[PR #459] [MERGED] fix: skill loading should default to 1000 lines #482

Closed
opened 2026-06-05 17:23:21 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/deepagentsjs/pull/459
Author: @open-swe[bot]
Created: 4/14/2026
Status: Merged
Merged: 4/14/2026
Merged by: @hntrl

Base: mainHead: open-swe/1972e1c7-0b3c-ef27-164d-efd93e8f48f3


📝 Commits (4)

  • 8bb8aa7 fix: skill loading prompt should instruct agents to use limit=1000 when reading skill files
  • 257be04 fix: extract skill read limit into constant and use context utility for skills system prompt
  • 5496a94 fix: also update fs.ts tool descriptions to interpolate DEFAULT_READ_LINE_LIMIT instead of hardcoding 100
  • cf8d5c0 chore: add changeset for skill loading limit fix

📊 Changes

3 files changed (+43 additions, -33 deletions)

View changed files

.changeset/skill-loading-limit.md (+5 -0)
📝 libs/deepagents/src/middleware/fs.ts (+5 -5)
📝 libs/deepagents/src/middleware/skills.ts (+33 -28)

📄 Description

Description

Ports the skill loading fix from the Python SDK (langchain-ai/deepagents#2721) to JS. The system prompt now instructs agents to pass limit=1000 when reading skill files via read_file, since the default of 100 lines is too small for most skill files.

Test Plan

  • Verify skill loading prompt includes limit=1000 instruction

Opened collaboratively by Sydney Runkle and open-swe.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/deepagentsjs/pull/459 **Author:** [@open-swe[bot]](https://github.com/apps/open-swe) **Created:** 4/14/2026 **Status:** ✅ Merged **Merged:** 4/14/2026 **Merged by:** [@hntrl](https://github.com/hntrl) **Base:** `main` ← **Head:** `open-swe/1972e1c7-0b3c-ef27-164d-efd93e8f48f3` --- ### 📝 Commits (4) - [`8bb8aa7`](https://github.com/langchain-ai/deepagentsjs/commit/8bb8aa7bc13fb748ada0cabb27058460ef1baec3) fix: skill loading prompt should instruct agents to use limit=1000 when reading skill files - [`257be04`](https://github.com/langchain-ai/deepagentsjs/commit/257be04bdd1ac999bbef60b21a2c3f8781863e61) fix: extract skill read limit into constant and use context utility for skills system prompt - [`5496a94`](https://github.com/langchain-ai/deepagentsjs/commit/5496a9419082a3b31dadc903110af877dc404b92) fix: also update fs.ts tool descriptions to interpolate DEFAULT_READ_LINE_LIMIT instead of hardcoding 100 - [`cf8d5c0`](https://github.com/langchain-ai/deepagentsjs/commit/cf8d5c039794f1763fd011d3256522ddeb9f291b) chore: add changeset for skill loading limit fix ### 📊 Changes **3 files changed** (+43 additions, -33 deletions) <details> <summary>View changed files</summary> ➕ `.changeset/skill-loading-limit.md` (+5 -0) 📝 `libs/deepagents/src/middleware/fs.ts` (+5 -5) 📝 `libs/deepagents/src/middleware/skills.ts` (+33 -28) </details> ### 📄 Description ## Description Ports the skill loading fix from the Python SDK (langchain-ai/deepagents#2721) to JS. The system prompt now instructs agents to pass `limit=1000` when reading skill files via `read_file`, since the default of 100 lines is too small for most skill files. ## Test Plan - [ ] Verify skill loading prompt includes `limit=1000` instruction _Opened collaboratively by Sydney Runkle and open-swe._ --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 17:23:21 -04:00
yindo closed this issue 2026-06-05 17:23:21 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/deepagentsjs#482