Conversation
…at/capabilities
…at/capabilities
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds integration support for Hermes Agent, nanobot, and OpenClaw, including configuration files, installation scripts, and integration tests. It also introduces new capabilities for code generation, document research, financial research, and video generation. My feedback highlights that several integration tests and documentation examples use invalid, future-dated arXiv URLs that will cause failures. Additionally, I suggested improving the robustness of the installation scripts by replacing error suppression with explicit directory checks.
|
|
||
| r = await call_tool(session, 'submit_doc_research_task', { | ||
| 'query': 'Summarize the key contributions of this paper', | ||
| 'urls': 'https://arxiv.org/abs/2504.17432', |
There was a problem hiding this comment.
This test uses a URL for an arXiv paper from the future (April 2025), which does not exist. This will cause the test to fail. Please replace it with a URL of a real, existing paper to ensure the test is valid.
|
|
||
| r = await call_tool(session, 'submit_doc_research_task', { | ||
| 'query': 'Summarize the key contributions of this paper', | ||
| 'urls': 'https://arxiv.org/abs/2504.17432', |
There was a problem hiding this comment.
This test uses a URL for an arXiv paper from the future (April 2025), which does not exist. This will cause the test to fail. Please replace it with a URL of a real, existing paper to ensure the test is valid.
|
|
||
| r = await call_tool(session, 'submit_doc_research_task', { | ||
| 'query': 'Summarize the key contributions of this paper', | ||
| 'urls': 'https://arxiv.org/abs/2504.17432', |
There was a problem hiding this comment.
This test uses a URL for an arXiv paper from the future (April 2025), which does not exist. This will cause the test to fail. Please replace it with a URL of a real, existing paper to ensure the test is valid.
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" 2>/dev/null || true | ||
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" 2>/dev/null || true |
There was a problem hiding this comment.
The use of 2>/dev/null || true is not robust. It suppresses all errors from cp, not just 'file not found', and prevents the script from failing even if there are permission issues. A safer approach is to explicitly check if the source directories exist before copying.
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" 2>/dev/null || true | |
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" 2>/dev/null || true | |
| if [ -d "$SKILL_SRC/references" ]; then | |
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" | |
| fi | |
| if [ -d "$SKILL_SRC/scripts" ]; then | |
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" | |
| fi |
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" 2>/dev/null || true | ||
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" 2>/dev/null || true |
There was a problem hiding this comment.
The use of 2>/dev/null || true is not robust. It suppresses all errors from cp, not just 'file not found', and prevents the script from failing even if there are permission issues. A safer approach is to explicitly check if the source directories exist before copying.
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" 2>/dev/null || true | |
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" 2>/dev/null || true | |
| if [ -d "$SKILL_SRC/references" ]; then | |
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" | |
| fi | |
| if [ -d "$SKILL_SRC/scripts" ]; then | |
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" | |
| fi |
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" 2>/dev/null || true | ||
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" 2>/dev/null || true |
There was a problem hiding this comment.
The use of 2>/dev/null || true is not robust. It suppresses all errors from cp, not just 'file not found', and prevents the script from failing even if there are permission issues. A safer approach is to explicitly check if the source directories exist before copying.
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" 2>/dev/null || true | |
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" 2>/dev/null || true | |
| if [ -d "$SKILL_SRC/references" ]; then | |
| cp -r "$SKILL_SRC/references" "$SKILL_DST/" | |
| fi | |
| if [ -d "$SKILL_SRC/scripts" ]; then | |
| cp -r "$SKILL_SRC/scripts" "$SKILL_DST/" | |
| fi |
| | Deep Research (async) | 20-60 min | Research "the current state of AI agent frameworks in 2026" — submit as a background task and tell me when it's done. | | ||
| | Code Generation (async) | 10-30 min | Generate a todo app with React frontend, Express backend, and SQLite. | | ||
| | Financial Research (async) | 20-60 min | Analyze CATL (300750.SZ) over the past four quarters. | | ||
| | Document Research (async) | 1-20 min | Analyze this paper: [https://arxiv.org/pdf/2504.17432](https://arxiv.org/pdf/2504.17432) | |
There was a problem hiding this comment.
The example test prompt for Document Research uses a URL for an arXiv paper from the future (April 2025). This link is invalid and will cause the example to fail. Please replace it with a URL of a real, existing paper.
| **Single document analysis:** | ||
| ``` | ||
| submit_doc_research_task( | ||
| query="Deeply analyze and summarize the following document", | ||
| urls="https://arxiv.org/pdf/2504.17432" | ||
| ) | ||
| ``` | ||
|
|
||
| **Multi-document comparison:** | ||
| ``` | ||
| submit_doc_research_task( | ||
| query="Compare Qwen3 and Qwen2.5, what optimizations are there?", | ||
| urls="https://arxiv.org/abs/2505.09388\nhttps://arxiv.org/abs/2412.15115" | ||
| ) |
There was a problem hiding this comment.
The example URLs in this documentation point to arXiv papers from the future (e.g., 2025, 2024). These links are invalid and will cause the examples to fail. Please replace them with URLs of real, existing papers to ensure the documentation is accurate and helpful.
1 participant
Change Summary
Related issue number
Checklist
pre-commit installandpre-commit run --all-filesbefore git commit, and passed lint check.