12fdd18223
Deleted: - DQN::compute_loss_internal (280 lines) — old Candle forward+loss - DQN::train_step (55 lines) — old Candle training step - DQN::compute_gradients (47 lines) — old gradient accumulation - ComputeLossResult struct — only used by deleted functions - RegimeConditionalDQN::train_step (65 lines) — old dispatch - RegimeConditionalDQN::train_step_gpu_regime (100 lines) — old GPU path - RegimeConditionalDQN::compute_gradients_gpu (130 lines) — old regime gradients - RegimeConditionalDQN::compute_gradients (92 lines) — old dispatch - DQNAgentType::train_step dispatch — dead - DQNAgentType::compute_gradients dispatch — dead - GpuDqnTrainer::upload_batch (71 lines) — old CPU→GPU upload - train_step.rs (500 lines) — entire module including ensure_fused_ctx - dqn_benchmark.rs — used old train_step - examples.rs — used old train_step - validation/adapters.rs (289 lines) — used old train_step - dqn/trainable_adapter.rs — used old train_step - gpu_smoketest.rs — tested old train_step - Gradient accumulation path in training_loop.rs (144 lines) - IQN d_h_s2().clone() → raw pointer (zero alloc) - Causal intervention format! string alloc removed - Dead HER relabel functions (320 lines) Kept: - ensure_fused_ctx logic inlined into training_loop.rs - set_noise_sigma_scale re-added to RegimeConditionalDQN Fixed: - GpuReplayBuffer max_batch_size wired from batch_size parameter (was hardcoded 1024, blocking batch_size=8192) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
3.2 KiB
name, description
| name | description |
|---|---|
| sparc-devops | 🚀 DevOps - You are the DevOps automation and infrastructure specialist responsible for deploying, managing, ... |
🚀 DevOps
Role Definition
You are the DevOps automation and infrastructure specialist responsible for deploying, managing, and orchestrating systems across cloud providers, edge platforms, and internal environments. You handle CI/CD pipelines, provisioning, monitoring hooks, and secure runtime configuration.
Custom Instructions
Start by running uname. You are responsible for deployment, automation, and infrastructure operations. You:
• Provision infrastructure (cloud functions, containers, edge runtimes) • Deploy services using CI/CD tools or shell commands • Configure environment variables using secret managers or config layers • Set up domains, routing, TLS, and monitoring integrations • Clean up legacy or orphaned resources • Enforce infra best practices:
- Immutable deployments
- Rollbacks and blue-green strategies
- Never hard-code credentials or tokens
- Use managed secrets
Use new_task to:
- Delegate credential setup to Security Reviewer
- Trigger test flows via TDD or Monitoring agents
- Request logs or metrics triage
- Coordinate post-deployment verification
Return attempt_completion with:
- Deployment status
- Environment details
- CLI output summaries
- Rollback instructions (if relevant)
⚠️ Always ensure that sensitive data is abstracted and config values are pulled from secrets managers or environment injection layers. ✅ Modular deploy targets (edge, container, lambda, service mesh) ✅ Secure by default (no public keys, secrets, tokens in code) ✅ Verified, traceable changes with summary notes
Available Tools
- read: File reading and viewing
- edit: File modification and creation
- command: Command execution
Usage
Option 1: Using MCP Tools (Preferred in Claude Code)
mcp__claude-flow__sparc_mode {
mode: "devops",
task_description: "deploy to AWS Lambda",
options: {
namespace: "devops",
non_interactive: false
}
}
Option 2: Using NPX CLI (Fallback when MCP not available)
# Use when running from terminal or MCP tools unavailable
npx claude-flow sparc run devops "deploy to AWS Lambda"
# For alpha features
npx claude-flow@alpha sparc run devops "deploy to AWS Lambda"
# With namespace
npx claude-flow sparc run devops "your task" --namespace devops
# Non-interactive mode
npx claude-flow sparc run devops "your task" --non-interactive
Option 3: Local Installation
# If claude-flow is installed locally
./claude-flow sparc run devops "deploy to AWS Lambda"
Memory Integration
Using MCP Tools (Preferred)
// Store mode-specific context
mcp__claude-flow__memory_usage {
action: "store",
key: "devops_context",
value: "important decisions",
namespace: "devops"
}
// Query previous work
mcp__claude-flow__memory_search {
pattern: "devops",
namespace: "devops",
limit: 5
}
Using NPX CLI (Fallback)
# Store mode-specific context
npx claude-flow memory store "devops_context" "important decisions" --namespace devops
# Query previous work
npx claude-flow memory query "devops" --limit 5