feat(talon): DEEPAGENTS_TALON_RECURSION_LIMIT env var - #4354
Merged
John Kennedy (jkennedyvz) merged 1 commit intoJun 28, 2026
Conversation
github-actions
Bot
added
feature
John Kennedy (jkennedyvz)
marked this pull request as ready for review
June 28, 2026 22:17
Expose `DEEPAGENTS_TALON_RECURSION_LIMIT` so operators can tune the per-invocation graph recursion limit without changing code. When set, it overrides the caller-supplied `recursion_limit`; otherwise the existing default applies. The default recursion limit bumps from `150` to `500` to match the new documented default in the env example, giving longer-running agents more room before hitting the limit. This is a behavior change only for code paths that relied on the constant default — explicit `recursion_limit=` call sites are unaffected, and the env var takes precedence over both. The existing positive-int env parsing for `DEEPAGENTS_TALON_CONTEXT_SIZE` is extracted into a shared `_positive_int_from_env` helper so both keys share the same validation and error messaging. Covers default, env override, env-beats-explicit-arg, and invalid-value cases with unit tests. Adds the variable to the Talon env example and documents it in the package README.
John Kennedy (jkennedyvz)
force-pushed
the
jkennedyvz/talon/recursion-limit-env
branch
from
June 28, 2026 22:18
7c8469c to
9d56a8e
Compare
John Kennedy (jkennedyvz)
deleted the
jkennedyvz/talon/recursion-limit-env
branch
June 28, 2026 22:21
This was referenced Jun 28, 2026
John Kennedy (jkennedyvz)
pushed a commit
that referenced
this pull request
Jun 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._ --- ## [0.0.2](deepagents-talon==0.0.1...deepagents-talon==0.0.2) (2026-06-30) ### Features * **talon:** `DEEPAGENTS_TALON_RECURSION_LIMIT` env var ([#4354](#4354)) ([82d1eac](82d1eac)) * **talon:** add reaction approval routing ([#4345](#4345)) ([3fe8c0c](3fe8c0c)) * **talon:** add Telegram channel adapter, CLI wiring, and offset persistence ([#4097](#4097)) ([7c87cec](7c87cec)) * **talon:** add tool approval env override ([#4349](#4349)) ([d26481d](d26481d)) * **talon:** audit reaction approval attempts ([#4348](#4348)) ([d7895c4](d7895c4)) * **talon:** ingest Telegram approval reactions ([#4346](#4346)) ([437af0b](437af0b)) ### Bug Fixes * **talon:** default workspace to current directory ([#4099](#4099)) ([5e337ae](5e337ae)) --- _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>
Marcelo5444
pushed a commit
to Marcelo5444/deepagents
that referenced
this pull request
Jul 30, 2026
…#4354) Exposes `DEEPAGENTS_TALON_RECURSION_LIMIT` so operators can tune the per-invocation graph recursion limit from the environment without changing code. When set, it overrides the caller-supplied `recursion_limit`; otherwise the existing default applies. The default recursion limit bumps from `150` to `500` to match the new documented default in the env example, giving longer-running agents more headroom before hitting the limit. Explicit `recursion_limit=` call sites are unaffected, and the env var takes precedence over both. --- **Changes** - Adds `RECURSION_LIMIT_ENV_KEY` and `_recursion_limit_from_env` to `DeepAgentRuntime`, resolved in the constructor so an invalid value fails fast at construction (matching the existing `recursion_limit <= 0` guard). - Extracts the existing positive-int env parsing for `DEEPAGENTS_TALON_CONTEXT_SIZE` into a shared `_positive_int_from_env` helper so both keys share the same validation and error messaging. - Bumps `DEFAULT_RECURSION_LIMIT` from `150` to `500`. - Adds `DEEPAGENTS_TALON_RECURSION_LIMIT=500` to the Talon env example. - Documents the variable in the package README. **API impact** The `recursion_limit` constructor parameter is keyword-only and unchanged in position/name; only its default value moved from `150` to `500`. The env var takes precedence, then the explicit arg, then the default. No breaking signature changes. **Tests** Unit tests cover: default when env unset, env override, env-beats-explicit-arg, and invalid-value rejection at construction. Full Talon suite passes (`178 passed`); the two pre-existing `ty` diagnostics in `speech.py` are unrelated to this change. Co-authored-by: Deep Agent <agent@deepagents.dev>
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._ --- ## [0.0.2](langchain-ai/deepagents@deepagents-talon==0.0.1...deepagents-talon==0.0.2) (2026-06-30) ### Features * **talon:** `DEEPAGENTS_TALON_RECURSION_LIMIT` env var ([langchain-ai#4354](langchain-ai#4354)) ([82d1eac](langchain-ai@82d1eac)) * **talon:** add reaction approval routing ([langchain-ai#4345](langchain-ai#4345)) ([3fe8c0c](langchain-ai@3fe8c0c)) * **talon:** add Telegram channel adapter, CLI wiring, and offset persistence ([langchain-ai#4097](langchain-ai#4097)) ([7c87cec](langchain-ai@7c87cec)) * **talon:** add tool approval env override ([langchain-ai#4349](langchain-ai#4349)) ([d26481d](langchain-ai@d26481d)) * **talon:** audit reaction approval attempts ([langchain-ai#4348](langchain-ai#4348)) ([d7895c4](langchain-ai@d7895c4)) * **talon:** ingest Telegram approval reactions ([langchain-ai#4346](langchain-ai#4346)) ([437af0b](langchain-ai@437af0b)) ### Bug Fixes * **talon:** default workspace to current directory ([langchain-ai#4099](langchain-ai#4099)) ([5e337ae](langchain-ai@5e337ae)) --- _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>
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.
Exposes
DEEPAGENTS_TALON_RECURSION_LIMITso operators can tune the per-invocation graph recursion limit from the environment without changing code. When set, it overrides the caller-suppliedrecursion_limit; otherwise the existing default applies.The default recursion limit bumps from
150to500to match the new documented default in the env example, giving longer-running agents more headroom before hitting the limit. Explicitrecursion_limit=call sites are unaffected, and the env var takes precedence over both.Changes
RECURSION_LIMIT_ENV_KEYand_recursion_limit_from_envtoDeepAgentRuntime, resolved in the constructor so an invalid value fails fast at construction (matching the existingrecursion_limit <= 0guard).DEEPAGENTS_TALON_CONTEXT_SIZEinto a shared_positive_int_from_envhelper so both keys share the same validation and error messaging.DEFAULT_RECURSION_LIMITfrom150to500.DEEPAGENTS_TALON_RECURSION_LIMIT=500to the Talon env example.API impact
The
recursion_limitconstructor parameter is keyword-only and unchanged in position/name; only its default value moved from150to500. The env var takes precedence, then the explicit arg, then the default. No breaking signature changes.Tests
Unit tests cover: default when env unset, env override, env-beats-explicit-arg, and invalid-value rejection at construction. Full Talon suite passes (
178 passed); the two pre-existingtydiagnostics inspeech.pyare unrelated to this change.