Files
github-spec-kit/src/specify_cli/integrations/kimi/__init__.py
Manfred Riem 53d9543355 feat: make agent-context extension a full opt-in (#3097)
* docs: add Spec Kit spec for agent-context full opt-in

Use Spec Kit's own specify workflow to author the spec that makes the
agent-context extension a full opt-in, removing all agent-context
configuration/support from the Python codebase and removing the
deprecation message. Force-added despite specs/ being gitignored; the
generated artifact will be purged prior to merge.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: add Spec Kit plan artifacts for agent-context full opt-in

Phase 0/1 of the SDD plan workflow: plan.md, research.md, data-model.md,
quickstart.md, and contracts/cli-behavior.md. Constitution Check is a
documented no-op (repo has no ratified constitution). Force-added despite
specs/ being gitignored; generated artifacts will be purged prior to merge.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: correct Constitution Check against ratified v1.0.0

Earlier draft wrongly treated the gate as a no-op; the fork's main is 16
commits behind upstream/main, which carries .specify/memory/constitution.md.
Re-evaluate the feature against Principles I-V (all PASS) and note that
Principle I mandates keeping context_file as a declared class attribute,
validating the R1 metadata decision.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: refresh plan artifacts against synced upstream/main

After syncing fork main to upstream and rebasing, re-scan the current
agent-context surface. Upstream generalized the single context_file into a
plural context_files concept with new resolver helpers
(_resolve_context_files, _resolve_context_file_values,
_format_context_file_values) and upsert/remove now loop over multiple
files. Update research.md, data-model.md, contracts, quickstart grep
guards, and the plan summary to cover the expanded removal scope.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: add Spec Kit tasks for agent-context full opt-in

Phase 2 of SDD: dependency-ordered tasks.md (30 tasks) organized by the
three user stories, with mandatory test tasks (Constitution Principle II)
and a foundational phase decoupling __CONTEXT_FILE__ resolution from the
extension config. Includes the extension self-seeding task (T015) and a
static guard test (T002) enforcing zero agent-context references in the CLI.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* feat!: remove agent-context lifecycle from the Specify CLI

Make the agent-context extension a full opt-in. The CLI no longer
installs the extension during init, writes agent-context-config.yml,
or creates/updates/removes the managed Spec Kit section in agent
context files. Context-section upsert/remove, marker resolution,
extension-enabled gating, the config helpers, and the obsolete inline
deprecation warning are all removed. Integration context_file stays as
inert metadata; __CONTEXT_FILE__ now resolves from registry metadata.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* feat(agent-context): self-seed context file from the active integration

When agent-context-config.yml has no context_file/context_files, the
bundled bash and PowerShell update scripts now resolve the context file
from the active integration in .specify/init-options.json via the
integration registry, so the extension no longer depends on the CLI
writing its config.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* test+docs: update suite and docs for agent-context opt-in

Update integration/extension tests to expect no agent-context install,
config, or context-section writes during init. Add a static guard test
(test_agent_context_cli_free.py) asserting the CLI source is free of
agent-context lifecycle symbols, plus backward-compatibility tests for
legacy projects. Refresh AGENTS.md, the extension README, and add a
CHANGELOG entry describing the opt-in behavior change.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix(agent-context): warn on self-seed failure, correct docs, speed up guard test

Address PR review feedback:
- Self-seed scripts (bash + PowerShell) now emit an actionable warning when
  an active integration is configured but specify_cli cannot be imported by
  the chosen Python (e.g. pipx installs), or when the integration declares no
  context file, instead of silently falling through to 'nothing to do'.
- Correct the extension README disable note: command rendering never reads the
  extension config; __CONTEXT_FILE__ is always substituted from integration
  metadata, so a stale context_files value cannot affect rendering.
- Cache CLI source reads in the static guard test via a module-scoped fixture
  so the directory walk happens once instead of once per forbidden symbol.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* feat(agent-context): ship self-owned per-agent context-file defaults

The extension now bundles agent-context-defaults.json (key→context_file
map) and self-seeds from it, dropping any dependency on the Specify CLI
registry. Both the bash and PowerShell update scripts read the bundled
JSON map keyed by the active integration from init-options.json.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* feat!: remove all agent-context state from the Specify CLI

Strip every context_file reference from the CLI: the field on all 35
integration classes, the IntegrationBase plumbing (process_template
param/step, _context_file_display, docstrings), the __CONTEXT_FILE__
resolution in agents.py, the legacy context_file/context_markers
popping in _helpers.py, and the context_file template in
integration_scaffold.py. Also drop the Agent context update step and
__CONTEXT_FILE__ placeholder from templates/commands/plan.md.

The agent-context extension now solely owns all context-file knowledge,
including the per-agent default mapping.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* test: drop context_file coverage and guard against CLI reintroduction

Remove CONTEXT_FILE attrs and context_file assertions across the base
mixins, all 35 per-integration test files, shared integration tests, and
conftest stubs. Rewrite the base-mixin context tests to assert no managed
section is written and no __CONTEXT_FILE__ placeholder survives. Extend
the CLI-free static guard to forbid context_file, __CONTEXT_FILE__, and
_context_file_display in src/specify_cli, and have the extension tests
copy the bundled defaults JSON so self-seed runs without the CLI.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: reflect full removal of agent-context state from the CLI

Update AGENTS.md (integration examples, required-fields table, context
behavior section, pitfalls), CHANGELOG, and the SDD spec artifacts
(FR-007, SC-002, data-model) to state that the CLI carries no
context_file and the extension fully owns the per-agent default mapping
via agent-context-defaults.json.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: align SDD artifacts with full context_file removal

Update research.md (R1, R2, R4, summary table), contracts/cli-behavior.md
(C3, C5), tasks.md (Phase 2, T026, notes), plan.md (Principle I, source
map), and checklists/requirements.md so the spec artifacts reflect the
implemented decision: the CLI carries no context_file attribute or
__CONTEXT_FILE__ resolution, and the per-agent defaults map lives in the
extension. Resolves PR review #4548130110.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: scrub stale context-file mentions from CLI docstrings

Update the multi_install_safe docstring (drop the removed "context file"
invariant), the RovoDev setup docstring (no longer upserts a context
section), the Copilot module docstring (drop the context-file line), and
tighten the _update_init_options_for_integration note. Pure docstring
changes — no behavioral impact. Resolves PR review #4548237085.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* test+docs: harden agent-context test helper and fix stale docs

- base.py: document multi_install_safe as an optional subclass attribute
  in the IntegrationBase docstring.
- test_cli.py: clarify the init-options assertion is guarding against
  leftover legacy agent-context keys, not relocation.
- test_extension_agent_context.py: _install_agent_context_config now
  asserts the bundled agent-context-defaults.json exists and always
  copies it, so self-seeding tests fail loudly instead of silently
  skipping when the map is missing.
- test_integration_cursor_agent.py: drop Path/IntegrationManifest imports
  left unused after removing the context-section frontmatter tests.

Resolves PR review #4548293116.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chore: remove gitignored SDD artifacts from specs/

The specs/001-agent-context-full-optin/ artifacts were force-added for
dogfooding visibility, but specs/ is gitignored and these were always
intended to be purged before merge. Remove them so merging does not add
an intentionally-untracked directory to repo history.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* chore: keep CHANGELOG.md identical to upstream

CHANGELOG.md is auto-generated at release time, so the branch should not
carry a manual entry. Restore it to match upstream/main exactly.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: preserve Cursor .mdc frontmatter in agent-context updater scripts

The bundled agent-context updater scripts wrote the managed section as
plain text. For Cursor-style `.mdc` targets this dropped the required
`---\nalwaysApply: true\n---` frontmatter, reintroducing the rule-loading
bug originally fixed in #1699. Port the `_ensure_mdc_frontmatter` logic
into both the bash and PowerShell updaters: prepend frontmatter when
missing, repair `alwaysApply` when set to the wrong value, and leave
non-`.mdc` targets untouched. Add regression tests covering both shells.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* test: scope CLI-free guard to agent-context-specific symbols

Drop the bare "context_file" substring from FORBIDDEN_SYMBOLS so the
guard no longer fails on unrelated future CLI fields named context_file.
The list still covers agent-context-specific identifiers (__CONTEXT_FILE__,
_context_file_display, _resolve_context_files, _resolve_context_file_values).

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: harden agent-context bash self-seed against malformed init JSON

Two robustness fixes in the embedded Python self-seed logic:
- Coerce the integration value from init-options.json to a string only when
  it is actually a string; otherwise treat it as unset so a corrupted
  dict/list value degrades to the existing nothing-to-do behavior instead of
  breaking the agents-map lookup.
- Normalize agent-context-defaults.json: only use 'agents' when both the JSON
  root and the 'agents' value are dicts, so a wrong-shaped (but valid) JSON
  falls back to the warning path instead of raising on .get.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: correct PowerShell hyphenated key lookup and regex replace count

- Self-seed now reads the defaults mapping via
  $defaults.agents.PSObject.Properties[$integrationKey].Value instead of
  member access ($defaults.agents.$integrationKey), which parsed hyphenated
  keys like 'cursor-agent'/'kiro-cli' as subtraction and failed to resolve.
- Replace the static [regex]::Replace(..., 1) call, whose trailing 1 was
  interpreted as RegexOptions.IgnoreCase rather than a replacement count, with
  an instance Regex whose Replace(input, replacement, 1) limits to the first
  match as intended.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* fix: make bash .mdc frontmatter guard case-insensitive

The bash updater only injected Cursor .mdc frontmatter when ctx_path ended
in lowercase '.mdc', so a mixed/upper-case extension (e.g. specify-rules.MDC)
was skipped and Cursor would not auto-load the rule file. Compare against the
casefolded path. The PowerShell variant already uses -match, which is
case-insensitive by default, so no change is needed there.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* docs: document separator-agnostic agent-context update invocation

The README hard-coded the dot-notation slash command
(/speckit.agent-context.update), which hyphen-separator agents like Forge and
Cline do not recognize. Document the canonical command ID plus both slash
invocations so users copy the form their agent accepts.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-29 15:27:26 -05:00

372 lines
14 KiB
Python

"""Kimi Code integration — skills-based agent (Moonshot AI).
Kimi uses the ``.kimi-code/skills/speckit-<name>/SKILL.md`` layout with
``/skill:speckit-<name>`` invocation syntax.
Legacy migration covers projects created before Kimi Code CLI moved to
this layout and handles two distinct changes: the directory move from
``.kimi/`` to ``.kimi-code/``, and the dotted-to-hyphenated skill naming
(``speckit.xxx`` → ``speckit-xxx``).
"""
from __future__ import annotations
import shutil
from pathlib import Path
from typing import Any
from ..base import IntegrationOption, SkillsIntegration
from ..manifest import IntegrationManifest
class KimiIntegration(SkillsIntegration):
"""Integration for Kimi Code CLI (Moonshot AI)."""
key = "kimi"
config = {
"name": "Kimi Code",
"folder": ".kimi-code/",
"commands_subdir": "skills",
"install_url": "https://code.kimi.com/",
"requires_cli": True,
}
registrar_config = {
"dir": ".kimi-code/skills",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": "/SKILL.md",
}
multi_install_safe = False
def build_command_invocation(self, command_name: str, args: str = "") -> str:
"""Build Kimi's native skill invocation: ``/skill:speckit-<stem>``.
Kimi Code CLI invokes installed skills with a ``/skill:<name>``
slash command (e.g. ``/skill:speckit-plan``), not the bare
``/speckit-<name>`` form produced by the generic skills base
class. Overriding here keeps ``dispatch_command()`` and workflow
command steps aligned with the ``/skill:`` guidance shown at init
time and in rendered hook invocations.
"""
stem = command_name
if stem.startswith("speckit."):
stem = stem[len("speckit.") :]
invocation = "/skill:speckit-" + stem.replace(".", "-")
if args:
invocation = f"{invocation} {args}"
return invocation
def post_process_skill_content(self, content: str) -> str:
"""Ensure in-skill cross-command references use Kimi's `/skill:` syntax."""
content = super().post_process_skill_content(content)
return content.replace("/speckit-", "/skill:speckit-")
@classmethod
def options(cls) -> list[IntegrationOption]:
return [
IntegrationOption(
"--skills",
is_flag=True,
default=True,
help="Install as agent skills (default for Kimi)",
),
IntegrationOption(
"--migrate-legacy",
is_flag=True,
default=False,
help=(
"Migrate legacy Kimi installations: "
".kimi/skills/ → .kimi-code/skills/ and speckit.xxx → speckit-xxx"
),
),
]
def setup(
self,
project_root: Path,
manifest: IntegrationManifest,
parsed_options: dict[str, Any] | None = None,
**opts: Any,
) -> list[Path]:
"""Install skills with optional legacy migration."""
parsed_options = parsed_options or {}
# Refuse a symlinked destination before any writes occur. base
# setup() only rejects a destination that *escapes* project_root
# after resolve(), so an in-tree symlinked ``.kimi-code`` /
# ``.kimi-code/skills`` (e.g. ``-> .``) would still pass that check
# and misdirect the SKILL.md writes into an unintended in-tree
# location (e.g. ``./skills/``). Reject any symlinked destination
# component up front so this never happens.
new_skills_dir = self.skills_dest(project_root)
if _has_symlinked_component(new_skills_dir, project_root):
raise ValueError(
f"Skills destination {new_skills_dir} contains a symlinked "
f"path component; refusing to install into it."
)
# Run base setup first so new-path targets (speckit-*) exist,
# then migrate/clean legacy dirs without risking user content loss.
created = super().setup(
project_root, manifest, parsed_options=parsed_options, **opts
)
if parsed_options.get("migrate_legacy", False):
old_skills_dir = project_root / ".kimi" / "skills"
# Validate both endpoints. base setup() already rejects a
# destination that *escapes* the project root, but an in-tree
# symlinked ``.kimi-code``/``.kimi-code/skills`` (e.g. ``-> .``)
# would still misdirect the move; ``_is_safe_legacy_dir`` rejects
# any symlinked component, giving the destination the same
# protection as the source.
if _is_safe_legacy_dir(old_skills_dir, project_root) and (
_is_safe_legacy_dir(new_skills_dir, project_root)
):
_migrate_legacy_kimi_skills_dir(old_skills_dir, new_skills_dir)
return created
def teardown(
self,
project_root: Path,
manifest: IntegrationManifest,
*,
force: bool = False,
) -> tuple[list[Path], list[Path]]:
"""Uninstall Kimi skills and remove leftover legacy directories."""
removed, skipped = super().teardown(project_root, manifest, force=force)
old_skills_dir = project_root / ".kimi" / "skills"
if _is_safe_legacy_dir(old_skills_dir, project_root):
legacy_dirs = sorted(
[*old_skills_dir.glob("speckit-*"), *old_skills_dir.glob("speckit.*")]
)
for legacy_dir in legacy_dirs:
if legacy_dir.is_symlink() or not legacy_dir.is_dir():
continue
if _is_speckit_generated_skill(legacy_dir):
try:
shutil.rmtree(legacy_dir)
removed.append(legacy_dir)
except OSError:
skipped.append(legacy_dir)
try:
old_skills_dir.rmdir()
except OSError:
pass
return removed, skipped
def _has_symlinked_component(path: Path, project_root: Path) -> bool:
"""Return ``True`` when *path* escapes *project_root* or any component is a symlink.
Walks the components strictly between *project_root* and *path*
(including the final one) and reports whether any of them is a symlink.
Components that do not exist yet are not symlinks, so this safely handles
a not-yet-created destination. *project_root* itself is trusted and never
checked. A *path* outside *project_root* is treated as unsafe.
"""
try:
relative = path.relative_to(project_root)
except ValueError:
return True
current = project_root
for part in relative.parts:
current = current / part
if current.is_symlink():
return True
return False
def _is_safe_legacy_dir(path: Path, project_root: Path) -> bool:
"""Return ``True`` when *path* is a real directory safely inside *project_root*.
Legacy migration and cleanup ``shutil.move()`` and ``shutil.rmtree()``
directories, so a symlinked ``.kimi``/``.kimi/skills`` (or one reached
through a symlinked parent) must never be followed: doing so could
relocate or delete content living outside the project tree — or operate
on an unrelated in-tree directory (e.g. ``.kimi -> .`` makes
``.kimi/skills`` resolve to ``./skills``).
Checking only the fully-resolved path is insufficient, because a symlink
pointing elsewhere *inside* the project still resolves to a location under
*project_root*. We therefore reject the path when it is not a directory,
when any component between *project_root* and *path* is a symlink
(including the final component), or when the resolved path escapes the
resolved *project_root*.
"""
if not path.is_dir():
return False
# Reject if any path component below project_root is a symlink (or the
# path escapes project_root). We trust project_root itself, so only
# components strictly under it are checked.
if _has_symlinked_component(path, project_root):
return False
try:
resolved = path.resolve()
root = project_root.resolve()
except OSError:
return False
return resolved == root or root in resolved.parents
def _migrate_legacy_kimi_skills_dir(
old_skills_dir: Path, new_skills_dir: Path
) -> tuple[int, int]:
"""Migrate skills from the legacy ``.kimi/skills/`` directory to ``.kimi-code/skills/``.
Handles both hyphenated (``speckit-xxx``) and dotted (``speckit.xxx``)
legacy directory names. If a target already exists, the legacy dir is
only removed when its ``SKILL.md`` is byte-identical and no extra user
files are present.
Returns ``(migrated_count, removed_count)``.
"""
if not old_skills_dir.is_dir():
return (0, 0)
migrated_count = 0
removed_count = 0
# Process hyphenated dirs first, then dotted dirs.
legacy_dirs = sorted(old_skills_dir.glob("speckit-*")) + sorted(
old_skills_dir.glob("speckit.*")
)
for legacy_dir in legacy_dirs:
if legacy_dir.is_symlink() or not legacy_dir.is_dir():
continue
legacy_skill = legacy_dir / "SKILL.md"
# Treat a symlinked SKILL.md as invalid: later read_bytes() would
# otherwise follow it and read content from outside the project.
if legacy_skill.is_symlink() or not legacy_skill.is_file():
continue
target_name = _legacy_to_target_name(legacy_dir.name)
if not target_name:
continue
target_dir = new_skills_dir / target_name
# Skip if the legacy dir is already the target dir (same-directory call).
if legacy_dir.resolve() == target_dir.resolve():
continue
if not target_dir.exists():
target_dir.parent.mkdir(parents=True, exist_ok=True)
shutil.move(str(legacy_dir), str(target_dir))
migrated_count += 1
continue
# Target exists — only remove legacy if SKILL.md is identical.
# Skip when the target dir or its SKILL.md is a symlink (or the dir is
# not a real directory) so the byte comparison never follows a link
# outside the project. (legacy_skill is already guaranteed to be a real
# file by the guard above.)
if target_dir.is_symlink() or not target_dir.is_dir():
continue
target_skill = target_dir / "SKILL.md"
if target_skill.is_symlink() or not target_skill.is_file():
continue
try:
if target_skill.read_bytes() == legacy_skill.read_bytes():
has_extra = any(
child.name != "SKILL.md" for child in legacy_dir.iterdir()
)
if not has_extra:
shutil.rmtree(legacy_dir)
removed_count += 1
except OSError:
pass
# Remove the legacy skills directory if it is now empty.
try:
old_skills_dir.rmdir()
except OSError:
pass
return (migrated_count, removed_count)
def _legacy_to_target_name(legacy_name: str) -> str:
"""Convert a legacy skill directory name to the modern hyphenated form."""
if legacy_name.startswith("speckit-"):
return legacy_name
if legacy_name.startswith("speckit."):
suffix = legacy_name[len("speckit.") :]
if suffix:
return f"speckit-{suffix.replace('.', '-')}"
return ""
def _is_speckit_generated_skill(skill_dir: Path) -> bool:
"""Return True when *skill_dir* contains a Speckit-generated SKILL.md.
Uses the ``metadata.author`` and ``metadata.source`` fields written by
``SkillsIntegration.setup()`` to avoid deleting user-authored skills.
"""
skill_file = skill_dir / "SKILL.md"
# A symlinked SKILL.md is never treated as Speckit-generated, so teardown
# cleanup never follows it to read frontmatter from outside the project.
if skill_file.is_symlink() or not skill_file.is_file():
return False
try:
content = skill_file.read_text(encoding="utf-8")
except OSError:
return False
if not content.startswith("---"):
return False
parts = content.split("---", 2)
if len(parts) < 3:
return False
try:
import yaml
frontmatter = yaml.safe_load(parts[1])
except Exception:
return False
if not isinstance(frontmatter, dict):
return False
metadata = frontmatter.get("metadata", {})
if not isinstance(metadata, dict):
return False
author = metadata.get("author", "")
source = metadata.get("source", "")
return (
author == "github-spec-kit"
and isinstance(source, str)
and source.startswith("templates/commands/")
)
def _migrate_legacy_kimi_dotted_skills(skills_dir: Path) -> tuple[int, int]:
"""Compatibility shim — migrate legacy dotted skill dirs in place.
.. deprecated::
Kept for direct callers/tests. New code should call
``_migrate_legacy_kimi_skills_dir`` directly.
Delegates to ``_migrate_legacy_kimi_skills_dir`` with *skills_dir* as both
source and destination, so it processes every ``speckit-*`` and
``speckit.*`` entry under *skills_dir*. Because the two paths are
identical, the same-path short-circuit there skips any directory whose
target resolves to itself; in practice this renames dotted
``speckit.xxx`` dirs to hyphenated ``speckit-xxx`` in place and never
moves content outside *skills_dir*.
Returns ``(migrated_count, removed_count)``.
"""
return _migrate_legacy_kimi_skills_dir(skills_dir, skills_dir)