Skip to content

fix(sdk,code): use file_path kwarg in read_file examples - #3630

Merged
Mason Daugherty (mdrxy) merged 1 commit into
mainfrom
mdrxy/readfile-desc-fix
May 27, 2026
Merged

fix(sdk,code): use file_path kwarg in read_file examples#3630
Mason Daugherty (mdrxy) merged 1 commit into
mainfrom
mdrxy/readfile-desc-fix

Conversation

@mdrxy

Copy link
Copy Markdown
Member

Closes #3568


Tool description and system-prompt examples for read_file showed the kwarg as path (read_file(path, limit=100)) while the underlying ReadFileSchema requires file_path. Frontier models tolerate the contradiction by deferring to the schema; open-weight models (qwen3, gemma4) copy the example verbatim and every call fails with file_path: Field required.

Changes

  • Rewrite the three text-mode example signatures in READ_FILE_TOOL_DESCRIPTION to read_file(file_path="...", …), matching the multimodal example already present.
  • Update the workflow line in SKILLS_SYSTEM_PROMPT (SkillsMiddleware) to use read_file(file_path="...", limit=1000).
  • Apply the same fix to deepagents-code's system_prompt.md and the format_tool_display docstring example.

@github-actions github-actions Bot changed the title fix(deepagents,code): use file_path kwarg in read_file examples fix(sdk,code): use file_path kwarg in read_file examples May 27, 2026
@github-actions github-actions Bot added dcode Related to `deepagents-code` deepagents Related to the `deepagents` SDK / agent harness fix A bug fix (PATCH) internal User is a member of the `langchain-ai` GitHub organization size: XS < 50 LOC labels May 27, 2026
@mdrxy
Mason Daugherty (mdrxy) merged commit 97946ee into main May 27, 2026
49 checks passed
@mdrxy
Mason Daugherty (mdrxy) deleted the mdrxy/readfile-desc-fix branch May 27, 2026 16:06
Mason Daugherty (mdrxy) added a commit that referenced this pull request May 28, 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._

---


##
[0.6.5](deepagents==0.6.4...deepagents==0.6.5)
(2026-05-28)

### Features

* `RubricMiddleware` for self-evaluated agent iteration
([#3529](#3529))
([5b8d44d](5b8d44d))
* Log when grep falls back from ripgrep
([#3593](#3593))
([379b1ff](379b1ff))

### Bug Fixes

* Use `file_path` kwarg in `read_file` examples
([#3630](#3630))
([97946ee](97946ee))
* `read_file` pagination skipping lines after wrapping
([#3641](#3641))
([390551d](390551d))
* Handle `None` state in messages delta reducer
([#3636](#3636))
([5a6d920](5a6d920))
* Return grep errors for sandbox exec failures
([#3637](#3637))
([f87d61f](f87d61f))

---

_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
…in-ai#3630)

Closes langchain-ai#3568

---

Tool description and system-prompt examples for `read_file` showed the
kwarg as `path` (`read_file(path, limit=100)`) while the underlying
`ReadFileSchema` requires `file_path`. Frontier models tolerate the
contradiction by deferring to the schema; open-weight models (qwen3,
gemma4) copy the example verbatim and every call fails with `file_path:
Field required`.

## Changes
- Rewrite the three text-mode example signatures in
`READ_FILE_TOOL_DESCRIPTION` to `read_file(file_path="...", …)`,
matching the multimodal example already present.
- Update the workflow line in `SKILLS_SYSTEM_PROMPT`
(`SkillsMiddleware`) to use `read_file(file_path="...", limit=1000)`.
- Apply the same fix to `deepagents-code`'s `system_prompt.md` and the
`format_tool_display` docstring example.
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._

---


##
[0.6.5](langchain-ai/deepagents@deepagents==0.6.4...deepagents==0.6.5)
(2026-05-28)

### Features

* `RubricMiddleware` for self-evaluated agent iteration
([langchain-ai#3529](langchain-ai#3529))
([5b8d44d](langchain-ai@5b8d44d))
* Log when grep falls back from ripgrep
([langchain-ai#3593](langchain-ai#3593))
([379b1ff](langchain-ai@379b1ff))

### Bug Fixes

* Use `file_path` kwarg in `read_file` examples
([langchain-ai#3630](langchain-ai#3630))
([97946ee](langchain-ai@97946ee))
* `read_file` pagination skipping lines after wrapping
([langchain-ai#3641](langchain-ai#3641))
([390551d](langchain-ai@390551d))
* Handle `None` state in messages delta reducer
([langchain-ai#3636](langchain-ai#3636))
([5a6d920](langchain-ai@5a6d920))
* Return grep errors for sandbox exec failures
([langchain-ai#3637](langchain-ai#3637))
([f87d61f](langchain-ai@f87d61f))

---

_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>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

dcode Related to `deepagents-code` deepagents Related to the `deepagents` SDK / agent harness fix A bug fix (PATCH) internal User is a member of the `langchain-ai` GitHub organization size: XS < 50 LOC

Projects

None yet

Development

Successfully merging this pull request may close these issues.

read_file tool description contradicts ReadFileSchema

1 participant