Files
github-spec-kit/src/specify_cli/integrations/copilot/__init__.py
Davide Barletta 74662cffad feat: update Bob integration to skills-based layout for Bob 2.0 (#3415)
* feat: update Bob integration to skills-based layout for Bob 2.0

Bob 2.0 replaces the command-based workflow (.bob/commands/*.md) with
a skills-based layout (.bob/skills/speckit-<name>/SKILL.md), matching
the pattern used by Claude Code, Codex, and other skills-first agents.

- Switch BobIntegration from MarkdownIntegration to SkillsIntegration
- Update folder/dir from .bob/commands to .bob/skills
- Change extension from .md to /SKILL.md (skills layout)
- Add --skills option (default: True) consistent with Codex pattern
- Update tests to inherit from SkillsIntegrationTests (28 tests pass)
- Bump catalog entry to version 2.0.0 with updated description

Assisted-by: IBM Bob (model: claude-sonnet-4-5, autonomous)

* PR comments fix: keep old Bob 1 commands till next release

* Copilot suggested change

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* feat(bob): address copilot comments, make skills layout default, demote legacy commands to opt-in

* fix(bob): honor legacy_commands in ai_skills persistence and add bob to ALWAYS_SLASH_AGENTS

- init.py: suppress ai_skills=True when --legacy-commands is passed so
  extensions and presets target .bob/commands, not .bob/skills
- _invocation_style.py: add 'bob' to ALWAYS_SLASH_AGENTS so init next-steps
  and hook invocations always show /speckit-<name> (skills is the default
  layout; no ai_skills flag required)

* Copilot suggestion

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* fix(bob): extend IntegrationBase directly to avoid false isinstance(SkillsIntegration)

- bob/__init__.py: switch BobIntegration base from SkillsIntegration to
  IntegrationBase; add _BobSkillsHelper for skills-mode delegation; set
  invoke_separator='-' explicitly; set _skills_mode flag in setup() so
  consumers can derive the effective mode without isinstance checks
- _helpers.py: replace isinstance(integration, SkillsIntegration) guard
  with getattr(_skills_mode) so legacy-commands mode does not persist
  ai_skills=True
- _invocation_style.py: remove 'bob' from ALWAYS_SLASH_AGENTS — Bob 2.0
  skills are invoked via natural language, not /skill-name slash commands
- integrations/catalog.json: advance updated_at to 2026-07-15

* fix(lint): remove unused SkillsIntegration import from _helpers.py

* Copilot suggested change

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* feat(bob): add bob skills integration with registrar-based mode detection

* address 3 comments from copilot

* feat(bob): update registrar config to use legacy commands layout

* fix lint

* Suggested fix from Copilot

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* fix pr comment

* fix pr comment

* fix pr comment

* refactor(bob): resolve skills mode via base-class hooks + fix command-ref separators

Rework the dual-mode handling introduced for Bob 2.0 so an integration's
internal representation never leaks into shared init/install/upgrade code,
and fix the legacy command-reference separator surfaced in review.

Base-class contract:
- Add IntegrationBase.is_skills_mode(parsed_options) — the single hook the
  shared machinery consults to decide whether to persist ai_skills and render
  skill invocations. SkillsIntegration returns True; Copilot honors --skills /
  self._skills_mode; Bob returns `not legacy_commands`.
- Add IntegrationBase.invoke_separator_for_mode(skills_enabled) — resolves the
  command-ref separator from a project's persisted mode for registration paths
  that only have the ai_skills flag (no CLI parsed_options). Default is
  behavior-preserving; Bob maps skills->"-", legacy->".".
- BobIntegration stays on IntegrationBase (mirroring Copilot, the other
  dual-mode agent) and delegates setup() to internal _BobSkillsHelper /
  _BobMarkdownHelper. Removes the _skills_mode method and all
  isinstance(SkillsIntegration) / callable(_skills_mode) probing from
  _helpers.py and init.py.

Fix legacy separator (review feedback): CommandRegistrar.register_commands and
PresetManager._resolve_skill_command_refs previously read the single static
AGENT_CONFIGS[key]["invoke_separator"], so legacy .bob/commands/ extension and
preset command refs rendered /speckit-<cmd> instead of Bob 1.x /speckit.<cmd>.
Both now resolve the separator per project mode via invoke_separator_for_mode.

Tests: add regression coverage for the is_skills_mode / invoke_separator_for_mode
hooks and legacy extension command-ref separators; normalize a width-sensitive
workflow assertion to match its siblings. Full suite green.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob,copilot): address review — preserve legacy layout, dual-mode separators, extension-skill token resolution

Addresses PR review 4716036212 (3 comments):

1. Bob legacy-install regression: `use`/`switch`/`upgrade` on an existing
   Bob 1.x project (only `.bob/commands/` on disk, no stored
   `legacy_commands`) called `is_skills_mode(None)` -> True and rewrote
   `ai_skills=True`, silently switching extension/command-reference handling
   to the skills layout. `is_skills_mode` now takes an optional `project_root`;
   Bob preserves an already-installed legacy layout until an explicit upgrade
   creates `.bob/skills/`. A fresh project still defaults to skills.

2. Copilot dual-mode separator: `invoke_separator_for_mode` was inherited
   from the base (mode-independent) and returned Copilot's static `.`, so
   preset/extension command refs in a Copilot skills project rendered
   `/speckit.<name>` instead of `/speckit-<name>`. Override it on Copilot to
   track the persisted `ai_skills` state, consistent with
   `build_command_invocation` and `effective_invoke_separator`.

3. Bob extension-skill command-ref tokens: verified that merging main's
   generic `_resolve_command_ref_tokens` (#3544) resolves Bob's tokens via
   the `CONDITIONAL_SLASH_AGENTS` path (`/speckit-<name>`); added Bob to the
   command-ref regression parametrize plus dedicated Bob use-path tests.

All tests pass (full suite green; merged with current main incl. #3544).

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): resolve command-ref separator with project-aware mode before shared-infra refresh (review #3415)

The `use`/`switch` paths refresh shared infrastructure via
`_with_integration_setting()` / `_invoke_separator_for_integration()`,
which previously resolved the invoke separator through
`effective_invoke_separator` / `is_skills_mode` WITHOUT a project_root.
For a pre-PR Bob 1.x project (.bob/commands/ on disk, no stored options),
this defaulted to the skills "-" separator and rewrote rendered
shared-template command refs to /speckit-*, even though ai_skills stayed
false. Thread project_root through effective_invoke_separator, the two
runtime helpers, and every call site so Bob's on-disk legacy detection
governs the separator before shared infra is refreshed.

Add a rendered-shared-template regression test covering `use --force`.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): scope persisted ai_skills flag to active agent when resolving command-ref separator (review #3415)

`register_commands` runs once per detected agent, but the persisted
`ai_skills` flag describes only the active integration (`opts["ai"]`).
When another agent (e.g. Copilot) is active in skills mode while a
legacy `.bob/commands` layout is also present, the previous code passed
that global `True` to Bob's `invoke_separator_for_mode`, rewriting Bob
1.x command refs to `/speckit-*` instead of `/speckit.*`.

Only consult the persisted flag for the agent it describes
(`opts["ai"] == agent_name`); otherwise resolve the separator from the
agent's own project-aware `effective_invoke_separator(None, project_root)`.

Add regression tests covering the mismatched-active-agent case and a
control for Bob-active skills mode.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): detect Spec Kit layout from managed artifacts, not any skills dir (review #3415)

Two related mis-detections from review 4723246468:

1. `BobIntegration.is_skills_mode` treated the mere presence of a
   `.bob/skills/` directory as proof the project is skills-based. A legacy
   Spec Kit install (managed `.bob/commands/speckit.*.md`) that also carried
   unrelated Bob 2 skills would be misclassified as skills, so
   `integration use bob` persisted `ai_skills` and rewrote shared refs.
   Now the layout is inferred from managed Spec Kit artifacts: legacy/command
   mode only when managed `speckit.*.md` command files exist and no managed
   `speckit-*` skill dirs do.

2. The `register_commands` separator for an inactive agent used a disk-based
   `effective_invoke_separator(None, project_root)` fallback that could pick
   the skills separator even though the registrar writes the static command
   layout (`.bob/commands/*.md`). Inactive agents now resolve the separator
   from the registrar's actual output layout (`extension == "/SKILL.md"`),
   so command-layout files keep `/speckit.*` refs regardless of sibling dirs.

Update the affected hook/E2E tests to use managed artifacts and add
regression tests for the mixed-layout and inactive-registrar scenarios.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): apply managed-artifact detection on upgrade + consistent skill post-processing (review #3415)

Two issues from review 4723782860:

1. `BobIntegration.setup()` resolved the layout via `is_skills_mode(parsed_options)`
   WITHOUT `project_root`, so `integration upgrade bob` on a Bob 1.x install
   (managed `.bob/commands/speckit.*.md`, no stored options) ignored the
   existing command files, generated skills, and stale-deleted the legacy
   commands — silently migrating the project. Pass `project_root` so the same
   managed-artifact detection used by `use` also governs upgrades.

2. Only `_BobSkillsHelper` overrode `post_process_skill_content` to suppress
   the shared slash-command hook note. Preset/extension skill generators call
   that hook on the registered `BobIntegration`, which inherited
   `IntegrationBase`'s note-injecting default. Repeat the no-op (delegating to
   the skills helper) on the registered class so every Bob skill-generation
   path is consistent with intent-activated core Bob skills.

Add regression tests for the upgrade-preservation and post-processing paths.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* feat(bob): add --skills migration opt-in; fix separator + manifest loss (review #3415)

Address review #3415 (4724160183):

- Comment 1: Add an explicit `--skills` opt-in to BobIntegration. It forces
  the skills layout over on-disk auto-detection, giving legacy Bob 1.x
  installs a supported migration path
  (`integration upgrade bob --integration-options="--skills"`). `--skills`
  and `--legacy-commands` are mutually exclusive (clean exit-1 error).

- Comment 2: In CommandRegistrar.register_commands, derive the command-ref
  separator from the output layout (agent_config["extension"]) for the
  active agent too, not the persisted ai_skills flag. A command-layout file
  (.bob/commands/*.md, .github/agents/*.agent.md) always renders /speckit.*;
  only a /SKILL.md scaffold uses /speckit-*. Dual-layout agents (Bob,
  Copilot) write skills via their own setup()/skills path, so
  register_commands only ever emits their command-layout files.

- Comment 3: Update docs/reference/integrations.md Bob entry to document the
  skills-based default (.bob/skills/), the deprecated --legacy-commands
  opt-out, and the --skills migration path.

Also fix a latent manifest-loss bug surfaced by the migration path: the
upgrade Phase 2 stale-file cleanup built a throwaway manifest sharing the
integration key and called uninstall(), which always deleted
{key}.manifest.json. Any layout-shrinking upgrade (e.g. legacy->skills)
thus wiped the freshly-saved manifest, leaving the project untracked and
un-upgradeable. uninstall() now takes remove_manifest (default True); the
stale-cleanup pass passes False.

Adds regression tests for the --skills opt-in, mutual exclusion, corrected
active-agent separator, remove_manifest=False, and an end-to-end
legacy->skills migration that verifies the manifest survives and the
project remains upgradeable. Full suite: 4555 passed, 5 skipped.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* docs(agents): align token-resolution comment with output-layout separator rule (review #3415)

Address review #3415 (4725516805). The comment above resolve_command_refs
still described the removed state-based behavior ("resolve it from the
integration using the project's persisted skills state"). Update it to
describe the output-layout rule that register_commands now uses: _sep is
derived from the layout this registrar writes (a /SKILL.md scaffold uses the
skills separator; a command-layout file uses the command separator), not the
persisted ai_skills state. Comment-only change; no behavior change.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): reconcile extension artifacts on layout change (review #3415)

When a dual-mode agent (Bob) flips between the legacy commands layout and
the skills layout during `integration upgrade` (via `--skills` /
`--legacy-commands`), the old layout's extension command/skill files were
left orphaned: Phase 2 stale cleanup only removes files tracked by the
*integration* manifest, while extension artifacts are tracked in the
extension registry. Detect the layout flip by comparing whether the old vs
new manifest tracks a `/SKILL.md` scaffold, and when it changed, unregister
the agent's extension artifacts before the existing re-registration so they
are recreated in the new layout (and the per-agent registry is updated).

Preset artifacts are documented as a known, pre-existing cross-cutting gap:
no agent-scoped preset re-registration exists in use/switch/upgrade for any
agent, so reconciling them is out of scope for this Bob migration.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): reject layout migration when preset overrides are installed (review #3415)

A command↔skills layout change during `integration upgrade` cannot reconcile
preset artifacts: presets track their command/skill files in per-preset
`registered_commands`/`registered_skills` metadata, and there is no
agent-scoped preset re-registration anywhere in the CLI. Migrating would
delete a preset's old-layout files without recreating them in the new layout
and leave the preset registry claiming artifacts that no longer exist.

Detect the intended layout via `is_skills_mode` (so a plain same-layout
upgrade is unaffected) and, when it flips while preset overrides are
installed for the agent, reject the upgrade *before any mutation* with an
actionable error pointing at the remove → upgrade → reinstall workaround.
Extension artifacts are still reconciled for the safe (no-preset) case.

Adds a regression test and documents the migration caveat in the Bob
integration reference entry.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): restrict layout reconciliation to the active integration (review #3415)

`integration_upgrade` supports upgrading a secondary (non-active) integration,
but the layout-change extension reconciliation was unsafe there.
`ExtensionManager.unregister_agent_artifacts()` treats the unscoped
per-extension `registered_skills` list as belonging to the passed agent and,
when that agent's skills directory is absent, falls back to scanning every
agent's skills directory — so reconciling a secondary Bob layout flip could
delete or untrack the *active* agent's extension skills. The subsequent
re-registration cannot repair that because extension skill rendering is
intentionally scoped to the active agent (#2948).

Gate the unregister-before-register reconciliation on `installed_key == key`
so it only runs for the active integration. Secondary agents only ever have
extension command files (skills are active-agent-only), which the existing
re-registration rewrites in place, so skipping the unregister orphans nothing
new. Adds a regression test asserting a secondary Bob layout change leaves the
active agent's extension skill intact on disk and in the registry.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): fail closed when preset registry is unreadable (review #3415)

Address review 4744636079:

- _migrate_commands: the preset guard previously failed *open* — a
  registry read/parse error returned an empty "no presets" list, so a
  --force layout-changing upgrade could delete preset-overridden command
  files while their registry state was unknown. Read the registry file
  directly and raise _PresetRegistryUnreadableError on any read/parse
  failure or malformed structure, rejecting the migration before any
  mutation. A genuinely absent registry still returns [] (safe).

- bob: correct the is_skills_mode docstring — upgrade *does* run setup();
  disk detection is needed because legacy Bob 1.x installs never persisted
  a legacy_commands option, so the stored mode is unavailable.

- tests: add fail-closed E2E (corrupted registry rejected, valid-empty
  allowed) plus a unit test for _installed_presets_affecting_agent covering
  absent / corrupted / malformed / valid / affecting-agent cases.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

* fix(bob): fail closed on malformed preset entries too (review #3415)

Address review 4745191015: the preset guard read a parseable registry but
silently skipped malformed per-preset metadata and treated a malformed
registered_commands value as "no matching artifacts". A registry such as
{"presets":{"p1":[]}} therefore allowed a layout migration even though p1's
ownership is unknown, risking deletion of preset-managed files. Now raise
_PresetRegistryUnreadableError for a non-dict preset entry, a non-dict
registered_commands, or a non-list registered_skills. Extend the unit test
to cover these malformed shapes.

Assisted-by: GitHub Copilot (model: Claude Opus 4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 63f93544-a77f-4f01-bf04-c88806a97dbf

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Manfred Riem <15701806+mnriem@users.noreply.github.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
2026-07-21 09:20:20 -05:00

532 lines
19 KiB
Python

"""Copilot integration — GitHub Copilot in VS Code.
Copilot has several unique behaviors compared to standard markdown agents:
- Commands use ``.agent.md`` extension (not ``.md``)
- Each command gets a companion ``.prompt.md`` file in ``.github/prompts/``
- Installs ``.vscode/settings.json`` with prompt file recommendations
When ``--skills`` is passed via ``--integration-options``, Copilot scaffolds
commands as ``speckit-<name>/SKILL.md`` directories under ``.github/skills/``
instead. The two modes are mutually exclusive.
"""
from __future__ import annotations
import json
import os
import shutil
import warnings
from pathlib import Path
from typing import Any
from ..base import IntegrationBase, IntegrationOption, SkillsIntegration
from ..manifest import IntegrationManifest
def _copilot_executable() -> str:
"""Return the executable name for Copilot CLI on this platform.
On Windows, subprocess invocation is reliable with `copilot.cmd`.
"""
if os.name == "nt":
return "copilot.cmd"
return "copilot"
def _allow_all() -> bool:
"""Return True if the Copilot CLI should run with full permissions.
Checks ``SPECKIT_COPILOT_ALLOW_ALL_TOOLS`` first (new canonical name).
Falls back to the deprecated ``SPECKIT_ALLOW_ALL_TOOLS`` if set,
emitting a deprecation warning. Default when neither is set: enabled.
"""
new_var = os.environ.get("SPECKIT_COPILOT_ALLOW_ALL_TOOLS")
if new_var is not None:
return new_var != "0"
old_var = os.environ.get("SPECKIT_ALLOW_ALL_TOOLS")
if old_var is not None:
warnings.warn(
"SPECKIT_ALLOW_ALL_TOOLS is deprecated; "
"use SPECKIT_COPILOT_ALLOW_ALL_TOOLS instead.",
UserWarning,
stacklevel=2,
)
return old_var != "0"
return True
def _warn_legacy_markdown_default() -> None:
"""Warn that Copilot's default markdown scaffold is being phased out."""
warnings.warn(
"Copilot legacy markdown mode is deprecated and will stop being the "
'default in a future Spec Kit release; pass --integration-options "--skills" '
"to opt in to Copilot skills mode now.",
UserWarning,
stacklevel=3,
)
class _CopilotSkillsHelper(SkillsIntegration):
"""Internal helper used when Copilot is scaffolded in skills mode.
Not registered in the integration registry — only used as a delegate
by ``CopilotIntegration`` when ``--skills`` is passed.
"""
key = "copilot"
config = {
"name": "GitHub Copilot",
"folder": ".github/",
"commands_subdir": "skills",
"install_url": "https://docs.github.com/en/copilot/concepts/agents/copilot-cli/about-copilot-cli",
"requires_cli": False,
}
registrar_config = {
"dir": ".github/skills",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": "/SKILL.md",
}
class CopilotIntegration(IntegrationBase):
"""Integration for GitHub Copilot (VS Code IDE + CLI).
The IDE integration (``requires_cli: False``) installs ``.agent.md``
command files. Workflow dispatch additionally requires the
``copilot`` CLI to be installed separately.
When ``--skills`` is passed via ``--integration-options``, commands
are scaffolded as ``speckit-<name>/SKILL.md`` under ``.github/skills/``
instead of the default ``.agent.md`` + ``.prompt.md`` layout.
"""
key = "copilot"
config = {
"name": "GitHub Copilot",
"folder": ".github/",
"commands_subdir": "agents",
"install_url": "https://docs.github.com/en/copilot/concepts/agents/copilot-cli/about-copilot-cli",
"requires_cli": False,
}
registrar_config = {
"dir": ".github/agents",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".agent.md",
}
# Mutable flag set by setup() — indicates the active scaffolding mode.
_skills_mode: bool = False
def effective_invoke_separator(
self,
parsed_options: dict[str, Any] | None = None,
project_root: Path | None = None,
) -> str:
"""Return ``"-"`` when skills mode is requested, ``"."`` otherwise."""
if parsed_options and parsed_options.get("skills"):
return "-"
if self._skills_mode:
return "-"
return self.invoke_separator
def is_skills_mode(
self,
parsed_options: dict[str, Any] | None = None,
project_root: Path | None = None,
) -> bool:
"""Copilot is skills mode when ``--skills`` was requested.
On the init path ``setup()`` has already recorded the choice in
``self._skills_mode``; on the ``use``/``install`` path (where no
``setup()`` runs) the signal comes from *parsed_options* (#3550), which
round-trips because ``--skills`` is persisted in the stored options.
"""
if parsed_options and parsed_options.get("skills"):
return True
return self._skills_mode
def invoke_separator_for_mode(self, skills_enabled: bool) -> str:
"""Skills projects render ``/speckit-<cmd>``; default markdown ``.``.
Copilot is dual-layout, so — like Bob — the command-reference
separator depends on the persisted ``ai_skills`` state rather than a
single static value. This keeps preset/extension command refs in a
Copilot skills project consistent with ``build_command_invocation``
(which emits ``/speckit-<stem>``).
"""
return "-" if skills_enabled else self.invoke_separator
@classmethod
def options(cls) -> list[IntegrationOption]:
return [
IntegrationOption(
"--skills",
is_flag=True,
default=False,
help="Scaffold commands as agent skills (speckit-<name>/SKILL.md) instead of .agent.md files",
),
]
def _resolve_executable(self) -> str:
"""Return the Copilot CLI executable, respecting the env-var override.
Checks ``SPECKIT_INTEGRATION_COPILOT_EXECUTABLE`` first. Falls
back to the platform-specific default from ``_copilot_executable()``
(``copilot.cmd`` on Windows, ``copilot`` elsewhere) so that
existing behaviour is preserved when the env var is unset.
"""
env_name = "SPECKIT_INTEGRATION_COPILOT_EXECUTABLE"
override = os.environ.get(env_name, "").strip()
return override if override else _copilot_executable()
def build_exec_args(
self,
prompt: str,
*,
model: str | None = None,
output_json: bool = True,
) -> list[str] | None:
# GitHub Copilot CLI uses ``copilot -p "prompt"`` for
# non-interactive mode. --yolo enables all permissions
# (tools, paths, and URLs) so the agent can perform file
# edits and shell commands without interactive prompts.
# Controlled by SPECKIT_COPILOT_ALLOW_ALL_TOOLS env var
# (default: enabled). The deprecated SPECKIT_ALLOW_ALL_TOOLS
# is also honoured as a fallback.
args = [self._resolve_executable(), "-p", prompt]
self._apply_extra_args_env_var(args)
if _allow_all():
args.append("--yolo")
if model:
args.extend(["--model", model])
if output_json:
args.extend(["--output-format", "json"])
return args
def build_command_invocation(self, command_name: str, args: str = "") -> str:
"""Build the native invocation for a Copilot command.
Default mode: agents are not slash-commands — return args as prompt.
Skills mode: ``/speckit-<stem>`` slash-command dispatch.
"""
if self._skills_mode:
stem = command_name
if stem.startswith("speckit."):
stem = stem[len("speckit."):]
invocation = "/speckit-" + stem.replace(".", "-")
if args:
invocation = f"{invocation} {args}"
return invocation
return args or ""
def dispatch_command(
self,
command_name: str,
args: str = "",
*,
project_root: Path | None = None,
model: str | None = None,
timeout: int = 600,
stream: bool = True,
) -> dict[str, Any]:
"""Dispatch via ``--agent speckit.<stem>`` instead of slash-commands.
Copilot ``.agent.md`` files are agents, not skills. The CLI
selects them with ``--agent <name>`` and the prompt is just
the user's arguments.
In skills mode, the prompt includes the skill invocation
(``/speckit-<stem>``).
"""
import subprocess
stem = command_name
if stem.startswith("speckit."):
stem = stem[len("speckit."):]
# Detect skills mode from project layout when not set via setup()
skills_mode = self._skills_mode
if not skills_mode and project_root:
skills_dir = project_root / ".github" / "skills"
if skills_dir.is_dir():
skills_mode = any(
d.is_dir() and (d / "SKILL.md").is_file()
for d in skills_dir.glob("speckit-*")
)
if skills_mode:
prompt = "/speckit-" + stem.replace(".", "-")
if args:
prompt = f"{prompt} {args}"
else:
agent_name = f"speckit.{stem}"
prompt = args or ""
cli_args = [self._resolve_executable(), "-p", prompt]
# Honour SPECKIT_INTEGRATION_COPILOT_EXTRA_ARGS for real workflow
# runs. `dispatch_command` builds cli_args inline rather than
# going through `build_exec_args`, so the hook must be invoked
# here too — otherwise the env var is silently ignored.
self._apply_extra_args_env_var(cli_args)
if not skills_mode:
cli_args.extend(["--agent", agent_name])
if _allow_all():
cli_args.append("--yolo")
if model:
cli_args.extend(["--model", model])
if not stream:
cli_args.extend(["--output-format", "json"])
cwd = str(project_root) if project_root else None
if stream:
try:
result = subprocess.run(
cli_args,
text=True,
cwd=cwd,
)
except KeyboardInterrupt:
return {
"exit_code": 130,
"stdout": "",
"stderr": "Interrupted by user",
}
return {
"exit_code": result.returncode,
"stdout": "",
"stderr": "",
}
result = subprocess.run(
cli_args,
capture_output=True,
text=True,
cwd=cwd,
timeout=timeout,
)
return {
"exit_code": result.returncode,
"stdout": result.stdout,
"stderr": result.stderr,
}
def command_filename(self, template_name: str) -> str:
"""Copilot commands use ``.agent.md`` extension."""
return f"speckit.{template_name}.agent.md"
def stale_cleanup_exclusions(self) -> set[str]:
"""Protect ``.vscode/settings.json`` from upgrade stale-deletion.
``setup()`` records this file in the manifest only when it creates it;
when it already exists the file is merged and intentionally left
untracked. On upgrade the untracked-but-existing file would otherwise
be flagged stale and deleted, destroying user settings (and the file
the integration still manages).
"""
return {".vscode/settings.json"}
def post_process_skill_content(self, content: str) -> str:
"""Inject shared hook guidance into Copilot skill content.
Delegates to :class:`_CopilotSkillsHelper` for shared post-processing.
The ``mode:`` frontmatter field is intentionally omitted: VS Code
Copilot Agent Skills do not support it (see issue #2799).
"""
return _CopilotSkillsHelper().post_process_skill_content(content)
def setup(
self,
project_root: Path,
manifest: IntegrationManifest,
parsed_options: dict[str, Any] | None = None,
**opts: Any,
) -> list[Path]:
"""Install copilot commands, companion prompts, and VS Code settings.
When ``parsed_options["skills"]`` is truthy, delegates to skills
scaffolding (``speckit-<name>/SKILL.md`` under ``.github/skills/``).
Otherwise uses the default ``.agent.md`` + ``.prompt.md`` layout.
"""
parsed_options = parsed_options or {}
self._skills_mode = bool(parsed_options.get("skills"))
if self._skills_mode:
return self._setup_skills(project_root, manifest, parsed_options, **opts)
if "skills" not in parsed_options:
_warn_legacy_markdown_default()
return self._setup_default(project_root, manifest, parsed_options, **opts)
def _setup_default(
self,
project_root: Path,
manifest: IntegrationManifest,
parsed_options: dict[str, Any] | None = None,
**opts: Any,
) -> list[Path]:
"""Default mode: .agent.md + .prompt.md + VS Code settings merge."""
project_root_resolved = project_root.resolve()
if manifest.project_root != project_root_resolved:
raise ValueError(
f"manifest.project_root ({manifest.project_root}) does not match "
f"project_root ({project_root_resolved})"
)
templates = self.list_command_templates()
if not templates:
return []
dest = self.commands_dest(project_root)
dest_resolved = dest.resolve()
try:
dest_resolved.relative_to(project_root_resolved)
except ValueError as exc:
raise ValueError(
f"Integration destination {dest_resolved} escapes "
f"project root {project_root_resolved}"
) from exc
dest.mkdir(parents=True, exist_ok=True)
created: list[Path] = []
script_type = opts.get("script_type", "sh")
arg_placeholder = self.registrar_config.get("args", "$ARGUMENTS")
# 1. Process and write command files as .agent.md
for src_file in templates:
raw = src_file.read_text(encoding="utf-8")
processed = self.process_template(
raw, self.key, script_type, arg_placeholder,
project_root=project_root,
)
dst_name = self.command_filename(src_file.stem)
dst_file = self.write_file_and_record(
processed, dest / dst_name, project_root, manifest
)
created.append(dst_file)
# 2. Generate companion .prompt.md files from the templates we just wrote
prompts_dir = project_root / ".github" / "prompts"
for src_file in templates:
cmd_name = f"speckit.{src_file.stem}"
prompt_content = f"---\nagent: {cmd_name}\n---\n"
prompt_file = self.write_file_and_record(
prompt_content,
prompts_dir / f"{cmd_name}.prompt.md",
project_root,
manifest,
)
created.append(prompt_file)
# Write .vscode/settings.json
settings_src = self._vscode_settings_path()
if settings_src and settings_src.is_file():
dst_settings = project_root / ".vscode" / "settings.json"
dst_settings.parent.mkdir(parents=True, exist_ok=True)
if dst_settings.exists():
# Merge into existing — don't track since we can't safely
# remove the user's settings file on uninstall.
self._merge_vscode_settings(settings_src, dst_settings)
else:
shutil.copy2(settings_src, dst_settings)
self.record_file_in_manifest(dst_settings, project_root, manifest)
created.append(dst_settings)
return created
def _setup_skills(
self,
project_root: Path,
manifest: IntegrationManifest,
parsed_options: dict[str, Any] | None = None,
**opts: Any,
) -> list[Path]:
"""Skills mode: delegate to ``_CopilotSkillsHelper`` then post-process."""
helper = _CopilotSkillsHelper()
created = SkillsIntegration.setup(
helper, project_root, manifest, parsed_options, **opts
)
# Post-process generated skill files with Copilot-specific frontmatter
skills_dir = helper.skills_dest(project_root).resolve()
for path in created:
try:
path.resolve().relative_to(skills_dir)
except ValueError:
continue
if path.name != "SKILL.md":
continue
content = path.read_text(encoding="utf-8")
updated = self.post_process_skill_content(content)
if updated != content:
path.write_bytes(updated.encode("utf-8"))
self.record_file_in_manifest(path, project_root, manifest)
return created
def _vscode_settings_path(self) -> Path | None:
"""Return path to the bundled vscode-settings.json template."""
tpl_dir = self.shared_templates_dir()
if tpl_dir:
candidate = tpl_dir / "vscode-settings.json"
if candidate.is_file():
return candidate
return None
@staticmethod
def _merge_vscode_settings(src: Path, dst: Path) -> None:
"""Merge settings from *src* into existing *dst* JSON file.
Top-level keys from *src* are added only if missing in *dst*.
For dict-valued keys, sub-keys are merged the same way.
If *dst* cannot be parsed (e.g. JSONC with comments), the merge
is skipped to avoid overwriting user settings.
"""
try:
existing = json.loads(dst.read_text(encoding="utf-8"))
except (json.JSONDecodeError, OSError):
# Cannot parse existing file (likely JSONC with comments).
# Skip merge to preserve the user's settings, but show
# what they should add manually.
import logging
template_content = src.read_text(encoding="utf-8")
logging.getLogger(__name__).warning(
"Could not parse %s (may contain JSONC comments). "
"Skipping settings merge to preserve existing file.\n"
"Please add the following settings manually:\n%s",
dst, template_content,
)
return
new_settings = json.loads(src.read_text(encoding="utf-8"))
if not isinstance(existing, dict) or not isinstance(new_settings, dict):
import logging
logging.getLogger(__name__).warning(
"Skipping settings merge: %s or template is not a JSON object.", dst
)
return
changed = False
for key, value in new_settings.items():
if key not in existing:
existing[key] = value
changed = True
elif isinstance(existing[key], dict) and isinstance(value, dict):
for sub_key, sub_value in value.items():
if sub_key not in existing[key]:
existing[key][sub_key] = sub_value
changed = True
if not changed:
return
dst.write_text(
json.dumps(existing, indent=4) + "\n", encoding="utf-8"
)