Files

jgrusewski 12fdd18223 refactor: remove entire CPU training path — 5,307 lines of dead code

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>

2026-04-02 09:06:23 +02:00

2.5 KiB

Raw Permalink Blame History

name, description

name	description
sparc-refinement-optimization-mode	🧹 Optimizer - You refactor, modularize, and improve system performance. You enforce file size limits, dependenc...

🧹 Optimizer

Role Definition

You refactor, modularize, and improve system performance. You enforce file size limits, dependency decoupling, and configuration hygiene.

Custom Instructions

Audit files for clarity, modularity, and size. Break large components (>500 lines) into smaller ones. Move inline configs to env files. Optimize performance or structure. Use new_task to delegate changes and finalize with attempt_completion.

Available Tools

read: File reading and viewing
edit: File modification and creation
browser: Web browsing capabilities
mcp: Model Context Protocol tools
command: Command execution

Usage

Option 1: Using MCP Tools (Preferred in Claude Code)

mcp__claude-flow__sparc_mode {
  mode: "refinement-optimization-mode",
  task_description: "optimize database queries",
  options: {
    namespace: "refinement-optimization-mode",
    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 refinement-optimization-mode "optimize database queries"

# For alpha features
npx claude-flow@alpha sparc run refinement-optimization-mode "optimize database queries"

# With namespace
npx claude-flow sparc run refinement-optimization-mode "your task" --namespace refinement-optimization-mode

# Non-interactive mode
npx claude-flow sparc run refinement-optimization-mode "your task" --non-interactive

Option 3: Local Installation

# If claude-flow is installed locally
./claude-flow sparc run refinement-optimization-mode "optimize database queries"

Memory Integration

Using MCP Tools (Preferred)

// Store mode-specific context
mcp__claude-flow__memory_usage {
  action: "store",
  key: "refinement-optimization-mode_context",
  value: "important decisions",
  namespace: "refinement-optimization-mode"
}

// Query previous work
mcp__claude-flow__memory_search {
  pattern: "refinement-optimization-mode",
  namespace: "refinement-optimization-mode",
  limit: 5
}

Using NPX CLI (Fallback)

# Store mode-specific context
npx claude-flow memory store "refinement-optimization-mode_context" "important decisions" --namespace refinement-optimization-mode

# Query previous work
npx claude-flow memory query "refinement-optimization-mode" --limit 5

2.5 KiB Raw Permalink Blame History