feat: add Kimi Code CLI agent support (#1790)

* feat: add Kimi Code (kimi) CLI agent support

- Register kimi in AGENT_CONFIG with folder `.kimi/`, markdown format, requires_cli=True
- Register kimi in CommandRegistrar.AGENT_CONFIGS
- Add kimi to supported agents table in AGENTS.md and README.md
- Add kimi to release packaging scripts (bash and PowerShell)
- Add kimi CLI installation to devcontainer post-create script
- Add kimi support to update-agent-context scripts (bash and PowerShell)
- Add 4 consistency tests covering all kimi integration surfaces
- Bump version to 0.1.14 and update CHANGELOG

* fix: include .specify/templates/ and real command files in release ZIPs

- Copy real command files from templates/commands/ (with speckit. prefix)
  instead of generating stubs, so slash commands have actual content
- Add .specify/templates/ to every ZIP so ensure_constitution_from_template
  can find constitution-template.md on init
- Add .vscode/settings.json to every ZIP
- Having 3 top-level dirs prevents the extraction flatten heuristic from
  incorrectly stripping the agent config folder (.kimi/, .claude/, etc.)
- Bump version to 0.1.14.1

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(kimi): use .kimi/skills/<name>/SKILL.md structure for Kimi Code CLI

Kimi Code CLI uses a skills system, not flat command files:
- Skills live in .kimi/skills/<name>/SKILL.md (project-level)
- Invoked with /skill:<name> (e.g. /skill:speckit.specify)
- Each skill is a directory containing SKILL.md with YAML frontmatter

Changes:
- AGENT_CONFIG["kimi"]["commands_subdir"] = "skills" (was "commands")
- create-release-packages.sh: new create_kimi_skills() function creates
  skill directories with SKILL.md from real template content
- Bump version to 0.1.14.2

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(test): align kimi commands_subdir assertion with skills structure

* fix: use forward slashes for tabnine path in create-release-packages.ps1

* fix: align kimi to .kimi/skills convention and fix ARGUMENTS unbound variable

* fix: address PR review comments for kimi agent support

  - Fix VERSION_NO_V undefined variable in create-github-release.sh
  - Restore version $1 argument handling in create-release-packages.sh
  - Fix tabnine/vibe/generic cases calling undefined generate_commands
  - Align roo path .roo/rules -> .roo/commands with AGENT_CONFIG
  - Fix kimi extension to use per-skill SKILL.md directory structure
  - Add parent mkdir before dest_file.write_text for nested paths
  - Restore devcontainer tools removed by regression + add Kimi CLI
  - Strengthen test_kimi_in_powershell_validate_set assertion

* fix: restore release scripts and address all PR review comments

  - Restore create-release-packages.sh to original with full generate_commands/
    rewrite_paths logic; add kimi case using create_kimi_skills function
  - Restore create-release-packages.ps1 to original with full Generate-Commands/
    Rewrite-Paths logic; add kimi case using New-KimiSkills function
  - Restore create-github-release.sh to original with proper $1 argument
    handling and VERSION_NO_V; add kimi zip entries
  - Add test_ai_help_includes_kimi for consistency with other agents
  - Strengthen test_kimi_in_powershell_validate_set to check ValidateSet

* fix: address second round of PR review comments

  - Add __AGENT__ and {AGENT_SCRIPT} substitutions in create_kimi_skills (bash)
  - Add __AGENT__ and {AGENT_SCRIPT} substitutions in New-KimiSkills (PowerShell)
  - Replace curl|bash Kimi installer with pipx install kimi-cli in post-create.sh

* fix: align kimi skill naming and add extension registrar test

  - Fix install_ai_skills() to use speckit.<cmd> naming for kimi (dot
    separator) instead of speckit-<cmd>, matching /skill:speckit.<cmd>
    invocation convention and packaging scripts
  - Add test_kimi_in_extension_registrar to verify CommandRegistrar.AGENT_CONFIGS
    includes kimi with correct dir and SKILL.md extension

* fix(test): align kimi skill name assertion with dot-separator convention

  test_skills_install_for_all_agents now expects speckit.specify (dot) for
  kimi and speckit-specify (hyphen) for all other agents, matching the
  install_ai_skills() implementation added in the previous commit.

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

src/specify_cli/__init__.py

@@ -265,6 +265,13 @@ AGENT_CONFIG = {
         "install_url": "https://github.com/mistralai/mistral-vibe",
         "requires_cli": True,
     },
+    "kimi": {
+        "name": "Kimi Code",
+        "folder": ".kimi/",
+        "commands_subdir": "skills",  # Kimi uses /skill:<name> with .kimi/skills/<name>/SKILL.md
+        "install_url": "https://code.kimi.com/",
+        "requires_cli": True,
+    },
     "generic": {
         "name": "Generic (bring your own agent)",
         "folder": None,  # Set dynamically via --ai-commands-dir
@@ -1188,7 +1195,12 @@ def install_ai_skills(project_path: Path, selected_ai: str, tracker: StepTracker
             # SKILL_DESCRIPTIONS lookups work.
             if command_name.startswith("speckit."):
                 command_name = command_name[len("speckit."):]
-            skill_name = f"speckit-{command_name}"
+            # Kimi CLI discovers skills by directory name and invokes them as
+            # /skill:<name> — use dot separator to match packaging convention.
+            if selected_ai == "kimi":
+                skill_name = f"speckit.{command_name}"
+            else:
+                skill_name = f"speckit-{command_name}"
 
             # Create skill directory (additive — never removes existing content)
             skill_dir = skills_dir / skill_name