feat(init-deep): restructure Phase 1 to fire background explore first, then LSP codemap

- Step 1: Fire ALL background explore agents immediately (non-blocking)
- Step 2: Main session builds codemap understanding using LSP tools while background runs
- Step 3: Collect background results after main session analysis

This maximizes throughput by having agents discover patterns while the main session
analyzes code structure semantically via LSP.

Author: sisyphus-dev-ai

src/features/builtin-commands/templates/init-deep.ts

@@ -46,28 +46,18 @@ TodoWrite([
 
 **Mark "p1-analysis" as in_progress.**
 
-Launch **ALL tasks simultaneously**:
-
-<parallel-tasks>
-
-### Structural Analysis (bash - run in parallel)
-\`\`\`bash
-# Task A: Directory depth analysis
-find . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/__pycache__/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c
-
-# Task B: File count per directory  
-find . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/__pycache__/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30
+<critical>
+**EXECUTION PATTERN**: Fire background agents FIRST (non-blocking), then main session builds codemap understanding using LSP tools in parallel. This maximizes throughput—agents discover while you analyze.
+</critical>
 
-# Task C: Code concentration
-find . -type f \\( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" -o -name "*.go" -o -name "*.rs" -o -name "*.java" \\) -not -path '*/node_modules/*' -not -path '*/venv/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20
+---
 
-# Task D: Existing knowledge files
-find . -type f \\( -name "AGENTS.md" -o -name "CLAUDE.md" \\) -not -path '*/node_modules/*' 2>/dev/null
-\`\`\`
+### Step 1: Fire Background Explore Agents (IMMEDIATELY)
 
-### Context Gathering (Explore agents - background_task in parallel)
+Fire ALL background tasks at once. They run asynchronously—don't wait for results yet.
 
 \`\`\`
+// Fire immediately - these run in parallel, non-blocking
 background_task(agent="explore", prompt="Project structure: PREDICT standard {lang} patterns → FIND package.json/pyproject.toml/go.mod → REPORT deviations only")
 
 background_task(agent="explore", prompt="Entry points: PREDICT typical (main.py, index.ts) → FIND actual → REPORT non-standard organization")
@@ -81,32 +71,56 @@ background_task(agent="explore", prompt="Build/CI: FIND .github/workflows, Makef
 background_task(agent="explore", prompt="Test patterns: FIND pytest.ini, jest.config, test structure → REPORT unique testing conventions")
 \`\`\`
 
-### Code Intelligence Analysis (LSP tools - run in parallel)
+---
+
+### Step 2: Main Session Codemap Understanding (while background runs)
+
+While background agents discover patterns, main session builds codemap understanding using direct tools.
+
+<parallel-tools>
+
+#### Structural Analysis (bash)
+\`\`\`bash
+# Task A: Directory depth analysis
+find . -type d -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/__pycache__/*' -not -path '*/dist/*' -not -path '*/build/*' | awk -F/ '{print NF-1}' | sort -n | uniq -c
+
+# Task B: File count per directory  
+find . -type f -not -path '*/\\.*' -not -path '*/node_modules/*' -not -path '*/venv/*' -not -path '*/__pycache__/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -30
+
+# Task C: Code concentration
+find . -type f \\( -name "*.py" -o -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.jsx" -o -name "*.go" -o -name "*.rs" -o -name "*.java" \\) -not -path '*/node_modules/*' -not -path '*/venv/*' | sed 's|/[^/]*$||' | sort | uniq -c | sort -rn | head -20
+
+# Task D: Existing knowledge files
+find . -type f \\( -name "AGENTS.md" -o -name "CLAUDE.md" \\) -not -path '*/node_modules/*' 2>/dev/null
+\`\`\`
+
+#### LSP Codemap Analysis (main session - semantic understanding)
 
-LSP provides semantic understanding beyond text search. Use for accurate code mapping.
+LSP provides semantic understanding beyond text search. Build the codemap while background agents run.
 
 \`\`\`
-# Step 1: Check LSP availability
+# Check LSP availability first
 lsp_servers()  # Verify language server is available
 
-# Step 2: Analyze entry point files (run in parallel)
-# Find entry points first, then analyze each with lsp_document_symbols
+# Analyze entry point files (run in parallel)
 lsp_document_symbols(filePath="src/index.ts")      # Main entry
 lsp_document_symbols(filePath="src/main.py")       # Python entry
 lsp_document_symbols(filePath="cmd/main.go")       # Go entry
 
-# Step 3: Discover key symbols across workspace (run in parallel)
+# Discover key symbols across workspace (run in parallel)
 lsp_workspace_symbols(filePath=".", query="class")      # All classes
 lsp_workspace_symbols(filePath=".", query="interface")  # All interfaces
 lsp_workspace_symbols(filePath=".", query="function")   # Top-level functions
 lsp_workspace_symbols(filePath=".", query="type")       # Type definitions
 
-# Step 4: Analyze symbol centrality (for top 5-10 key symbols)
+# Analyze symbol centrality (for top 5-10 key symbols)
 # High reference count = central/important concept
 lsp_find_references(filePath="src/index.ts", line=X, character=Y)  # Main export
 \`\`\`
 
-#### LSP Analysis Output Format
+</parallel-tools>
+
+#### Codemap Output Format
 
 \`\`\`
 CODE_INTELLIGENCE = {
@@ -125,12 +139,21 @@ CODE_INTELLIGENCE = {
 \`\`\`
 
 <critical>
-**LSP Fallback**: If LSP unavailable (no server installed), skip this section and rely on explore agents + AST-grep patterns.
+**LSP Fallback**: If LSP unavailable (no server installed), skip LSP section and rely on explore agents + AST-grep patterns.
 </critical>
 
-</parallel-tasks>
+---
+
+### Step 3: Collect Background Results
+
+After main session analysis complete, collect background agent results:
+
+\`\`\`
+// Collect all background_task results
+// background_output(task_id="...") for each fired task
+\`\`\`
 
-**Collect all results. Mark "p1-analysis" as completed.**
+**Merge bash + LSP + background agent findings. Mark "p1-analysis" as completed.**
 
 ---