[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AD4SFA59ZBZSXNSX2BMXYC":3,"skill-same:01M6AD4SFA59ZBZSXNSX2BMXYC":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6AD4SFA59ZBZSXNSX2BMXYC","developer-code-organization",null,"Code organization patterns, file structure guidelines, WASM build variants, and string processing conventions for gh-aw Go code.","github\u002Fgh-aw","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3VCZ4WKQSFSRTPN7N9DN",5636,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fdeveloper-code-organization\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"code","developer code organization","developer","organization","build","variants","for","processing","STRING","conventions","structure","patterns","go","gh","file","guidelines","wasm","2026-11-10 10:12:30",false,"---\nname: developer-code-organization\ndescription: Code organization patterns, file structure guidelines, WASM build variants, and string processing conventions for gh-aw Go code.\n---\n\n\n# Code Organization\n\nUse this reference for gh-aw code organization patterns, file structure guidelines, WASM build-variant stubs, and string sanitization\u002Fnormalization conventions.\n\n## Table of Contents\n\n- [File Organization Principles](#file-organization-principles)\n- [Excellent Patterns to Follow](#excellent-patterns-to-follow)\n- [File Size Guidelines](#file-size-guidelines)\n- [Decision Trees](#decision-tree-creating-new-files)\n- [Case Study: Refactoring Large Files](#case-study-refactoring-large-files)\n- [Anti-Patterns to Avoid](#anti-patterns-to-avoid)\n- [Helper File Conventions](#helper-file-conventions)\n- [String Sanitization vs Normalization](#string-sanitization-vs-normalization)\n- [WASM Build-Variant Pattern](#wasm-build-variant-pattern)\n\n### File Organization Principles\n\nThe codebase follows clear patterns for organizing code by functionality rather than type. This section provides guidance on maintaining code quality and structure.\n\n#### Prefer Many Small Files Over Large Ones\n\nOrganize code into focused files of 100-500 lines rather than creating large monolithic files.\n\n**Example:**\n```\ncreate_issue.go (160 lines)\ncreate_pull_request.go (238 lines)\ncreate_discussion.go (118 lines)\n```\n\n#### Group by Functionality, Not by Type\n\n**Recommended approach:**\n```\ncreate_issue.go            # Issue creation logic\ncreate_issue_test.go       # Issue creation tests\nadd_comment.go             # Comment addition logic\nadd_comment_test.go        # Comment tests\n```\n\n**Avoid:**\n```\nmodels.go                  # All structs\nlogic.go                   # All business logic\ntests.go                   # All tests\n```\n\n### Excellent Patterns to Follow\n\n#### Create Functions Pattern\n\nOne file per GitHub entity creation operation:\n- `create_issue.go` - GitHub issue creation logic\n- `create_pull_request.go` - Pull request creation logic\n- `create_discussion.go` - Discussion creation logic\n- `create_code_scanning_alert.go` - Code scanning alert creation\n\nBenefits:\n- Clear separation of concerns\n- Easy to locate specific functionality\n- Prevents files from becoming too large\n- Facilitates parallel development\n\n#### Engine Separation Pattern\n\nEach AI engine has its own file with shared helpers in `engine_helpers.go`:\n- `copilot_engine.go` - GitHub Copilot engine\n- `claude_engine.go` - Claude engine\n- `codex_engine.go` - Codex engine\n- `custom_engine.go` - Custom engine support\n- `engine_helpers.go` - Shared engine utilities\n\n#### Test Organization Pattern\n\nTests live alongside implementation files:\n- Feature tests: `feature.go` + `feature_test.go`\n- Integration tests: `feature_integration_test.go`\n- Specific scenario tests: `feature_scenario_test.go`\n\n### File Size Guidelines\n\n| Category | Lines | Use Case | Example |\n|----------|-------|----------|---------|\n| Small files | 50-200 | Utilities, simple features | `args.go` (65 lines) |\n| Medium files | 200-500 | Most feature implementations | `create_issue.go` (160 lines) |\n| Large files | 500-800 | Complex features | `permissions.go` (905 lines) |\n| Very large files | 800+ | Core infrastructure only | `compiler.go` (1596 lines) |\n\n### Decision Tree: Creating New Files\n\n```mermaid\ngraph TD\n    A[Need to add code] --> B{New safe output type?}\n    B -->|Yes| C[Create create_entity.go]\n    B -->|No| D{New AI engine?}\n    D -->|Yes| E[Create engine_name_engine.go]\n    D -->|No| F{Current file > 800 lines?}\n    F -->|Yes| G[Consider splitting by boundaries]\n    F -->|No| H{Functionality independent?}\n    H -->|Yes| I[Create new file]\n    H -->|No| J[Add to existing file]\n```\n\n### Decision Tree: Splitting Files\n\n```mermaid\ngraph TD\n    A[Evaluating file split] --> B{File > 1000 lines?}\n    B -->|Yes| C[SHOULD split]\n    B -->|No| D{File > 800 lines?}\n    D -->|Yes| E[CONSIDER splitting]\n    D -->|No| F{Multiple responsibilities?}\n    F -->|Yes| E\n    F -->|No| G{Frequent merge conflicts?}\n    G -->|Yes| E\n    G -->|No| H[Keep as is]\n```\n\n### Case Study: Refactoring Large Files\n\nThe refactoring of `pkg\u002Fparser\u002Ffrontmatter.go` demonstrates applying file organization principles to a large monolithic file.\n\n#### Initial State\n- **Original file**: 1,907 lines (monolithic structure)\n- **Problem**: Difficult to navigate, understand, and maintain\n- **Goal**: Split into focused, maintainable modules\n\n#### Refactoring Approach\n\n```mermaid\ngraph TD\n    A[frontmatter.go\u003Cbr\u002F>1,907 LOC] --> B[ansi_strip.go\u003Cbr\u002F>108 LOC]\n    A --> C[frontmatter_content.go\u003Cbr\u002F>284 LOC]\n    A --> D[remote_fetch.go\u003Cbr\u002F>258 LOC]\n    A --> E[workflow_update.go\u003Cbr\u002F>129 LOC]\n    A --> F[frontmatter.go\u003Cbr\u002F>1,166 LOC]\n\n    B --> G[ANSI escape\u003Cbr\u002F>sequence utilities]\n    C --> H[Frontmatter\u003Cbr\u002F>parsing & extraction]\n    D --> I[GitHub remote\u003Cbr\u002F>content fetching]\n    E --> J[Workflow file\u003Cbr\u002F>updates]\n    F --> K[Core frontmatter\u003Cbr\u002F>processing]\n\n    style B fill:#90EE90\n    style C fill:#90EE90\n    style D fill:#90EE90\n    style E fill:#90EE90\n    style F fill:#FFE4B5\n```\n\n#### Results\n\n| Metric | Before | After | Change |\n|--------|--------|-------|--------|\n| Main file size | 1,907 LOC | 1,166 LOC | -741 LOC (-39%) |\n| Number of files | 1 | 5 | +4 files |\n| Average file size | 1,907 LOC | 233 LOC | -88% |\n| Test pass rate | 100% | 100% | No change ✓ |\n| Breaking changes | N\u002FA | 0 | None ✓ |\n\n#### Modules Extracted\n\n1. **ansi_strip.go** (108 LOC)\n   - ANSI escape sequence stripping utilities\n   - Standalone, no dependencies\n   - Functions: `StripANSI()`, `isFinalCSIChar()`, `isCSIParameterChar()`\n\n2. **frontmatter_content.go** (284 LOC)\n   - Basic frontmatter parsing and extraction\n   - Pure functions without side effects\n   - Functions: `ExtractFrontmatterFromContent()`, `ExtractFrontmatterString()`, `ExtractMarkdownContent()`, etc.\n\n3. **remote_fetch.go** (258 LOC)\n   - GitHub remote content fetching\n   - GitHub API interactions and caching\n   - Functions: `downloadIncludeFromWorkflowSpec()`, `resolveRefToSHA()`, `downloadFileFromGitHub()`\n\n4. **workflow_update.go** (129 LOC)\n   - High-level workflow file updates\n   - Frontmatter manipulation and cron expression handling\n   - Functions: `UpdateWorkflowFrontmatter()`, `EnsureToolsSection()`, `QuoteCronExpressions()`\n\n#### Key Principles Applied\n\n- **Single Responsibility**: Each module handles one aspect of frontmatter processing\n- **Clear Boundaries**: Well-defined interfaces between modules\n- **Progressive Refactoring**: Extract standalone utilities first, then higher-level modules\n- **No Breaking Changes**: Maintain public API compatibility throughout\n- **Test-Driven Safety**: Run tests after each extraction\n\n#### Remaining Work\n\nThree complex modules remain in the original file (requiring future work):\n- **tool_sections.go** (~420 LOC): Tool configuration extraction and merging\n- **include_expander.go** (~430 LOC): Recursive include resolution with cycle detection\n- **frontmatter_imports.go** (~360 LOC): BFS import traversal and processing\n\nThese remain due to high interdependency, stateful logic, and complex recursive algorithms.\n\n### Anti-Patterns to Avoid\n\n#### God Files\nSingle file doing everything - split by responsibility instead. The frontmatter.go refactoring demonstrates how a 1,907-line \"god file\" can be systematically broken down.\n\n#### Vague Naming\nAvoid non-descriptive file names like `utils.go`, `helpers.go`, `misc.go`, `common.go`.\n\nUse specific names like `ansi_strip.go`, `remote_fetch.go`, or `workflow_update.go` that clearly indicate their purpose.\n\n#### Mixed Concerns\nKeep files focused on one domain. Don't mix unrelated functionality in one file.\n\n#### Test Pollution\nSplit tests by scenario rather than having one massive test file.\n\n#### Premature Abstraction\nWait until you have 2-3 use cases before extracting common patterns.\n\n### Helper File Conventions\n\nHelper files contain shared utility functions used across multiple modules. Follow these guidelines when creating or modifying helper files.\n\n#### When to Create Helper Files\n\nCreate a helper file when you have:\n1. **Shared utilities** used by 3+ files in the same domain\n2. **Clear domain focus** (e.g., configuration parsing, MCP rendering, CLI wrapping)\n3. **Stable functionality** that won't change frequently\n\n**Examples of Good Helper Files:**\n- `github_cli.go` - GitHub CLI wrapping functions (ExecGH, ExecGHWithOutput)\n- `config_helpers.go` - Safe output configuration parsing (parseLabelsFromConfig, parseTitlePrefixFromConfig)\n- `map_helpers.go` - Generic map\u002Ftype utilities (parseIntValue, filterMapKeys)\n- `mcp_renderer.go` - MCP configuration rendering (RenderGitHubMCPDockerConfig, RenderJSONMCPConfig)\n\n#### Naming Conventions\n\nHelper file names should be **specific and descriptive**, not generic:\n\n**Good Names:**\n- `github_cli.go` - Indicates GitHub CLI helpers\n- `mcp_renderer.go` - Indicates MCP rendering helpers\n- `config_helpers.go` - Indicates configuration parsing helpers\n\n**Avoid:**\n- `helpers.go` - Too generic\n- `utils.go` - Too vague\n- `misc.go` - Indicates poor organization\n- `common.go` - Doesn't specify domain\n\n#### What Belongs in Helper Files\n\n**Include:**\n- Small (\u003C 50 lines) utility functions used by multiple files\n- Domain-specific parsing\u002Fvalidation functions\n- Wrapper functions that simplify common operations\n- Type conversion utilities\n\n**Exclude:**\n- Complex business logic (belongs in domain-specific files)\n- Functions used by only 1-2 callers (co-locate with callers)\n- Large functions (> 100 lines) - consider dedicated files\n- Multiple unrelated domains in one file\n\n#### Helper File Organization\n\n**Current Helper Files in pkg\u002Fworkflow:**\n\n| File | Purpose | Functions | Usage |\n|------|---------|-----------|-------|\n| `github_cli.go` | GitHub CLI wrapper | 2 functions | Used by CLI commands and workflow resolution |\n| `config_helpers.go` | Safe output config parsing | 5 functions | Used by safe output processors |\n| `map_helpers.go` | Generic map\u002Ftype utilities | 2 functions | Used across workflow compilation |\n| `prompt_step_helper.go` | Prompt step generation | 1 function | Used by prompt generators |\n| `mcp_renderer.go` | MCP config rendering | Multiple rendering functions | Used by all AI engines |\n| `engine_helpers.go` | Shared engine utilities | Agent, npm install helpers | Used by Copilot, Claude, Codex engines |\n\n#### When NOT to Create Helper Files\n\nAvoid creating helper files when:\n1. **Single caller** - Co-locate with the caller instead\n2. **Tight coupling** - Function is tightly coupled to one module\n3. **Frequent changes** - Helper files should be stable\n4. **Mixed concerns** - Multiple unrelated utilities (split into focused files)\n\n**Example of co-location preference:**\n```go\n\u002F\u002F Instead of: helpers.go containing formatStepName() used only by compiler.go\n\u002F\u002F Do: Put formatStepName() directly in compiler.go\n```\n\n#### Refactoring Guidelines\n\nWhen refactoring helper files:\n1. **Group by domain** - MCP rendering → mcp_renderer.go, not engine_helpers.go\n2. **Keep functions small** - Large helpers (> 100 lines) may need dedicated files\n3. **Document usage** - Add comments explaining when to use each helper\n4. **Check call sites** - Ensure 3+ callers before keeping in helper file\n\n#### Example: MCP Function Reorganization\n\nThe MCP rendering functions were moved from `engine_helpers.go` to `mcp_renderer.go` because:\n- **Domain focus**: All functions relate to MCP configuration rendering\n- **Multiple callers**: Used by Claude, Copilot, Codex, and Custom engines\n- **Cohesive**: Functions work together to render MCP configs\n- **Stable**: Rendering patterns don't change frequently\n\n**Before:**\n```\nengine_helpers.go (478 lines)\n  - Agent helpers\n  - npm install helpers\n  - MCP rendering functions ← Should be in mcp_renderer.go\n```\n\n**After:**\n```\nengine_helpers.go (213 lines)\n  - Agent helpers\n  - npm install helpers\n  \nmcp_renderer.go (523 lines)\n  - MCP rendering functions\n  - MCP configuration types\n```\n\n### String Sanitization vs Normalization\n\nThe codebase uses two distinct patterns for string processing with different purposes.\n\n#### Sanitize Pattern: Character Validity\n\n**Purpose**: Remove or replace invalid characters to create valid identifiers, file names, or artifact names.\n\n**When to use**: When you need to ensure a string contains only valid characters for a specific context (identifiers, YAML artifact names, filesystem paths).\n\n**What it does**:\n- Removes special characters that are invalid in the target context\n- Replaces separators (colons, slashes, spaces) with hyphens\n- Converts to lowercase for consistency\n- May preserve certain characters (dots, underscores) based on configuration\n\n#### Normalize Pattern: Format Standardization\n\n**Purpose**: Standardize format by removing extensions, converting between conventions, or applying consistent formatting rules.\n\n**When to use**: When you need to convert between different representations of the same logical entity (e.g., file extensions, naming conventions).\n\n**What it does**:\n- Removes file extensions (.md, .lock.yml)\n- Converts between naming conventions (dashes to underscores)\n- Standardizes identifiers to a canonical form\n- Does NOT validate character validity (assumes input is already valid)\n\n#### Function Reference\n\n**Sanitize Functions**:\n- `SanitizeName(name string, opts *SanitizeOptions) string` - Configurable sanitization with custom character preservation\n- `SanitizeWorkflowName(name string) string` - Sanitizes workflow names for artifact names and file paths\n- `SanitizeIdentifier(name string) string` - Creates clean identifiers for user agent strings\n\n**Normalize Functions**:\n- `normalizeWorkflowName(name string) string` - Removes file extensions to get base workflow identifier\n- `normalizeSafeOutputIdentifier(identifier string) string` - Converts dashes to underscores for safe output identifiers\n\n#### Decision Tree\n\n```mermaid\ngraph TD\n    A[Need to process a string?] --> B{Need to ensure character validity?}\n    B -->|Yes| C[Use SANITIZE]\n    C --> D{Artifact name \u002F file path?}\n    C --> E{Identifier \u002F user agent?}\n    C --> F{Custom requirements?}\n    D --> G[SanitizeWorkflowName]\n    E --> H[SanitizeIdentifier]\n    F --> I[SanitizeName with options]\n    B -->|No| J{Need to standardize format?}\n    J -->|Yes| K[Use NORMALIZE]\n    K --> L{Remove file extensions?}\n    K --> M{Convert conventions?}\n    L --> N[normalizeWorkflowName]\n    M --> O[normalizeSafeOutputIdentifier]\n```\n\n#### Best Practices\n\n1. **Choose the right tool**: Use sanitize for character validity, normalize for format standardization.\n2. **Don't double-process**: If normalize produces a valid identifier, don't sanitize it again.\n3. **Document intent**: When using these functions, add comments explaining which pattern you're using and why.\n4. **Validate assumptions**: If you assume input is already valid, document that assumption.\n5. **Consider defaults**: Use `SanitizeIdentifier` when you need a fallback default value for empty results.\n\n#### Anti-Patterns\n\n**Don't sanitize already-normalized strings**:\n```go\n\u002F\u002F BAD: Sanitizing a normalized workflow name\nnormalized := normalizeWorkflowName(\"weekly-research.md\")\nsanitized := SanitizeWorkflowName(normalized) \u002F\u002F Unnecessary!\n```\n\n**Don't normalize for character validity**:\n```go\n\u002F\u002F BAD: Using normalize for invalid characters\nuserInput := \"My Workflow: Test\u002FBuild\"\nnormalized := normalizeWorkflowName(userInput) \u002F\u002F Wrong tool!\n\u002F\u002F normalized = \"My Workflow: Test\u002FBuild\" (unchanged - invalid chars remain)\n```\n\n\n### WASM Build-Variant Pattern\n\nSeven files in `pkg\u002Fworkflow\u002F` provide stub implementations of OS-dependent\nfeatures for the WASM compilation target (`GOOS=js GOARCH=wasm`) used by the\ngh-aw web playground. Each file is named with the `_wasm.go` suffix (Go's\nimplicit filename build constraint for `GOARCH=wasm`) **and** carries an\nexplicit `\u002F\u002Fgo:build js || wasm` tag at line 1:\n\n```\npkg\u002Fworkflow\u002Fdependabot_wasm.go\npkg\u002Fworkflow\u002Fdocker_validation_wasm.go\npkg\u002Fworkflow\u002Fgit_helpers_wasm.go\npkg\u002Fworkflow\u002Fgithub_cli_wasm.go\npkg\u002Fworkflow\u002Fnpm_validation_wasm.go\npkg\u002Fworkflow\u002Fpip_validation_wasm.go\npkg\u002Fworkflow\u002Frepository_features_validation_wasm.go\n```\n\nEach `_wasm.go` file mirrors the public\u002Fpackage-level function signatures of\nits non-WASM counterpart but replaces OS calls (exec, filesystem, network)\nwith either no-ops or `fmt.Errorf(\"... not available in Wasm\")` returns.\n\n#### When a `_wasm.go` Stub is Required\n\nAdd a `_wasm.go` stub whenever you add a **new function** to an existing\n`_wasm.go`-guarded file (or create a new file that calls OS-level tools at\ncompile\u002Fvalidation time). Specifically:\n\n- Functions that call `os\u002Fexec` or run external binaries (gh, git, docker,\n  npm, pip, uv, etc.)\n- Functions that read from the real filesystem during compilation\n- Functions that perform network I\u002FO at validation time\n\nFunctions that **do not** need a WASM stub:\n- Pure data transformations (string manipulation, YAML marshaling)\n- Functions that only operate on in-memory data structures\n- Functions gated behind `WithSkipValidation(true)` (already excluded at\n  runtime, but still need to compile)\n\n#### How to Add a Stub\n\n1. Identify the non-WASM file (e.g., `github_cli.go`).\n2. Open (or create) the corresponding `_wasm.go` file (e.g.,\n   `github_cli_wasm.go`).\n3. Ensure the build tag at line 1 is `\u002F\u002Fgo:build js || wasm`.\n4. Add a stub with the same signature that returns a zero value and\u002For an\n   error:\n   ```go\n   func MyNewFunction(args ...string) ([]byte, error) {\n       return nil, fmt.Errorf(\"MyNewFunction not available in Wasm\")\n   }\n   ```\n5. Verify the WASM build still compiles:\n   ```bash\n   GOOS=js GOARCH=wasm go build .\u002Fpkg\u002Fworkflow\u002F\n   ```\n\n#### Known Gap\n\n`github_cli_wasm.go` currently omits stubs for `enrichGHError`,\n`runGHWithSpinnerContext`, `RunGHCombinedContext`, `RunGHWithHost`, and\n`SetGHHostEnv`. These are unexported helpers or thin wrappers called only\nby the exported `RunGH*` family, which are already stubbed; the compiler\ndoes not reference them directly. This is intentional — avoid adding stubs\nfor unexported helpers unless the WASM build breaks.\n\n\n","# Code Organization\n\nUse this reference for gh-aw code organization patterns, file structure guidelines, WASM build-variant stubs, and string sanitization\u002Fnormalization conventions.\n\n## Table of Contents\n\n- [File Organization Principles](#file-organization-principles)\n- [Excellent Patterns to Follow](#excellent-patterns-to-follow)\n- [File Size Guidelines](#file-size-guidelines)\n- [Decision Trees](#decision-tree-creating-new-files)\n- [Case Study: Refactoring Large Files](#case-study-refactoring-large-files)\n- [Anti-Patterns to Avoid](#anti-patterns-to-avoid)\n- [Helper File Conventions](#helper-file-conventions)\n- [String Sanitization vs Normalization](#string-sanitization-vs-normalization)\n- [WASM Build-Variant Pattern](#wasm-build-variant-pattern)\n\n### File Organization Principles\n\nThe codebase follows clear patterns for organizing code by functionality rather than type. This section provides guidance on maintaining code quality and structure.\n\n#### Prefer Many Small Files Over Large Ones\n\nOrganize code into focused files of 100-500 lines rather than creating large monolithic files.\n\n**Example:**\n```\ncreate_issue.go (160 lines)\ncreate_pull_request.go (238 lines)\ncreate_discussion.go (118 lines)\n```\n\n#### Group by Functionality, Not by Type\n\n**Recommended approach:**\n```\ncreate_issue.go            # Issue creation logic\ncreate_issue_test.go       # Issue creation tests\nadd_comment.go             # Comment addition logic\nadd_comment_test.go        # Comment tests\n```\n\n**Avoid:**\n```\nmodels.go                  # All structs\nlogic.go                   # All business logic\ntests.go                   # All tests\n```\n\n### Excellent Patterns to Follow\n\n#### Create Functions Pattern\n\nOne file per GitHub entity creation operation:\n- `create_issue.go` - GitHub issue creation logic\n- `create_pull_request.go` - Pull request creation logic\n- `create_discussion.go` - Discussion creation logic\n- `create_code_scanning_alert.go` - Code scanning alert creation\n\nBenefits:\n- Clear separation of concerns\n- Easy to locate specific functionality\n- Prevents files from becoming too large\n- Facilitates parallel development\n\n#### Engine Separation Pattern\n\nEach AI engine has its own file with shared helpers in `engine_helpers.go`:\n- `copilot_engine.go` - GitHub Copilot engine\n- `claude_engine.go` - Claude engine\n- `codex_engine.go` - Codex engine\n- `custom_engine.go` - Custom engine support\n- `engine_helpers.go` - Shared engine utilities\n\n#### Test Organization Pattern\n\nTests live alongside implementation files:\n- Feature tests: `feature.go` + `feature_test.go`\n- Integration tests: `feature_integration_test.go`\n- Specific scenario tests: `feature_scenario_test.go`\n\n### File Size Guidelines\n\n| Category | Lines | Use Case | Example |\n|----------|-------|----------|---------|\n| Small files | 50-200 | Utilities, simple features | `args.go` (65 lines) |\n| Medium files | 200-500 | Most feature implementations | `create_issue.go` (160 lines) |\n| Large files | 500-800 | Complex features | `permissions.go` (905 lines) |\n| Very large files | 800+ | Core infrastructure only | `compiler.go` (1596 lines) |\n\n### Decision Tree: Creating New Files\n\n```mermaid\ngraph TD\n    A[Need to add code] --> B{New safe output type?}\n    B -->|Yes| C[Create create_entity.go]\n    B -->|No| D{New AI engine?}\n    D -->|Yes| E[Create engine_name_engine.go]\n    D -->|No| F{Current file > 800 lines?}\n    F -->|Yes| G[Consider splitting by boundaries]\n    F -->|No| H{Functionality independent?}\n    H -->|Yes| I[Create new file]\n    H -->|No| J[Add to existing file]\n```\n\n### Decision Tree: Splitting Files\n\n```mermaid\ngraph TD\n    A[Evaluating file split] --> B{File > 1000 lines?}\n    B -->|Yes| C[SHOULD split]\n    B -->|No| D{File > 800 lines?}\n    D -->|Yes| E[CONSIDER splitting]\n    D -->|No| F{Multiple responsibilities?}\n    F -->|Yes| E\n    F -->|No| G{Frequent merge conflicts?}\n    G -->|Yes| E\n    G -->|No| H[Keep as is]\n```\n\n### Case Study: Refactoring Large Files\n\nThe refactoring of `pkg\u002Fparser\u002Ffrontmatter.go` demonstrates applying file organization principles to a large monolithic file.\n\n#### Initial State\n- **Original file**: 1,907 lines (monolithic structure)\n- **Problem**: Difficult to navigate, understand, and maintain\n- **Goal**: Split into focused, maintainable modules\n\n#### Refactoring Approach\n\n```mermaid\ngraph TD\n    A[frontmatter.go\u003Cbr\u002F>1,907 LOC] --> B[ansi_strip.go\u003Cbr\u002F>108 LOC]\n    A --> C[frontmatter_content.go\u003Cbr\u002F>284 LOC]\n    A --> D[remote_fetch.go\u003Cbr\u002F>258 LOC]\n    A --> E[workflow_update.go\u003Cbr\u002F>129 LOC]\n    A --> F[frontmatter.go\u003Cbr\u002F>1,166 LOC]\n\n    B --> G[ANSI escape\u003Cbr\u002F>sequence utilities]\n    C --> H[Frontmatter\u003Cbr\u002F>parsing & extraction]\n    D --> I[GitHub remote\u003Cbr\u002F>content fetching]\n    E --> J[Workflow file\u003Cbr\u002F>updates]\n    F --> K[Core frontmatter\u003Cbr\u002F>processing]\n\n    style B fill:#90EE90\n    style C fill:#90EE90\n    style D fill:#90EE90\n    style E fill:#90EE90\n    style F fill:#FFE4B5\n```\n\n#### Results\n\n| Metric | Before | After | Change |\n|--------|--------|-------|--------|\n| Main file size | 1,907 LOC | 1,166 LOC | -741 LOC (-39%) |\n| Number of files | 1 | 5 | +4 files |\n| Average file size | 1,907 LOC | 233 LOC | -88% |\n| Test pass rate | 100% | 100% | No change ✓ |\n| Breaking changes | N\u002FA | 0 | None ✓ |\n\n#### Modules Extracted\n\n1. **ansi_strip.go** (108 LOC)\n   - ANSI escape sequence stripping utilities\n   - Standalone, no dependencies\n   - Functions: `StripANSI()`, `isFinalCSIChar()`, `isCSIParameterChar()`\n\n2. **frontmatter_content.go** (284 LOC)\n   - Basic frontmatter parsing and extraction\n   - Pure functions without side effects\n   - Functions: `ExtractFrontmatterFromContent()`, `ExtractFrontmatterString()`, `ExtractMarkdownContent()`, etc.\n\n3. **remote_fetch.go** (258 LOC)\n   - GitHub remote content fetching\n   - GitHub API interactions and caching\n   - Functions: `downloadIncludeFromWorkflowSpec()`, `resolveRefToSHA()`, `downloadFileFromGitHub()`\n\n4. **workflow_update.go** (129 LOC)\n   - High-level workflow file updates\n   - Frontmatter manipulation and cron expression handling\n   - Functions: `UpdateWorkflowFrontmatter()`, `EnsureToolsSection()`, `QuoteCronExpressions()`\n\n#### Key Principles Applied\n\n- **Single Responsibility**: Each module handles one aspect of frontmatter processing\n- **Clear Boundaries**: Well-defined interfaces between modules\n- **Progressive Refactoring**: Extract standalone utilities first, then higher-level modules\n- **No Breaking Changes**: Maintain public API compatibility throughout\n- **Test-Driven Safety**: Run tests after each extraction\n\n#### Remaining Work\n\nThree complex modules remain in the original file (requiring future work):\n- **tool_sections.go** (~420 LOC): Tool configuration extraction and merging\n- **include_expander.go** (~430 LOC): Recursive include resolution with cycle detection\n- **frontmatter_imports.go** (~360 LOC): BFS import traversal and processing\n\nThese remain due to high interdependency, stateful logic, and complex recursive algorithms.\n\n### Anti-Patterns to Avoid\n\n#### God Files\nSingle file doing everything - split by responsibility instead. The frontmatter.go refactoring demonstrates how a 1,907-line \"god file\" can be systematically broken down.\n\n#### Vague Naming\nAvoid non-descriptive file names like `utils.go`, `helpers.go`, `misc.go`, `common.go`.\n\nUse specific names like `ansi_strip.go`, `remote_fetch.go`, or `workflow_update.go` that clearly indicate their purpose.\n\n#### Mixed Concerns\nKeep files focused on one domain. Don't mix unrelated functionality in one file.\n\n#### Test Pollution\nSplit tests by scenario rather than having one massive test file.\n\n#### Premature Abstraction\nWait until you have 2-3 use cases before extracting common patterns.\n\n### Helper File Conventions\n\nHelper files contain shared utility functions used across multiple modules. Follow these guidelines when creating or modifying helper files.\n\n#### When to Create Helper Files\n\nCreate a helper file when you have:\n1. **Shared utilities** used by 3+ files in the same domain\n2. **Clear domain focus** (e.g., configuration parsing, MCP rendering, CLI wrapping)\n3. **Stable functionality** that won't change frequently\n\n**Examples of Good Helper Files:**\n- `github_cli.go` - GitHub CLI wrapping functions (ExecGH, ExecGHWithOutput)\n- `config_helpers.go` - Safe output configuration parsing (parseLabelsFromConfig, parseTitlePrefixFromConfig)\n- `map_helpers.go` - Generic map\u002Ftype utilities (parseIntValue, filterMapKeys)\n- `mcp_renderer.go` - MCP configuration rendering (RenderGitHubMCPDockerConfig, RenderJSONMCPConfig)\n\n#### Naming Conventions\n\nHelper file names should be **specific and descriptive**, not generic:\n\n**Good Names:**\n- `github_cli.go` - Indicates GitHub CLI helpers\n- `mcp_renderer.go` - Indicates MCP rendering helpers\n- `config_helpers.go` - Indicates configuration parsing helpers\n\n**Avoid:**\n- `helpers.go` - Too generic\n- `utils.go` - Too vague\n- `misc.go` - Indicates poor organization\n- `common.go` - Doesn't specify domain\n\n#### What Belongs in Helper Files\n\n**Include:**\n- Small (\u003C 50 lines) utility functions used by multiple files\n- Domain-specific parsing\u002Fvalidation functions\n- Wrapper functions that simplify common operations\n- Type conversion utilities\n\n**Exclude:**\n- Complex business logic (belongs in domain-specific files)\n- Functions used by only 1-2 callers (co-locate with callers)\n- Large functions (> 100 lines) - consider dedicated files\n- Multiple unrelated domains in one file\n\n#### Helper File Organization\n\n**Current Helper Files in pkg\u002Fworkflow:**\n\n| File | Purpose | Functions | Usage |\n|------|---------|-----------|-------|\n| `github_cli.go` | GitHub CLI wrapper | 2 functions | Used by CLI commands and workflow resolution |\n| `config_helpers.go` | Safe output config parsing | 5 functions | Used by safe output processors |\n| `map_helpers.go` | Generic map\u002Ftype utilities | 2 functions | Used across workflow compilation |\n| `prompt_step_helper.go` | Prompt step generation | 1 function | Used by prompt generators |\n| `mcp_renderer.go` | MCP config rendering | Multiple rendering functions | Used by all AI engines |\n| `engine_helpers.go` | Shared engine utilities | Agent, npm install helpers | Used by Copilot, Claude, Codex engines |\n\n#### When NOT to Create Helper Files\n\nAvoid creating helper files when:\n1. **Single caller** - Co-locate with the caller instead\n2. **Tight coupling** - Function is tightly coupled to one module\n3. **Frequent changes** - Helper files should be stable\n4. **Mixed concerns** - Multiple unrelated utilities (split into focused files)\n\n**Example of co-location preference:**\n```go\n\u002F\u002F Instead of: helpers.go containing formatStepName() used only by compiler.go\n\u002F\u002F Do: Put formatStepName() directly in compiler.go\n```\n\n#### Refactoring Guidelines\n\nWhen refactoring helper files:\n1. **Group by domain** - MCP rendering → mcp_renderer.go, not engine_helpers.go\n2. **Keep functions small** - Large helpers (> 100 lines) may need dedicated files\n3. **Document usage** - Add comments explaining when to use each helper\n4. **Check call sites** - Ensure 3+ callers before keeping in helper file\n\n#### Example: MCP Function Reorganization\n\nThe MCP rendering functions were moved from `engine_helpers.go` to `mcp_renderer.go` because:\n- **Domain focus**: All functions relate to MCP configuration rendering\n- **Multiple callers**: Used by Claude, Copilot, Codex, and Custom engines\n- **Cohesive**: Functions work together to render MCP configs\n- **Stable**: Rendering patterns don't change frequently\n\n**Before:**\n```\nengine_helpers.go (478 lines)\n  - Agent helpers\n  - npm install helpers\n  - MCP rendering functions ← Should be in mcp_renderer.go\n```\n\n**After:**\n```\nengine_helpers.go (213 lines)\n  - Agent helpers\n  - npm install helpers\n  \nmcp_renderer.go (523 lines)\n  - MCP rendering functions\n  - MCP configuration types\n```\n\n### String Sanitization vs Normalization\n\nThe codebase uses two distinct patterns for string processing with different purposes.\n\n#### Sanitize Pattern: Character Validity\n\n**Purpose**: Remove or replace invalid characters to create valid identifiers, file names, or artifact names.\n\n**When to use**: When you need to ensure a string contains only valid characters for a specific context (identifiers, YAML artifact names, filesystem paths).\n\n**What it does**:\n- Removes special characters that are invalid in the target context\n- Replaces separators (colons, slashes, spaces) with hyphens\n- Converts to lowercase for consistency\n- May preserve certain characters (dots, underscores) based on configuration\n\n#### Normalize Pattern: Format Standardization\n\n**Purpose**: Standardize format by removing extensions, converting between conventions, or applying consistent formatting rules.\n\n**When to use**: When you need to convert between different representations of the same logical entity (e.g., file extensions, naming conventions).\n\n**What it does**:\n- Removes file extensions (.md, .lock.yml)\n- Converts between naming conventions (dashes to underscores)\n- Standardizes identifiers to a canonical form\n- Does NOT validate character validity (assumes input is already valid)\n\n#### Function Reference\n\n**Sanitize Functions**:\n- `SanitizeName(name string, opts *SanitizeOptions) string` - Configurable sanitization with custom character preservation\n- `SanitizeWorkflowName(name string) string` - Sanitizes workflow names for artifact names and file paths\n- `SanitizeIdentifier(name string) string` - Creates clean identifiers for user agent strings\n\n**Normalize Functions**:\n- `normalizeWorkflowName(name string) string` - Removes file extensions to get base workflow identifier\n- `normalizeSafeOutputIdentifier(identifier string) string` - Converts dashes to underscores for safe output identifiers\n\n#### Decision Tree\n\n```mermaid\ngraph TD\n    A[Need to process a string?] --> B{Need to ensure character validity?}\n    B -->|Yes| C[Use SANITIZE]\n    C --> D{Artifact name \u002F file path?}\n    C --> E{Identifier \u002F user agent?}\n    C --> F{Custom requirements?}\n    D --> G[SanitizeWorkflowName]\n    E --> H[SanitizeIdentifier]\n    F --> I[SanitizeName with options]\n    B -->|No| J{Need to standardize format?}\n    J -->|Yes| K[Use NORMALIZE]\n    K --> L{Remove file extensions?}\n    K --> M{Convert conventions?}\n    L --> N[normalizeWorkflowName]\n    M --> O[normalizeSafeOutputIdentifier]\n```\n\n#### Best Practices\n\n1. **Choose the right tool**: Use sanitize for character validity, normalize for format standardization.\n2. **Don't double-process**: If normalize produces a valid identifier, don't sanitize it again.\n3. **Document intent**: When using these functions, add comments explaining which pattern you're using and why.\n4. **Validate assumptions**: If you assume input is already valid, document that assumption.\n5. **Consider defaults**: Use `SanitizeIdentifier` when you need a fallback default value for empty results.\n\n#### Anti-Patterns\n\n**Don't sanitize already-normalized strings**:\n```go\n\u002F\u002F BAD: Sanitizing a normalized workflow name\nnormalized := normalizeWorkflowName(\"weekly-research.md\")\nsanitized := SanitizeWorkflowName(normalized) \u002F\u002F Unnecessary!\n```\n\n**Don't normalize for character validity**:\n```go\n\u002F\u002F BAD: Using normalize for invalid characters\nuserInput := \"My Workflow: Test\u002FBuild\"\nnormalized := normalizeWorkflowName(userInput) \u002F\u002F Wrong tool!\n\u002F\u002F normalized = \"My Workflow: Test\u002FBuild\" (unchanged - invalid chars remain)\n```\n\n\n### WASM Build-Variant Pattern\n\nSeven files in `pkg\u002Fworkflow\u002F` provide stub implementations of OS-dependent\nfeatures for the WASM compilation target (`GOOS=js GOARCH=wasm`) used by the\ngh-aw web playground. Each file is named with the `_wasm.go` suffix (Go's\nimplicit filename build constraint for `GOARCH=wasm`) **and** carries an\nexplicit `\u002F\u002Fgo:build js || wasm` tag at line 1:\n\n```\npkg\u002Fworkflow\u002Fdependabot_wasm.go\npkg\u002Fworkflow\u002Fdocker_validation_wasm.go\npkg\u002Fworkflow\u002Fgit_helpers_wasm.go\npkg\u002Fworkflow\u002Fgithub_cli_wasm.go\npkg\u002Fworkflow\u002Fnpm_validation_wasm.go\npkg\u002Fworkflow\u002Fpip_validation_wasm.go\npkg\u002Fworkflow\u002Frepository_features_validation_wasm.go\n```\n\nEach `_wasm.go` file mirrors the public\u002Fpackage-level function signatures of\nits non-WASM counterpart but replaces OS calls (exec, filesystem, network)\nwith either no-ops or `fmt.Errorf(\"... not available in Wasm\")` returns.\n\n#### When a `_wasm.go` Stub is Required\n\nAdd a `_wasm.go` stub whenever you add a **new function** to an existing\n`_wasm.go`-guarded file (or create a new file that calls OS-level tools at\ncompile\u002Fvalidation time). Specifically:\n\n- Functions that call `os\u002Fexec` or run external binaries (gh, git, docker,\n  npm, pip, uv, etc.)\n- Functions that read from the real filesystem during compilation\n- Functions that perform network I\u002FO at validation time\n\nFunctions that **do not** need a WASM stub:\n- Pure data transformations (string manipulation, YAML marshaling)\n- Functions that only operate on in-memory data structures\n- Functions gated behind `WithSkipValidation(true)` (already excluded at\n  runtime, but still need to compile)\n\n#### How to Add a Stub\n\n1. Identify the non-WASM file (e.g., `github_cli.go`).\n2. Open (or create) the corresponding `_wasm.go` file (e.g.,\n   `github_cli_wasm.go`).\n3. Ensure the build tag at line 1 is `\u002F\u002Fgo:build js || wasm`.\n4. Add a stub with the same signature that returns a zero value and\u002For an\n   error:\n   ```go\n   func MyNewFunction(args ...string) ([]byte, error) {\n       return nil, fmt.Errorf(\"MyNewFunction not available in Wasm\")\n   }\n   ```\n5. Verify the WASM build still compiles:\n   ```bash\n   GOOS=js GOARCH=wasm go build .\u002Fpkg\u002Fworkflow\u002F\n   ```\n\n#### Known Gap\n\n`github_cli_wasm.go` currently omits stubs for `enrichGHError`,\n`runGHWithSpinnerContext`, `RunGHCombinedContext`, `RunGHWithHost`, and\n`SetGHHostEnv`. These are unexported helpers or thin wrappers called only\nby the exported `RunGH*` family, which are already stubbed; the compiler\ndoes not reference them directly. This is intentional — avoid adding stubs\nfor unexported helpers unless the WASM build breaks.\n\n\n",{"name":5,"description":7},"main","8541229759617347888641eba917d3b0ad66a984",".github\u002Fskills\u002Fdeveloper-code-organization",626,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw","https:\u002F\u002Fgh.io\u002Fgh-aw","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-15 06:45:15",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add github\u002Fgh-aw --skill developer-code-organization",{"tool":62,"command":63},"bunx","bunx skills add github\u002Fgh-aw --skill developer-code-organization",{"tool":65,"command":66},"pnpm","pnpm dlx skills add github\u002Fgh-aw --skill developer-code-organization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fdeveloper-code-organization\u002FSKILL.md",true,[],[71,79,87,114,131,156],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"01M7DQYVZ9W9DDXKQ9452SNP8J","cracktro","Edit, preview, and verify the standalone interactive talk deck in docs\u002Fpublic\u002Fcracktro (slides, SVG diagrams, transitions, WebAudio sound).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcracktro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":86},"01M7612HQ4378TK8QZ5HPAF4KR","create-connector","Create or extend a declaration-only third-party connector, with narrow reads, separate safe outputs, optional protected triggers, and offline conformance evidence.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcreate-connector\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":101,"publishedAt":41},"01M6ADC942STTXHFV410J4DH0X","GitHub Agentic Workflows","GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension for writing Agentic Workflows in markdown and compiling them to GitHub Actions.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002FSKILL.md",[93,98],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",[9,102,103,104,105,106,107,108,109,37,30,110,111,112,113],"github agentic workflows","agentic workflows","workflows","agentic","extension","markdown","github cli","cli","compiling","writing","github actions","actions",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":41},"01M6ADC6ZXSA46N9XD6VNAP1MS","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[121,122,123,124,125,126,127,128,35,129,130],"windows","windows compatibility","compatibility","command","git","bugs","platform","high","cross-platform","path",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":41},"01M6ADC44957SVQF96R5YY247P","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[138,139,140,141,142,109,143,144,145,146,147,148,149,150,30,151,152,153,154,155],"versioning","policy","versioning policy","gate","implementation","workspace","pr","sdk","release","ci","npm","semver","squad","incident","incidents","Rules","version","resolution",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":166,"publishedAt":41},"01M6ADC1PHMEAEVR87F8PDR89X","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[162,165],{"categoryNo":163,"categoryName":164,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},[167,168,169,170,171,172,173,174,175,176,177,178,179,30,180,181],"tiered memory","memory","performance","design","agent memory","proposal","cold","model","wiki","spawn","memory-management","context","three","runtime","management"]