link ([#3858](#3858)) ([ea7dae5](ea7dae5)) * Keep terminal-default theme on Esc in `/theme` selector ([#3854](#3854)) ([c3bc67b](c3bc67b)) * Preserve inherited `PYTHONPATH` for server subprocess ([#3833](#3833)) ([4689569](4689569)) * Resolve interpreter PTC allowlist against the runtime tool registry ([#3845](#3845)) ([c59a27e](c59a27e)) * Treat multi-line key-event pastes as one input ([#3856](#3856)) ([6bb15d4](6bb15d4)) --- _Everything above this line will be the GitHub release body._ --- > [!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: Mason Daugherty <github@mdrxy.com>
Marcelo5444
pushed a commit
to Marcelo5444/deepagents
that referenced
this pull request
Jul 30, 2026
[Docs](langchain-ai/docs#4318) Add configurable model retry counts for supported and custom dcode providers. --- Adds a typed top-level `[retries]` config and `--max-retries` override so a single transient provider error does not end a dcode run when users opt into retries. The retry config now applies to registered retry-capable providers and supports arbitrary chat model providers via `[retries.<provider>].param`, so users can name the constructor kwarg when it is not `max_retries`. Precedence is: CLI `--max-retries` > `--model-params` > provider `params` > provider `[retries]` > global `[retries]` > SDK default. Made by [Open SWE](https://openswe.vercel.app) --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Marcelo5444
pushed a commit
to Marcelo5444/deepagents
that referenced
this pull request
Jul 30, 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). --- _Everything below this line will be the GitHub release body._ --- ## [0.1.13](langchain-ai/deepagents@deepagents-code==0.1.12...deepagents-code==0.1.13) (2026-06-11) ### Features * Pluggable third-party sandbox backends ([langchain-ai#3842](langchain-ai#3842)) ([2b635a7](langchain-ai@2b635a7)) * Auto-install ripgrep on first run ([langchain-ai#3348](langchain-ai#3348)) ([fecf22b](langchain-ai@fecf22b)) * `config` command and canonical config manifest ([langchain-ai#3763](langchain-ai#3763)) ([79899a3](langchain-ai@79899a3)) * Confirm modal for `/install --package` ([langchain-ai#3840](langchain-ai#3840)) ([3d75026](langchain-ai@3d75026)) * Copy focused input selection on `Ctrl+C` ([langchain-ai#3841](langchain-ai#3841)) ([99f782c](langchain-ai@99f782c)) * `[retries]` config ([langchain-ai#3772](langchain-ai#3772)) ([9334d91](langchain-ai@9334d91)) * Show connection state in the status bar ([langchain-ai#3710](langchain-ai#3710)) ([3e3e8fe](langchain-ai@3e3e8fe)) * Surface LangSmith tracing projects in `LocalContextMiddleware` ([langchain-ai#3836](langchain-ai#3836)) ([676abec](langchain-ai@676abec)) ### Bug Fixes * Add debug-log guidance for truncated startup errors ([langchain-ai#3849](langchain-ai#3849)) ([cd1ef30](langchain-ai@cd1ef30)) * Drop lock-key events so Caps Lock in iTerm2 doesn't type ([langchain-ai#3855](langchain-ai#3855)) ([110f1a7](langchain-ai@110f1a7)) * Hand pointer over splash tracing project link ([langchain-ai#3858](langchain-ai#3858)) ([ea7dae5](langchain-ai@ea7dae5)) * Keep terminal-default theme on Esc in `/theme` selector ([langchain-ai#3854](langchain-ai#3854)) ([c3bc67b](langchain-ai@c3bc67b)) * Preserve inherited `PYTHONPATH` for server subprocess ([langchain-ai#3833](langchain-ai#3833)) ([4689569](langchain-ai@4689569)) * Resolve interpreter PTC allowlist against the runtime tool registry ([langchain-ai#3845](langchain-ai#3845)) ([c59a27e](langchain-ai@c59a27e)) * Treat multi-line key-event pastes as one input ([langchain-ai#3856](langchain-ai#3856)) ([6bb15d4](langchain-ai@6bb15d4)) --- _Everything above this line will be the GitHub release body._ --- > [!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: Mason Daugherty <github@mdrxy.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
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.
Docs
Add configurable model retry counts for supported and custom dcode providers.
Adds a typed top-level
[retries]config and--max-retriesoverride so a single transient provider error does not end a dcode run when users opt into retries.The retry config now applies to registered retry-capable providers and supports arbitrary chat model providers via
[retries.<provider>].param, so users can name the constructor kwarg when it is notmax_retries. Precedence is: CLI--max-retries>--model-params> providerparams> provider[retries]> global[retries]> SDK default.Made by Open SWE