Merge pull request #828 from github/localden/updates

Update clarify.md

AGENTS.md

@@ -37,58 +37,57 @@ Specify supports multiple AI agents by generating agent-specific command files a
 | **Cursor** | `.cursor/commands/` | Markdown | `cursor-agent` | Cursor CLI |
 | **Qwen Code** | `.qwen/commands/` | TOML | `qwen` | Alibaba's Qwen Code CLI |
 | **opencode** | `.opencode/command/` | Markdown | `opencode` | opencode CLI |
+| **Codex CLI** | `.codex/commands/` | Markdown | `codex` | Codex CLI |
 | **Windsurf** | `.windsurf/workflows/` | Markdown | N/A (IDE-based) | Windsurf IDE workflows |
+| **Kilo Code** | `.kilocode/rules/` | Markdown | N/A (IDE-based) | Kilo Code IDE |
+| **Auggie CLI** | `.augment/rules/` | Markdown | `auggie` | Auggie CLI |
+| **Roo Code** | `.roo/rules/` | Markdown | N/A (IDE-based) | Roo Code IDE |
 | **CodeBuddy** | `.codebuddy/commands/` | Markdown | `codebuddy` | CodeBuddy |
 | **Amazon Q Developer CLI** | `.amazonq/prompts/` | Markdown | `q` | Amazon Q Developer CLI |
 
 ### Step-by-Step Integration Guide
 
-Follow these steps to add a new agent (using Windsurf as an example):
+Follow these steps to add a new agent (using a hypothetical new agent as an example):
 
-#### 1. Update AI_CHOICES Constant
+#### 1. Add to AGENT_CONFIG
 
-Add the new agent to the `AI_CHOICES` dictionary in `src/specify_cli/__init__.py`:
+**IMPORTANT**: Use the actual CLI tool name as the key, not a shortened version.
+
+Add the new agent to the `AGENT_CONFIG` dictionary in `src/specify_cli/__init__.py`. This is the **single source of truth** for all agent metadata:
 
 ```python
-AI_CHOICES = {
+AGENT_CONFIG = {
-    "copilot": "GitHub Copilot",
+    # ... existing agents ...
-    "claude": "Claude Code", 
+    "new-agent-cli": {  # Use the ACTUAL CLI tool name (what users type in terminal)
-    "gemini": "Gemini CLI",
+        "name": "New Agent Display Name",
-    "cursor": "Cursor",
+        "folder": ".newagent/",  # Directory for agent files
-    "qwen": "Qwen Code",
+        "install_url": "https://example.com/install",  # URL for installation docs (or None if IDE-based)
-    "opencode": "opencode",
+        "requires_cli": True,  # True if CLI tool required, False for IDE-based agents
-    "windsurf": "Windsurf",
+    },
-    "codebuddy": "CodeBuddy"
-    "q": "Amazon Q Developer CLI"
 }
 ```
 
-Also update the `agent_folder_map` in the same file to include the new agent's folder for the security notice:
+**Key Design Principle**: The dictionary key should match the actual executable name that users install. For example:
+- ✅ Use `"cursor-agent"` because the CLI tool is literally called `cursor-agent`
+- ❌ Don't use `"cursor"` as a shortcut if the tool is `cursor-agent`
 
-```python
+This eliminates the need for special-case mappings throughout the codebase.
-agent_folder_map = {
+
-    "claude": ".claude/",
+**Field Explanations**:
-    "gemini": ".gemini/",
+- `name`: Human-readable display name shown to users
-    "cursor": ".cursor/",
+- `folder`: Directory where agent-specific files are stored (relative to project root)
-    "qwen": ".qwen/",
+- `install_url`: Installation documentation URL (set to `None` for IDE-based agents)
-    "opencode": ".opencode/",
+- `requires_cli`: Whether the agent requires a CLI tool check during initialization
-    "codex": ".codex/",
-    "windsurf": ".windsurf/",
-    "kilocode": ".kilocode/",
-    "auggie": ".auggie/",
-    "copilot": ".github/",
-    "q": ".amazonq/",
-    "codebuddy": ".codebuddy/"
-}
-```
 
 #### 2. Update CLI Help Text
 
-Update all help text and examples to include the new agent:
+Update the `--ai` parameter help text in the `init()` command to include the new agent:
 
-- Command option help: `--ai` parameter description
+```python
-- Function docstrings and examples
+ai_assistant: str = typer.Option(None, "--ai", help="AI assistant to use: claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, codebuddy, new-agent-cli, or q"),
-- Error messages with agent lists
+```
+
+Also update any function docstrings, examples, and error messages that list available agents.
 
 #### 3. Update README Documentation
 
@@ -192,11 +191,58 @@ elif selected_ai == "windsurf":
         agent_tool_missing = True
 ```
 
-**Note**: Skip CLI checks for IDE-based agents (Copilot, Windsurf).
+**Note**: CLI tool checks are now handled automatically based on the `requires_cli` field in AGENT_CONFIG. No additional code changes needed in the `check()` or `init()` commands - they automatically loop through AGENT_CONFIG and check tools as needed.
+
+## Important Design Decisions
+
+### Using Actual CLI Tool Names as Keys
+
+**CRITICAL**: When adding a new agent to AGENT_CONFIG, always use the **actual executable name** as the dictionary key, not a shortened or convenient version.
+
+**Why this matters:**
+- The `check_tool()` function uses `shutil.which(tool)` to find executables in the system PATH
+- If the key doesn't match the actual CLI tool name, you'll need special-case mappings throughout the codebase
+- This creates unnecessary complexity and maintenance burden
+
+**Example - The Cursor Lesson:**
+
+❌ **Wrong approach** (requires special-case mapping):
+```python
+AGENT_CONFIG = {
+    "cursor": {  # Shorthand that doesn't match the actual tool
+        "name": "Cursor",
+        # ...
+    }
+}
+
+# Then you need special cases everywhere:
+cli_tool = agent_key
+if agent_key == "cursor":
+    cli_tool = "cursor-agent"  # Map to the real tool name
+```
+
+✅ **Correct approach** (no mapping needed):
+```python
+AGENT_CONFIG = {
+    "cursor-agent": {  # Matches the actual executable name
+        "name": "Cursor",
+        # ...
+    }
+}
+
+# No special cases needed - just use agent_key directly!
+```
+
+**Benefits of this approach:**
+- Eliminates special-case logic scattered throughout the codebase
+- Makes the code more maintainable and easier to understand
+- Reduces the chance of bugs when adding new agents
+- Tool checking "just works" without additional mappings
 
 ## Agent Categories
 
 ### CLI-Based Agents
+
 Require a command-line tool to be installed:
 - **Claude Code**: `claude` CLI
 - **Gemini CLI**: `gemini` CLI  
@@ -260,19 +306,22 @@ Different agents use different argument placeholders:
 
 ## Common Pitfalls
 
-1. **Forgetting update scripts**: Both bash and PowerShell scripts must be updated
+1. **Using shorthand keys instead of actual CLI tool names**: Always use the actual executable name as the AGENT_CONFIG key (e.g., `"cursor-agent"` not `"cursor"`). This prevents the need for special-case mappings throughout the codebase.
-2. **Missing CLI checks**: Only add for agents that actually have CLI tools
+2. **Forgetting update scripts**: Both bash and PowerShell scripts must be updated when adding new agents.
-3. **Wrong argument format**: Use correct placeholder format for each agent type
+3. **Incorrect `requires_cli` value**: Set to `True` only for agents that actually have CLI tools to check; set to `False` for IDE-based agents.
-4. **Directory naming**: Follow agent-specific conventions exactly
+4. **Wrong argument format**: Use correct placeholder format for each agent type (`$ARGUMENTS` for Markdown, `{{args}}` for TOML).
-5. **Help text inconsistency**: Update all user-facing text consistently
+5. **Directory naming**: Follow agent-specific conventions exactly (check existing agents for patterns).
+6. **Help text inconsistency**: Update all user-facing text consistently (help strings, docstrings, README, error messages).
 
 ## Future Considerations
 
 When adding new agents:
+
 - Consider the agent's native command/workflow patterns
 - Ensure compatibility with the Spec-Driven Development process
 - Document any special requirements or limitations
 - Update this guide with lessons learned
+- Verify the actual CLI tool name before adding to AGENT_CONFIG
 
 ---
 

README.md

@@ -61,6 +61,12 @@ specify init <PROJECT_NAME>
 specify check
 ```
 
+To upgrade specify run:
+
+```bash
+uv tool install specify-cli --force --from git+https://github.com/github/spec-kit.git
+```
+
 #### Option 2: One-time Usage
 
 Run directly without installing:

src/specify_cli/__init__.py

@@ -882,7 +882,7 @@ def init(
 
     should_init_git = False
     if not no_git:
-        should_init_git = check_tool("git", "https://git-scm.com/downloads")
+        should_init_git = check_tool("git")
         if not should_init_git:
             console.print("[yellow]Git not found - will skip repository initialization[/yellow]")
 
@@ -904,7 +904,7 @@ def init(
         agent_config = AGENT_CONFIG.get(selected_ai)
         if agent_config and agent_config["requires_cli"]:
             install_url = agent_config["install_url"]
-            if not check_tool(selected_ai, install_url):
+            if not check_tool(selected_ai):
                 error_panel = Panel(
                     f"[cyan]{selected_ai}[/cyan] not found\n"
                     f"Install from: [cyan]{install_url}[/cyan]\n"

templates/commands/clarify.md

@@ -97,7 +97,15 @@ Execution steps:
 
 4. Sequential questioning loop (interactive):
     - Present EXACTLY ONE question at a time.
-    - For multiple‑choice questions render options as a Markdown table:
+    - For multiple‑choice questions:
+       * **Analyze all options** and determine the **most suitable option** based on:
+          - Best practices for the project type
+          - Common patterns in similar implementations
+          - Risk reduction (security, performance, maintainability)
+          - Alignment with any explicit project goals or constraints visible in the spec
+       * Present your **recommended option prominently** at the top with clear reasoning (1-2 sentences explaining why this is the best choice).
+       * Format as: `**Recommended:** Option [X] - <reasoning>`
+       * Then render all options as a Markdown table:
 
        | Option | Description |
        |--------|-------------|
@@ -106,9 +114,14 @@ Execution steps:
        | C | <Option C description> | (add D/E as needed up to 5)
        | Short | Provide a different short answer (<=5 words) | (Include only if free-form alternative is appropriate)
 
-    - For short‑answer style (no meaningful discrete options), output a single line after the question: `Format: Short answer (<=5 words)`.
+       * After the table, add: `You can reply with the option letter (e.g., "A"), accept the recommendation by saying "yes" or "recommended", or provide your own short answer.`
+    - For short‑answer style (no meaningful discrete options):
+       * Provide your **suggested answer** based on best practices and context.
+       * Format as: `**Suggested:** <your proposed answer> - <brief reasoning>`
+       * Then output: `Format: Short answer (<=5 words). You can accept the suggestion by saying "yes" or "suggested", or provide your own answer.`
     - After the user answers:
-       * Validate the answer maps to one option or fits the <=5 word constraint.
+       * If the user replies with "yes", "recommended", or "suggested", use your previously stated recommendation/suggestion as the answer.
+       * Otherwise, validate the answer maps to one option or fits the <=5 word constraint.
        * If ambiguous, ask for a quick disambiguation (count still belongs to same question; do not advance).
        * Once satisfactory, record it in working memory (do not yet write to disk) and move to the next queued question.
     - Stop asking further questions when:

templates/vscode-settings.json

@@ -8,6 +8,6 @@
     },
     "chat.tools.terminal.autoApprove": {
         ".specify/scripts/bash/": true,
-        ".specify/scripts/ps/": true
+        ".specify/scripts/powershell/": true
     }
 }