菜单
Debug failed/issue tasks from Beam.ai using Langfuse traces. Load when user says "debug issue tasks", "check failed tasks", "why did task fail", "task errors", "debug agent", or needs to investigate task failures.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | beam-debug-issue-tasks |
| description | Debug failed/issue tasks from Beam.ai using Langfuse traces. Load when user says "debug issue tasks", "check failed tasks", "why did task fail", "task errors", "debug agent", or needs to investigate task failures. |
Debug failed Beam.ai tasks using Langfuse traces.
.env file at project root:
# Beam.ai - BID instance
BEAM_API_KEY=your_bid_api_key
BEAM_WORKSPACE_ID=your_bid_workspace_id
# Beam.ai - Prod instance
BEAM_API_KEY_PROD=your_prod_api_key
BEAM_WORKSPACE_ID_PROD=your_prod_workspace_id
# Langfuse (self-hosted)
LANGFUSE_PUBLIC_KEY=pk-lf-...
LANGFUSE_SECRET_KEY=sk-lf-...
LANGFUSE_HOST=https://tracing.beamstudio.ai
Dependencies: pip install requests python-dotenv
# List issue tasks (default: last 1 day, BID workspace)
python 03-skills/beam-debug-issue-tasks/scripts/debug_issue_tasks.py <agent_id>
# Debug specific task with full trace analysis
python 03-skills/beam-debug-issue-tasks/scripts/debug_issue_tasks.py <agent_id> --task-id <task_id>
# Use prod workspace
python 03-skills/beam-debug-issue-tasks/scripts/debug_issue_tasks.py <agent_id> --workspace prod
| Workspace | API Endpoint | Langfuse Project |
|---|---|---|
bid (default) | api.bid.beamstudio.ai | cmauxbgww000582ry4644c2qr |
prod | api.beamstudio.ai | clw5gbhuy0003u3rv4jzzoesh |
Tasks are flagged as "issue" if status is:
FAILED - Execution failedERROR - Processing errorSTOPPED - Condition failedCANCELLED - User cancelledTIMEOUT - Execution timeoutUSER_INPUT_REQUIRED - Missing input dataReports saved to: 04-workspace/agents/{agent_name}/debug/
Format: Smart Brevity (headline, takeaway, why it matters, details, fix)
Key spans analyzed:
ParameterSelection/v2 - How parameters were matchedExecuteGPT_Tool/v1 - Tool execution reasoningNodeSelection:EdgeEvaluation/v1 - Routing decisionsTaskSuccessCriteriaCheck/v1 - Why task stopped| Flag | Description | Default |
|---|---|---|
agent_id | Beam agent ID (required) | - |
--workspace, -w | Workspace: bid or prod | bid |
--days, -d | Look back period (1, 3, 7, 14, 30) | 1 |
--task-id, -t | Debug specific task ID | - |
--summary, -s | Show grouped summary | false |
--limit, -l | Max tasks to show | 10 |
--output, -o | Save to JSON file | - |
--no-trace | Skip Langfuse lookup | false |
# Task stopped: condition failed
Checklist evaluation: subfolder must equal 'Schreiben Schuldner' but was null.
**Why it matters**: This task did not complete successfully and may need attention.
**The details**:
- **Status**: `STOPPED`
- **Task**: `ab3cbbb8-28da-41aa-b726-25931d14d7d4`
- **Latency**: 159.6s
- **Cost**: $0.1043
**Key spans**:
- NodeSelection:EdgeEvaluation/v1 (23.4s)
- TaskSuccessCriteriaCheck/v1 (7.2s)
**Root cause**:
> The criterion is not met because subfolder is not set to required value.
**Fix**: Review the condition that stopped execution. Check if input data meets requirements.
Each report includes direct links:
| Error | Solution |
|---|---|
BEAM_API_KEY not found | Add to .env |
Invalid workspace | Check workspace parameter (bid/prod) |
No traces found | Verify agent has Langfuse integration |
401 Unauthorized | Verify API keys |
beam-get-agent-analytics - Performance metricsbeam-create-agent-task - Create test tasksbeam-list-agents - List available agentsConnect to any Airtable base by name. Load when user mentions 'airtable', 'connect airtable', 'setup airtable', 'query [base-name]', 'add to [table]', 'airtable bases', or any base name from persistent context. Meta-skill that discovers workspace, caches schemas, and routes to appropriate operations.
Shared resource library for Airtable integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, field types) and scripts used by airtable-connect, airtable-query, and airtable-sync.
Connect to Beam AI workspace for agent management. Load when user mentions 'beam', 'beam agent', 'beam task', 'beam analytics', 'list agents', 'create task', or any Beam AI operations. Meta-skill that validates config, discovers agents, and routes to appropriate operations.
Shared resource library for Beam AI integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by beam-connect and individual Beam skills.
Read, send, and manage Gmail emails. Load when user mentions 'gmail', 'email', 'send email', 'check email', 'inbox', 'draft', or references sending/reading emails.
Read, create, and manage Google Calendar events. Load when user mentions 'google calendar', 'calendar', 'schedule', 'meeting', 'event', 'appointment', 'book time', 'check availability', 'find slots', 'free time', or references scheduling/calendar operations.