refactor: modularize configuration system and implement safe atomic file I/O

.code-reducer.yaml

@@ -2,6 +2,26 @@ model_id: ornith:9b
 ollama_base_url: http://localhost:11434
 ollama_num_ctx: 20000
 docs_dir: wiki
+
+system_prompt: |
+    You are Code-Reducer, an expert technical writer and code analyzer. Your job is to strictly follow instructions. You do not yap, you do not write filler.
+    DEFENSIVE RULES: 1. Do NOT use absolute terms ('always', 'never', 'zero') unless explicitly proven. 2. Do NOT guess downstream consequences or invent unhandled paths. If an error is swallowed, just say it is swallowed. 3. Do NOT name standard library packages unless explicitly stated in the source text. 4. Only report facts you are 100% sure about.
+
+module_synthesis_prompt: |-
+    Task: Write a technical documentation page for a code module based on the provided list of its internal components.
+    Rule 1: Group related functions and classes under appropriate Markdown headings.
+    Rule 2: Explain the responsibility of the module and the data flow.
+    Rule 3: Keep it highly technical and dense.
+
+architecture_prompt: |-
+    Task: Write a global architecture or quickstart document based on the module summaries.
+    Rule 1: Explain the system boundaries and how the modules interact.
+    Rule 2: Provide a dense, developer-friendly overview.
+
+file_fact_consolidation_prompt: |-
+    You are a specialized code documentation assistant.
+    Consolidate, deduplicate and merge the following facts extracted from different chunks of the same file into a single, cohesive summary.
+
 extraction_steps:
     - name: API_SIGNATURES
       prompt: |-
@@ -19,45 +39,11 @@ extraction_steps:
       prompt: |-
         Task: Analyze side effects and error handling.
         Output: Detail how this code communicates with the outside world (I/O like network, disk, DB) and how it handles/returns errors (wrap, sentinel, panic).
+
 ignore:
-    - .git
-    - node_modules
-    - bower_components
-    - dist
-    - build
-    - cache
-    - __pycache__
-    - .pytest_cache
-    - .mypy_cache
-    - .tox
-    - venv
-    - .venv
-    - code-reducer
-    - .gemini
-    - .code-reducer.yaml
-    - .code-reducer.lock
-    - AGENTS.md
-    - README.md
-    - go.sum
-    - .gitignore
-ignore_extensions:
-    - .png
-    - .jpg
-    - .jpeg
-    - .gif
-    - .pdf
-    - .exe
-    - .dll
-    - .so
-    - .o
-    - .a
-    - .zip
-    - .gz
-    - .tar
-    - .lock
-    - .pyc
-    - .pyo
-    - .pyd
-    - -lock.json
-    - .lock.yaml
-    - pnpm-lock.yaml
+  - README.md
+  - .code-reducer.yaml
+  - go.sum
+  - go.mod
+  - screeshots
+  - examples

.github/workflows/release.yml

@@ -20,13 +20,19 @@ jobs:
             goarch: "386"
     steps:
       - name: Checkout Repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v4
 
       - name: Set up Go
-        uses: actions/setup-go@v6
+        uses: actions/setup-go@v5
         with:
           go-version: '1.26'
 
+      - name: Run Vet
+        run: go vet ./...
+
+      - name: Run Tests
+        run: go test -race -v ./...
+
       - name: Build Binary
         env:
           GOOS: ${{ matrix.goos }}
@@ -55,7 +61,7 @@ jobs:
           fi
 
       - name: Upload to Release
-        uses: softprops/action-gh-release@v3
+        uses: softprops/action-gh-release@v2
         with:
           files: ${{ steps.package.outputs.asset_path }}
         env:

.gitignore

@@ -1,2 +1,16 @@
 .code-reducer.lock
-code-reducer
+code-reducer
+
+# IDEs and Editors
+.idea/
+.vscode/
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.swp
+
+# Build output
+dist/
+tmp/
+*.tmp.*

cmd/root.go

@@ -16,7 +16,7 @@ import (
 )
 
 var (
-	modelIdFlag string
+	modelIDFlag string
 	numCtxFlag  string
 )
 
@@ -30,7 +30,7 @@ var RootCmd = &cobra.Command{
 }
 
 func init() {
-	RootCmd.PersistentFlags().StringVar(&modelIdFlag, "model-id", "", "Specify LLM model ID")
+	RootCmd.PersistentFlags().StringVar(&modelIDFlag, "model-id", "", "Specify LLM model ID")
 	RootCmd.PersistentFlags().StringVar(&numCtxFlag, "num-ctx", "", "Specify Ollama context window size")
 }
 
@@ -59,7 +59,7 @@ func executeCommand(mode string) error {
 	}
 
 	// Resolve the merged configuration
-	cfg, err := config.ResolveConfig(repoRoot, modelIdFlag, numCtxFlag)
+	cfg, err := config.ResolveConfig(repoRoot, modelIDFlag, numCtxFlag)
 	if err != nil {
 		return err
 	}
@@ -81,10 +81,10 @@ func executeCommand(mode string) error {
 	defer stop()
 
 	runner := engine.NewRunner(cfg)
-	err = runner.Run(ctx, repoRoot, mode, func(ev engine.Event) {
-		if ev.Type == "status" {
+	err = runner.Run(ctx, repoRoot, engine.Mode(mode), func(ev engine.Event) {
+		if ev.Type == engine.EventStatus {
 			fmt.Println(ev.Message)
-		} else if ev.Type == "error" {
+		} else if ev.Type == engine.EventError {
 			fmt.Fprintf(os.Stderr, "Error: %s\n", ev.Message)
 		} else {
 			fmt.Println(ev.Message)

cmd/setup.go

@@ -67,46 +67,28 @@ func RunSetupFlow(repoRoot string) error {
 	}
 
 	var customIgnores []string
-	var customExtensions []string
 
 	if existingCfg != nil {
-		customIgnores = subtractSlice(existingCfg.Ignore, config.DefaultIgnores)
-		customExtensions = subtractSlice(existingCfg.IgnoreExtensions, config.DefaultIgnoredExtensions)
+		customIgnores = existingCfg.Ignore
 	}
 
-	userInputIgnores, ignoresModified := promptStringList(reader, "Enter custom directories/files to ignore (comma-separated)", customIgnores)
+	userInputIgnores, ignoresModified := promptStringList(reader, "Enter directories, files, or patterns to ignore (comma-separated)", customIgnores)
 	var ignores []string
 	if ignoresModified {
 		if len(userInputIgnores) > 0 {
-			ignores = config.MergeAndDeduplicate(config.DefaultIgnores, userInputIgnores)
+			ignores = userInputIgnores
 		} else {
 			ignores = []string{}
 		}
 	} else {
 		if existingCfg != nil {
 			ignores = existingCfg.Ignore
 		} else {
-			ignores = config.DefaultIgnores
-		}
-	}
-
-	userInputExtensions, extensionsModified := promptStringList(reader, "Enter custom file extensions to ignore (comma-separated)", customExtensions)
-	var ignoreExtensions []string
-	if extensionsModified {
-		if len(userInputExtensions) > 0 {
-			ignoreExtensions = config.MergeAndDeduplicate(config.DefaultIgnoredExtensions, userInputExtensions)
-		} else {
-			ignoreExtensions = []string{}
-		}
-	} else {
-		if existingCfg != nil {
-			ignoreExtensions = existingCfg.IgnoreExtensions
-		} else {
-			ignoreExtensions = config.DefaultIgnoredExtensions
+			ignores = []string{}
 		}
 	}
 
-	existingDocsDir := "wiki"
+	existingDocsDir := config.DefaultDocsDir
 	if existingCfg != nil && existingCfg.DocsDir != "" {
 		existingDocsDir = existingCfg.DocsDir
 	}
@@ -119,14 +101,37 @@ func RunSetupFlow(repoRoot string) error {
 		extractionSteps = config.DefaultExtractionSteps
 	}
 
+	existingSystemPrompt := config.DefaultSystemPrompt
+	existingModuleSynthesisPrompt := config.DefaultModuleSynthesisPrompt
+	existingArchitecturePrompt := config.DefaultArchitecturePrompt
+	existingFileFactConsolidationPrompt := config.DefaultFileFactConsolidationPrompt
+
+	if existingCfg != nil {
+		if existingCfg.SystemPrompt != "" {
+			existingSystemPrompt = existingCfg.SystemPrompt
+		}
+		if existingCfg.ModuleSynthesisPrompt != "" {
+			existingModuleSynthesisPrompt = existingCfg.ModuleSynthesisPrompt
+		}
+		if existingCfg.ArchitecturePrompt != "" {
+			existingArchitecturePrompt = existingCfg.ArchitecturePrompt
+		}
+		if existingCfg.FileFactConsolidationPrompt != "" {
+			existingFileFactConsolidationPrompt = existingCfg.FileFactConsolidationPrompt
+		}
+	}
+
 	newCfg := &config.Config{
-		ModelID:          modelInput,
-		OllamaBaseURL:    urlInput,
-		OllamaNumCtx:     numCtx,
-		DocsDir:          docsDirInput,
-		ExtractionSteps:  extractionSteps,
-		Ignore:           ignores,
-		IgnoreExtensions: ignoreExtensions,
+		ModelID:                     modelInput,
+		OllamaBaseURL:               urlInput,
+		OllamaNumCtx:                numCtx,
+		DocsDir:                     docsDirInput,
+		ExtractionSteps:             extractionSteps,
+		Ignore:                      ignores,
+		SystemPrompt:                existingSystemPrompt,
+		ModuleSynthesisPrompt:       existingModuleSynthesisPrompt,
+		ArchitecturePrompt:          existingArchitecturePrompt,
+		FileFactConsolidationPrompt: existingFileFactConsolidationPrompt,
 	}
 
 	err = config.SaveConfig(repoRoot, newCfg)
@@ -191,16 +196,4 @@ func promptString(reader *bufio.Reader, promptMsg, existingVal string) string {
 	return input
 }
 
-func subtractSlice[T comparable](a, b []T) []T {
-	bMap := make(map[T]bool)
-	for _, item := range b {
-		bMap[item] = true
-	}
-	var result []T
-	for _, item := range a {
-		if !bMap[item] {
-			result = append(result, item)
-		}
-	}
-	return result
-}
+

examples/go/.code-reducer.yaml

@@ -0,0 +1,48 @@
+# Example .code-reducer.yaml for analyzing Go projects
+model_id: "ornith:9b"
+ollama_base_url: "http://localhost:11434"
+ollama_num_ctx: 8192
+docs_dir: "wiki"
+
+# System Prompt defines the AI persona
+system_prompt: |
+  You are Code-Reducer, an expert technical writer and Go code analyzer. Your job is to strictly follow instructions. You do not yap, you do not write filler.
+  DEFENSIVE RULES: 
+  1. Do NOT use absolute terms ('always', 'never', 'zero') unless explicitly proven. 
+  2. Do NOT guess downstream consequences or invent unhandled paths. If an error is swallowed, just say it is swallowed. 
+  3. Do NOT name standard library packages unless explicitly stated in the source text. 
+  4. Only report facts you are 100% sure about.
+
+# Prompts for synthesized output
+module_synthesis_prompt: |
+  Task: Write a technical documentation page for a code module based on the provided list of its internal components.
+  Rule 1: Group related functions and classes under appropriate Markdown headings.
+  Rule 2: Explain the responsibility of the module and the data flow.
+  Rule 3: Keep it highly technical and dense.
+
+architecture_prompt: |
+  Task: Write a global architecture or quickstart document based on the module summaries.
+  Rule 1: Explain the system boundaries and how the modules interact.
+  Rule 2: Provide a dense, developer-friendly overview.
+
+file_fact_consolidation_prompt: |
+  You are a specialized code documentation assistant. Consolidate, deduplicate and merge the following facts extracted from different chunks of the same file into a single, cohesive summary.
+
+# Custom extraction steps during map phase
+extraction_steps:
+  - name: "API_SIGNATURES"
+    prompt: |
+      Task: Extract the public surface area of the file.
+      Output: A strict Markdown list of all exported structs, interfaces, and methods. For each, note the actual input and output types. Ignore internal logic.
+  - name: "BUSINESS_LOGIC"
+    prompt: |
+      Task: Analyze the business logic and domain concepts.
+      Output: Explain what business rules or domain concepts this file solves. Describe the high-level algorithmic flow. Ignore implementation details.
+  - name: "STATE_AND_CONCURRENCY"
+    prompt: |
+      Task: Analyze state mutation and concurrency.
+      Output: List all mutable state (global variables, changing struct fields) and what concurrency mechanisms (e.g., sync.Mutex, channels) protect them. If none, state 'No mutable state'.
+  - name: "ERRORS_AND_SIDE_EFFECTS"
+    prompt: |
+      Task: Analyze side effects and error handling.
+      Output: Detail how this code communicates with the outside world (I/O like network, disk, DB) and how it handles/returns errors (wrap, sentinel, panic).

examples/terraform/.code-reducer.yaml

@@ -0,0 +1,55 @@
+# Example .code-reducer.yaml for analyzing Terraform infrastructure projects
+model_id: "ornith:9b"
+ollama_base_url: "http://localhost:11434"
+ollama_num_ctx: 8192
+docs_dir: "wiki"
+
+# Tell the LLM to behave as a Cloud Architect and IaC analyzer
+system_prompt: |
+  You are Code-Reducer, an expert Cloud Architect and Terraform infrastructure analyzer. Your job is to strictly follow instructions. You do not yap, you do not write filler.
+  DEFENSIVE RULES: 
+  1. Do NOT assume resources exist unless explicitly declared in the configuration.
+  2. Do NOT guess downstream resource side effects unless directly linked (e.g., via security group attachments or subnet associations).
+  3. Only report resource definitions and configurations you are 100% sure about.
+
+# Synthesis prompt for directory modules (which represent infrastructure sub-components)
+module_synthesis_prompt: |
+  Task: Write a technical documentation page for a Terraform module based on the provided list of its internal resources, variables, and sub-modules.
+  Rule 1: Group related resources (e.g., networking, compute, database, IAM) under appropriate Markdown headings.
+  Rule 2: Explain the primary responsibility of this module, the resource dependency flow, and security configurations.
+  Rule 3: Keep it highly technical, listing key resources, inputs, and outputs.
+
+# Synthesis prompt for the global infrastructure overview
+architecture_prompt: |
+  Task: Write a global cloud architecture overview and deployment guide based on the module summaries.
+  Rule 1: Explain the high-level cloud topology, provider requirements, and how modules connect (e.g., VPC connecting to EKS and RDS).
+  Rule 2: Provide a dense, developer-friendly infrastructure overview and standard Terraform deployment commands (init, plan, apply).
+
+file_fact_consolidation_prompt: |
+  You are a specialized infrastructure documentation assistant. Consolidate, deduplicate and merge the following facts extracted from different chunks of the same Terraform file into a single, cohesive summary.
+
+# Custom extraction steps during map phase
+extraction_steps:
+  - name: "PROVISIONED_RESOURCES"
+    prompt: |
+      Task: Extract resources and data sources defined in this file.
+      Output: A strict Markdown list of all resources (`resource "type" "name"`) and data sources (`data "type" "name"`). Note key parameters (e.g. instance type, VPC CIDR, backend configurations).
+  - name: "VARIABLES_AND_OUTPUTS"
+    prompt: |
+      Task: Analyze input variables, outputs, and local variables.
+      Output: List all input variables (with types and default values) and outputs exported by this file. Mention any complex local variables (`locals`) that define key configurations.
+  - name: "MODULE_DEPENDENCIES"
+    prompt: |
+      Task: Analyze sub-module usage.
+      Output: Identify any external or internal modules called in this file (`module "name"`), their source paths, and the key inputs passed to them.
+  - name: "IAM_AND_SECURITY"
+    prompt: |
+      Task: Analyze permissions, IAM roles, and security groups.
+      Output: Detail security groups, firewall rules, IAM roles, policies, and KMS keys defined in this file. Outline what access permissions or network paths they allow.
+
+# Ignore Terraform state, local plugins, and lock files
+ignore:
+  - ".terraform"
+  - "*.tfstate"
+  - "*.tfstate.backup"
+  - ".terraform.lock.hcl"