Files
github-spec-kit/src/specify_cli/integrations/hermes/__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

274 lines
10 KiB
Python

"""Hermes Agent integration — skills-based agent.
Hermes Agent (https://github.com/NousResearch/hermes-agent) is an open-source
AI agent framework by Nous Research. It stores skills in
``~/.hermes/skills/`` (user-global) rather than a project-local directory.
Usage::
specify init my-project --integration hermes
specify init --here --integration hermes
"""
from __future__ import annotations
from pathlib import Path
from shutil import rmtree
from typing import Any
import yaml
from ..base import IntegrationOption, SkillsIntegration
from ..manifest import IntegrationManifest
class HermesIntegration(SkillsIntegration):
"""Integration for Hermes Agent skills.
Hermes loads skills from ``~/.hermes/skills/`` (user home directory)
rather than a project-local path. Skills are installed directly to
the global directory — no project-local copies are created since
Hermes discovers them globally. A project-local marker directory
(``.hermes/skills/`` empty) is created so extension commands (e.g.
git) can detect Hermes as an active integration. Uninstall removes
both the marker and all global ``speckit-*`` skills, matching the
standard integration teardown behaviour.
"""
key = "hermes"
config = {
"name": "Hermes Agent",
"folder": ".hermes/",
"commands_subdir": "skills",
"install_url": "https://github.com/NousResearch/hermes-agent",
"requires_cli": True,
}
registrar_config = {
"dir": "~/.hermes/skills",
"detect_dir": ".hermes/skills",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": "/SKILL.md",
}
# -- Helpers -----------------------------------------------------------
@staticmethod
def _hermes_home_skills_dir() -> Path:
"""Return ``~/.hermes/skills/`` — the global skills directory."""
return Path.home() / ".hermes" / "skills"
# -- Options -----------------------------------------------------------
@classmethod
def options(cls) -> list[IntegrationOption]:
return [
IntegrationOption(
"--skills",
is_flag=True,
default=True,
help="Install as agent skills (default for Hermes Agent)",
),
]
# -- Setup -------------------------------------------------------------
def setup(
self,
project_root: Path,
manifest: IntegrationManifest,
parsed_options: dict[str, Any] | None = None,
**opts: Any,
) -> list[Path]:
"""Install command templates as global Hermes skills.
Writes each skill directly to
``~/.hermes/skills/speckit-<name>/SKILL.md`` where Hermes
discovers them at runtime. No project-local SKILL.md copies are
created — the global directory is the single source of truth.
A project-local marker (``.hermes/skills/`` empty) is created
so extension commands (e.g. git) can detect Hermes as an active
integration.
"""
templates = self.list_command_templates()
if not templates:
return []
# Safety check: verify manifest project_root matches (standard pattern)
project_root_resolved = project_root.resolve()
if manifest.project_root != project_root_resolved:
raise ValueError(
f"manifest.project_root ({manifest.project_root}) does not match "
f"project_root ({project_root_resolved})"
)
script_type = opts.get("script_type", "sh")
arg_placeholder = (
self.registrar_config.get("args", "$ARGUMENTS")
if self.registrar_config
else "$ARGUMENTS"
)
global_skills_dir = self._hermes_home_skills_dir()
global_skills_dir.mkdir(parents=True, exist_ok=True)
created: list[Path] = []
for src_file in templates:
raw = src_file.read_text(encoding="utf-8")
# Derive the skill name from the template stem
command_name = src_file.stem # e.g. "plan"
skill_name = f"speckit-{command_name.replace('.', '-')}"
# Parse frontmatter for description
frontmatter: dict[str, Any] = {}
if raw.startswith("---"):
parts = raw.split("---", 2)
if len(parts) >= 3:
try:
fm = yaml.safe_load(parts[1])
if isinstance(fm, dict):
frontmatter = fm
except yaml.YAMLError:
pass
# Process body through the standard template pipeline
processed_body = self.process_template(
raw,
self.key,
script_type,
arg_placeholder,
invoke_separator=self.invoke_separator,
)
# Strip the processed frontmatter — we rebuild it for skills.
if processed_body.startswith("---"):
parts = processed_body.split("---", 2)
if len(parts) >= 3:
processed_body = parts[2]
# Select description
description = frontmatter.get("description", "")
if not description:
description = f"Spec Kit: {command_name} workflow"
# Build SKILL.md with manually formatted frontmatter
def _quote(v: str) -> str:
escaped = v.replace("\\", "\\\\").replace('"', '\\"')
return f'"{escaped}"'
skill_content = (
f"---\n"
f"name: {_quote(skill_name)}\n"
f"description: {_quote(description)}\n"
f"compatibility: "
f"{_quote('Requires spec-kit project structure with .specify/ directory')}\n"
f"metadata:\n"
f" author: {_quote('github-spec-kit')}\n"
f" source: {_quote('templates/commands/' + src_file.name)}\n"
f"---\n"
f"{processed_body}"
)
skill_content = self.post_process_skill_content(skill_content)
# Write directly to global ~/.hermes/skills/speckit-<name>/SKILL.md
skill_dir = global_skills_dir / skill_name
skill_dir.mkdir(parents=True, exist_ok=True)
skill_file = skill_dir / "SKILL.md"
normalized = skill_content.replace("\r\n", "\n")
skill_file.write_bytes(normalized.encode("utf-8"))
created.append(skill_file)
# Create project-local marker directory so extension commands
# (e.g. git) can detect Hermes as an active integration.
# Hermes itself ignores this directory — skills live globally.
(project_root / ".hermes" / "skills").mkdir(parents=True, exist_ok=True)
return created
# -- Uninstall ---------------------------------------------------------
def teardown(
self,
project_root: Path,
manifest: IntegrationManifest,
*,
force: bool = False,
) -> tuple[list[Path], list[Path]]:
"""Uninstall integration files including global Hermes skills.
Removes the project-local marker directory (if empty), delegates to
``manifest.uninstall()`` for project-local tracked files, and
removes all ``speckit-*`` skills under ``~/.hermes/skills/``.
Global skills are always removed on teardown — this matches the
standard integration behaviour where all files created by the
integration are removed on ``specify integration uninstall``.
"""
# Delegate to manifest for project-local tracked files (scripts,
# templates, context entries tracked in the manifest).
removed, skipped = manifest.uninstall(project_root, force=force)
# Remove project-local marker directory if empty
local_skills_dir = project_root / ".hermes" / "skills"
if local_skills_dir.is_dir() and not any(local_skills_dir.iterdir()):
local_skills_dir.rmdir()
hermes_dir = project_root / ".hermes"
if hermes_dir.is_dir() and not any(hermes_dir.iterdir()):
hermes_dir.rmdir()
# Remove all global Hermes skills for speckit — these are always
# removed on uninstall regardless of the force flag, matching the
# standard behaviour where all integration files are cleaned up.
global_skills_dir = self._hermes_home_skills_dir()
if global_skills_dir.is_dir():
for skill_dir in sorted(global_skills_dir.iterdir()):
if skill_dir.is_dir() and skill_dir.name.startswith("speckit-"):
try:
rmtree(skill_dir)
removed.append(skill_dir)
except OSError:
skipped.append(skill_dir)
return removed, skipped
# -- CLI dispatch ------------------------------------------------------
def build_exec_args(
self,
prompt: str,
*,
model: str | None = None,
output_json: bool = True,
) -> list[str] | None:
"""Build Hermes CLI invocation for programmatic dispatch.
Uses ``hermes chat -Q -q`` for one-shot queries in quiet mode,
mapping slash-command invocations to the appropriate skill-based
dispatch.
"""
args = [self._resolve_executable(), "chat", "-Q"]
if model:
args.extend(["-m", model])
if output_json:
args.append("--json")
# If prompt starts with a slash command, pass it directly
# so Hermes can dispatch to the appropriate skill.
if prompt.startswith("/"):
command, _, remainder = prompt[1:].partition(" ")
if command:
args.extend(["-s", command])
if remainder:
args.extend(["-q", remainder])
else:
args.extend(["-q", prompt])
else:
args.extend(["-q", prompt])
return args