mirror of
https://github.com/obra/superpowers.git
synced 2026-07-24 19:24:04 +08:00
Compare commits
3 Commits
dev
...
hermes-har
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b6613057ae | ||
|
|
178528c03e | ||
|
|
7b177613c0 |
@@ -9,7 +9,7 @@
|
||||
{
|
||||
"name": "superpowers",
|
||||
"description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"source": "./",
|
||||
"author": {
|
||||
"name": "Jesse Vincent",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "superpowers",
|
||||
"description": "Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"author": {
|
||||
"name": "Jesse Vincent",
|
||||
"email": "jesse@fsck.com"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "superpowers",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"description": "An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.",
|
||||
"author": {
|
||||
"name": "Jesse Vincent",
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
"name": "superpowers",
|
||||
"displayName": "Superpowers",
|
||||
"description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"author": {
|
||||
"name": "Jesse Vincent",
|
||||
"email": "jesse@fsck.com"
|
||||
|
||||
6
.gitignore
vendored
6
.gitignore
vendored
@@ -11,3 +11,9 @@ triage/
|
||||
# development (see CLAUDE.md / README.md). It is not part of the published
|
||||
# plugin, so the whole directory is ignored here.
|
||||
evals/
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
*.pyc
|
||||
*.pyo
|
||||
.pytest_cache/
|
||||
|
||||
104
.hermes-plugin/__init__.py
Normal file
104
.hermes-plugin/__init__.py
Normal file
@@ -0,0 +1,104 @@
|
||||
import os
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
BOOTSTRAP_MARKER = "superpowers:using-superpowers bootstrap for hermes"
|
||||
|
||||
|
||||
def _skills_dir() -> str:
|
||||
"""Locate the stock skills/ tree for either supported install layout.
|
||||
|
||||
- git-clone install (`hermes plugins install obra/superpowers`): the plugin
|
||||
dir is the repo root, so `.hermes-plugin/` and `skills/` are siblings and
|
||||
this module resolves `../skills`.
|
||||
- flattened install (plugin files copied to the plugin dir root): `skills/`
|
||||
sits next to this module.
|
||||
|
||||
Raises loudly when neither matches — a bootstrap that silently skips is how
|
||||
a broken install masquerades as a working one.
|
||||
"""
|
||||
here = os.path.dirname(os.path.realpath(__file__))
|
||||
candidates = (
|
||||
os.path.realpath(os.path.join(here, "..", "skills")),
|
||||
os.path.realpath(os.path.join(here, "skills")),
|
||||
)
|
||||
for cand in candidates:
|
||||
if os.path.isfile(os.path.join(cand, "using-superpowers", "SKILL.md")):
|
||||
return cand
|
||||
raise RuntimeError(
|
||||
"superpowers plugin: cannot find the skills/ tree "
|
||||
f"(looked at {candidates}). Reinstall with "
|
||||
"`hermes plugins install obra/superpowers`."
|
||||
)
|
||||
|
||||
|
||||
def _strip_frontmatter(content: str) -> str:
|
||||
match = re.match(r"^---\n[\s\S]*?\n---\n([\s\S]*)$", content)
|
||||
return (match.group(1) if match else content).strip()
|
||||
|
||||
|
||||
def _build_bootstrap(skills_dir: str) -> str:
|
||||
with open(
|
||||
os.path.join(skills_dir, "using-superpowers", "SKILL.md"),
|
||||
encoding="utf-8",
|
||||
) as f:
|
||||
body = _strip_frontmatter(f.read())
|
||||
|
||||
tools_path = os.path.join(
|
||||
skills_dir, "using-superpowers", "references", "hermes-tools.md"
|
||||
)
|
||||
with open(tools_path, encoding="utf-8") as f:
|
||||
tool_mapping = f.read().strip()
|
||||
|
||||
return (
|
||||
f"<EXTREMELY_IMPORTANT>\n"
|
||||
f"{BOOTSTRAP_MARKER}\n\n"
|
||||
f"You have superpowers.\n\n"
|
||||
f"The using-superpowers skill content is included below and is already "
|
||||
f"loaded for this Hermes session. Follow it now. "
|
||||
f"Do not try to load using-superpowers again.\n\n"
|
||||
f"{body}\n\n"
|
||||
f"## Loading Superpowers Skills on Hermes\n\n"
|
||||
f"Superpowers skills are registered with Hermes' native skill loader: "
|
||||
f'invoke one with `skill_view("superpowers:skill-name")` '
|
||||
f'(for example `skill_view("superpowers:brainstorming")`). '
|
||||
f"If a namespaced lookup returns 'not found', read the skill file "
|
||||
f"directly instead:\n"
|
||||
f'`read_file("{skills_dir}/skill-name/SKILL.md")`\n\n'
|
||||
f"The superpowers skills directory is: `{skills_dir}`\n\n"
|
||||
f"{tool_mapping}\n"
|
||||
f"</EXTREMELY_IMPORTANT>"
|
||||
)
|
||||
|
||||
|
||||
def register(ctx):
|
||||
skills_dir = _skills_dir()
|
||||
bootstrap = _build_bootstrap(skills_dir)
|
||||
|
||||
# Register every stock skill with Hermes' native loader so skill_view can
|
||||
# load them on demand. Standard markdown; no conversion (plugin guide).
|
||||
# register_skill requires a pathlib.Path — a str raises AttributeError and
|
||||
# hermes silently disables the whole plugin (verified 2026-07-23).
|
||||
for name in sorted(os.listdir(skills_dir)):
|
||||
skill_md = os.path.join(skills_dir, name, "SKILL.md")
|
||||
if os.path.isfile(skill_md):
|
||||
ctx.register_skill(name, Path(skill_md))
|
||||
|
||||
# pre_llm_call returning {"context": ...} is the documented injection path
|
||||
# (on_session_start return values are ignored, and ctx.inject_message
|
||||
# refuses from that hook — verified empirically 2026-07-23). The context is
|
||||
# appended to the first turn's user message.
|
||||
def pre_llm_call(
|
||||
session_id=None,
|
||||
user_message=None,
|
||||
conversation_history=None,
|
||||
is_first_turn=None,
|
||||
model=None,
|
||||
platform=None,
|
||||
**kwargs,
|
||||
):
|
||||
if is_first_turn:
|
||||
return {"context": bootstrap}
|
||||
return None
|
||||
|
||||
ctx.register_hook("pre_llm_call", pre_llm_call)
|
||||
6
.hermes-plugin/plugin.yaml
Normal file
6
.hermes-plugin/plugin.yaml
Normal file
@@ -0,0 +1,6 @@
|
||||
name: superpowers
|
||||
version: 6.1.1
|
||||
description: Superpowers skills and workflow bootstrap for Hermes Agent
|
||||
author: obra
|
||||
provides_hooks:
|
||||
- pre_llm_call
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "superpowers",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"description": "An agentic skills framework and software development methodology.",
|
||||
"author": {
|
||||
"name": "Jesse Vincent",
|
||||
|
||||
14
README.md
14
README.md
@@ -11,7 +11,7 @@ If this sounds like someone you know, definitely send them our way.
|
||||
|
||||
## Quickstart
|
||||
|
||||
Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).
|
||||
Give your agent Superpowers: [Claude Code](#claude-code), [Antigravity](#antigravity), [Codex App](#codex-app), [Codex CLI](#codex-cli), [Cursor](#cursor), [Factory Droid](#factory-droid), [Gemini CLI](#gemini-cli), [GitHub Copilot CLI](#github-copilot-cli), [Hermes Agent](#hermes-agent), [Kimi Code](#kimi-code), [OpenCode](#opencode), [Pi](#pi).
|
||||
|
||||
## How it works
|
||||
|
||||
@@ -199,6 +199,18 @@ pi -e /path/to/superpowers
|
||||
|
||||
The Pi package loads the Superpowers skills and a small extension that injects the `using-superpowers` bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility `Skill` tool is required. Subagent and task-list tools remain optional Pi companion packages.
|
||||
|
||||
### Hermes Agent
|
||||
|
||||
Install Superpowers as a Hermes plugin from this repository:
|
||||
|
||||
```bash
|
||||
hermes plugins install obra/superpowers --enable
|
||||
```
|
||||
|
||||
Restart any active Hermes sessions after installing. Note: Hermes has no
|
||||
post-compaction hook, so a very long session that compacts over its first
|
||||
turn loses the bootstrap — start a fresh session if skills stop triggering.
|
||||
|
||||
## The Basic Workflow
|
||||
|
||||
1. **brainstorming** - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.
|
||||
|
||||
@@ -1,38 +1,5 @@
|
||||
# Superpowers Release Notes
|
||||
|
||||
## v6.2.0 (2026-07-23)
|
||||
|
||||
### Subagent-Driven Development
|
||||
|
||||
Two structural changes to how SDD tracks progress and closes out review findings, both developed against live eval campaigns.
|
||||
|
||||
- **The workspace is now plan-scoped.** `.superpowers/sdd/` had no plan identity and no end-of-life: a follow-up plan in the same working tree could read the previous plan's ledger as its own progress (observed in the wild, with multiple contamination rounds and ad-hoc workarounds). `sdd-workspace` now requires the plan file and resolves a per-plan directory, `.superpowers/sdd/<plan-basename>/`; `task-brief` and `review-package` write into their plan's directory (`review-package` gains the plan file as its first argument); the ledger names its plan on its first line; and the workspace is deleted once the final review is clean — git history is the durable record. Baseline evals showed controllers already refused foreign ledgers, but at a cost of 6–13 tool calls of cross-plan git forensics per resume; plan-scoping makes the answer structural instead. (25/25 baseline and GREEN eval runs documented in `docs/specs/` and `docs/plans/`.)
|
||||
- **The review-fix loop resumes the implementer.** The lifecycle restructure gives fix rounds resume-the-implementer semantics instead of fresh dispatches, adds a scoped re-review prompt (`re-review-prompt.md`) so the re-reviewer checks the fixes rather than re-reading the whole task, and installs a five-round circuit breaker with controller adjudication when it trips. SKILL.md reorganizes by lifecycle, and its Red Flags convert to the house rationalization-table form.
|
||||
|
||||
### Skills
|
||||
|
||||
A branch-wide compression campaign: recap sections, social proof, and benefits-selling prose aimed at a reader who has already invoked the skill are gone, with every load-bearing argument folded into a rationalization-table row or moved to its point of use. Each cut was micro-tested with subagent probes, and the one cut that measurably degraded behavior was reworked rather than shipped.
|
||||
|
||||
- **`testing-anti-patterns.md` is now `writing-good-tests.md`.** The TDD reference doc is rebuilt as a positive catalog — six rules that lead with the GOOD example — and absorbs a falsifiability discipline: name the production change that would fail the test, derive expectations independently of the code under test, and a closing mutation check. It closes two holes by name: the string-presence trap (grep-style tests on scripts, skills, and prompts counterfeit falsifiability — the observable is behavior, never text) and the change-detector trap (a constant assertion can fail and still protect nothing), each with a hard stop in the gate function. Trivial code and human prose earn no test; the trigger broadens from "adding mocks" to any test writing.
|
||||
- **TDD's "Why Order Matters" rebuttals survive as rationalization rows.** Deleting the section outright measurably degraded test-first behavior under "just write it, tests after" pressure (control 8/10 → treatment 5/10, corroborated on Claude and Codex), so each prose rebuttal now lives in its Common Rationalizations row — the section is gone but the arguments fire where an agent hits them mid-rationalization.
|
||||
- **`finishing-a-development-branch` no longer offers to discard your work.** The completion menu dates from when throwing away branches was routine; "Discard this work" next to "Merge" advertised destroying finished, passing work. Discard survives as an explicit-request-only path with the same typed-confirmation ritual. The same pass made PR creation forge-agnostic (your forge's CLI or the URL printed on push, not a blessed list of tools) and fixed a real bug: the worktree path was recomputed after cleanup had already changed directory, so provenance checks never matched and cleanup silently no-oped.
|
||||
- **Recap and persuasion prose removed across the library.** `brainstorming`, `systematic-debugging`, `dispatching-parallel-agents`, `verification-before-completion`, `executing-plans`, `subagent-driven-development`, `requesting-code-review`, `receiving-code-review`, `using-git-worktrees`, `writing-plans`, and `writing-skills` all drop their Bottom Line / Key Principles / Real-World Impact / Advantages sections; `using-git-worktrees` and `finishing-a-development-branch` convert their guard sections to the house Excuse/Reality rationalization table.
|
||||
|
||||
### Windows
|
||||
|
||||
- **The SessionStart hook now dispatches via Git Bash.** The hook's command string starts with a quoted path, which broke both shells Claude Code might hand it to: PowerShell parsed the quoted string as an expression and died with a parser error (#1751), and cmd.exe's quote-stripping rule truncated the command when the profile path contained a metacharacter like `(` (#1918) — either way the bootstrap silently never loaded. The hook now declares `shell: "bash"`, which Claude Code ≥ 2.1.81 resolves to Git for Windows directly, and which surfaces an actionable install prompt when Git Bash is missing. Older Claude Code versions ignore the unknown key and behave as before. Verified end-to-end on Linux, Windows 11 with Git Bash under a hostile path, and Windows 11 without Git Bash.
|
||||
|
||||
### Harness Support
|
||||
|
||||
- **Gemini CLI support is restored.** The v6.1.0 removal (on the news that Google had EOLed the Gemini CLI) was premature; the install docs and the `gemini-tools.md` tool-mapping reference are back while permanent removal gets a proper evaluation. (#1959)
|
||||
|
||||
### Fixes
|
||||
|
||||
- **`find-polluter.sh` actually finds test files now.** `find .` emits `./`-prefixed paths, so the documented `-path "src/**/*.test.ts"` pattern matched nothing — and `wc -l` on empty input then reported "Found 1". Fixed the prefix mismatch (#2008, #2011), plus two follow-ups: a caller-supplied `./`-prefixed pattern no longer double-prefixes into a never-matching form, and `**/` is also matched collapsed so tests directly under the base directory (`src/top.test.ts` vs `src/**/*.test.ts`) aren't silently skipped. The script gains a deterministic test suite.
|
||||
- **The Codex package script works beyond macOS.** Deterministic-metadata tar flags were bsdtar-only spellings, staged file modes depended on two umasks canceling out, and the test's timestamp assertion parsed bsdtar's column layout in a US timezone. GNU tar now gets equivalent flags producing byte-identical headers, modes are pinned canonical, and the test asserts mtime via `tarfile`.
|
||||
- **SDD's skill test no longer flakes.** The file's worst case exceeded the runner's per-file ceiling (raised to 900s), and the assert helpers matched free-form model prose case-sensitively; matching is now case-insensitive and `assert_order` dumps output on failure so the next flake is diagnosable.
|
||||
- **Docs and test cleanup after the v6.1.0 reference pruning.** Dead links to the deleted `claude-code-tools.md`/`copilot-tools.md` are replaced with the current architecture (#1969), a dangling `#subagent-support` anchor in the Antigravity reference is dropped (#2010), and the Antigravity/Pi mapping tests assert only the surviving harness-specific mappings — scoped to the table so they fail again if it's deleted.
|
||||
|
||||
## v6.1.1 (2026-07-02)
|
||||
|
||||
### Codex
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "superpowers",
|
||||
"description": "Core skills library: TDD, debugging, collaboration patterns, and proven techniques",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"contextFileName": "GEMINI.md"
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "superpowers",
|
||||
"version": "6.2.0",
|
||||
"version": "6.1.1",
|
||||
"description": "Superpowers skills and runtime bootstrap for coding agents",
|
||||
"type": "module",
|
||||
"main": ".opencode/plugins/superpowers.js",
|
||||
|
||||
@@ -56,6 +56,7 @@ If your harness appears here, read its reference file for special instructions:
|
||||
- Codex: `references/codex-tools.md`
|
||||
- Pi: `references/pi-tools.md`
|
||||
- Antigravity: `references/antigravity-tools.md`
|
||||
- Hermes Agent: `references/hermes-tools.md`
|
||||
|
||||
## User Instructions
|
||||
|
||||
|
||||
56
skills/using-superpowers/references/hermes-tools.md
Normal file
56
skills/using-superpowers/references/hermes-tools.md
Normal file
@@ -0,0 +1,56 @@
|
||||
# Hermes Agent Tool Mapping
|
||||
|
||||
Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Hermes Agent these resolve to the tools below.
|
||||
|
||||
## Tools
|
||||
|
||||
| Action skills request | Hermes tool |
|
||||
|---|---|
|
||||
| Read a file | `read_file` |
|
||||
| Create a new file | `write_file` |
|
||||
| Edit a file (targeted patch) | `patch` |
|
||||
| Run a shell command | `terminal` |
|
||||
| Search file contents | `search_files` |
|
||||
| Find files by name | `terminal` with `find` |
|
||||
| Fetch a URL / read a webpage | `web_extract(urls=[...])` |
|
||||
| Search the web | `web_search(query=...)` |
|
||||
| Dispatch a subagent | `delegate_task(goal=..., context=..., toolsets=[...], role="leaf")` |
|
||||
| Task tracking | `todo` tool |
|
||||
| Invoke a skill | `skill_view("skill-name")` |
|
||||
|
||||
## Instructions file
|
||||
|
||||
When a skill mentions "your instructions file," on Hermes Agent this is **`AGENTS.md`** in the project directory, or **`SOUL.md`** globally at `~/.hermes/SOUL.md`.
|
||||
|
||||
## Invoking a skill
|
||||
|
||||
Hermes Agent has a `skills` toolset with `skill_view` and `skills_list` tools.
|
||||
To invoke a superpowers skill, use:
|
||||
|
||||
```
|
||||
skill_view("brainstorming")
|
||||
skill_view("test-driven-development")
|
||||
```
|
||||
|
||||
If `skill_view` cannot find a superpowers skill (it may not appear in the catalog
|
||||
until the plugin fully registers it), fall back to reading the SKILL.md directly:
|
||||
|
||||
```
|
||||
read_file(path="~/.hermes/plugins/superpowers/skills/<skill-name>/SKILL.md")
|
||||
```
|
||||
|
||||
This fallback is the same mechanism used by other harnesses without native skill loading.
|
||||
|
||||
## Subagent dispatch
|
||||
|
||||
Use `delegate_task` to spawn isolated subagents for parallel or sequential workstreams:
|
||||
|
||||
```
|
||||
delegate_task(goal="...", context="...", toolsets=[...], role="leaf")
|
||||
```
|
||||
|
||||
If `delegate_task` is unavailable, do the work inline rather than inventing tool calls.
|
||||
|
||||
## Task tracking
|
||||
|
||||
Use the `todo` tool for task tracking within a session. For multi-agent task boards, use `hermes kanban` CLI if available. Treat older `TodoWrite` references as the task-tracking action.
|
||||
0
tests/hermes/__init__.py
Normal file
0
tests/hermes/__init__.py
Normal file
30
tests/hermes/conftest.py
Normal file
30
tests/hermes/conftest.py
Normal file
@@ -0,0 +1,30 @@
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_ctx():
|
||||
ctx = MagicMock()
|
||||
ctx._hooks = {}
|
||||
ctx._skills = {}
|
||||
|
||||
def register_hook(event, fn):
|
||||
ctx._hooks[event] = fn
|
||||
|
||||
def register_skill(name, path):
|
||||
# Mimic hermes' real register_skill, which calls path.exists() and
|
||||
# therefore breaks on a str (the bug that silently disabled the whole
|
||||
# plugin, found 2026-07-23). Keeping that fidelity here means a
|
||||
# regression to str paths fails these tests instead of failing
|
||||
# silently inside hermes.
|
||||
if not isinstance(path, Path):
|
||||
raise AttributeError(
|
||||
f"register_skill requires a pathlib.Path, got {type(path).__name__}"
|
||||
)
|
||||
ctx._skills[name] = path
|
||||
|
||||
ctx.register_hook.side_effect = register_hook
|
||||
ctx.register_skill.side_effect = register_skill
|
||||
return ctx
|
||||
98
tests/hermes/test_bootstrap.py
Normal file
98
tests/hermes/test_bootstrap.py
Normal file
@@ -0,0 +1,98 @@
|
||||
import importlib
|
||||
import os
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
|
||||
sys.path.insert(0, os.path.abspath(
|
||||
os.path.join(os.path.dirname(__file__), "../../.hermes-plugin")
|
||||
))
|
||||
|
||||
BOOTSTRAP_MARKER = "superpowers:using-superpowers bootstrap for hermes"
|
||||
|
||||
# Hermes spills injected context over 10,000 chars to a file, which breaks
|
||||
# inline injection semantics. The bootstrap must stay under it with margin.
|
||||
HERMES_CONTEXT_SPILL_LIMIT = 10_000
|
||||
|
||||
|
||||
def _load():
|
||||
if "__init__" in sys.modules:
|
||||
del sys.modules["__init__"]
|
||||
return importlib.import_module("__init__")
|
||||
|
||||
|
||||
def _bootstrap():
|
||||
m = _load()
|
||||
return m._build_bootstrap(m._skills_dir())
|
||||
|
||||
|
||||
class TestStripFrontmatter:
|
||||
def test_strips_yaml_block(self):
|
||||
m = _load()
|
||||
content = "---\nname: foo\ndescription: bar\n---\n# Body\nContent here"
|
||||
assert m._strip_frontmatter(content) == "# Body\nContent here"
|
||||
|
||||
def test_no_frontmatter_returns_trimmed_content(self):
|
||||
m = _load()
|
||||
content = "# No frontmatter\nJust content"
|
||||
assert m._strip_frontmatter(content) == "# No frontmatter\nJust content"
|
||||
|
||||
def test_strips_surrounding_whitespace_from_body(self):
|
||||
m = _load()
|
||||
content = "---\nname: foo\n---\n\n\n# Body\n\n"
|
||||
assert m._strip_frontmatter(content) == "# Body"
|
||||
|
||||
|
||||
class TestSkillsDirResolution:
|
||||
def test_repo_layout_resolves(self):
|
||||
# The repo checkout IS the git-clone layout: .hermes-plugin/ and
|
||||
# skills/ are siblings, so resolution must succeed from here.
|
||||
m = _load()
|
||||
skills = m._skills_dir()
|
||||
assert os.path.isfile(
|
||||
os.path.join(skills, "using-superpowers", "SKILL.md")
|
||||
)
|
||||
|
||||
|
||||
class TestBootstrapContent:
|
||||
def test_marker_and_wrapper(self):
|
||||
content = _bootstrap()
|
||||
assert BOOTSTRAP_MARKER in content
|
||||
assert content.startswith("<EXTREMELY_IMPORTANT>")
|
||||
assert content.rstrip().endswith("</EXTREMELY_IMPORTANT>")
|
||||
|
||||
def test_contains_using_superpowers_body(self):
|
||||
content = _bootstrap()
|
||||
# A distinctive line from the skill body proves the real SKILL.md was
|
||||
# embedded, not a stub.
|
||||
assert "You have superpowers" in content
|
||||
assert "## The Rule" in content
|
||||
|
||||
def test_frontmatter_stripped(self):
|
||||
content = _bootstrap()
|
||||
assert "---\nname:" not in content
|
||||
|
||||
def test_tool_mapping_sourced_from_reference_file(self):
|
||||
m = _load()
|
||||
content = _bootstrap()
|
||||
ref = os.path.join(
|
||||
m._skills_dir(), "using-superpowers", "references", "hermes-tools.md"
|
||||
)
|
||||
with open(ref, encoding="utf-8") as f:
|
||||
ref_text = f.read().strip()
|
||||
# The mapping is included verbatim from the reference file — the
|
||||
# single source, not a drift-prone inline copy.
|
||||
assert ref_text in content
|
||||
assert "read_file" in content
|
||||
|
||||
def test_skill_view_guidance_present(self):
|
||||
content = _bootstrap()
|
||||
assert 'skill_view("superpowers:brainstorming")' in content
|
||||
|
||||
def test_under_hermes_context_spill_limit(self):
|
||||
content = _bootstrap()
|
||||
assert len(content) < HERMES_CONTEXT_SPILL_LIMIT, (
|
||||
f"bootstrap is {len(content)} chars; hermes spills injected "
|
||||
f"context over {HERMES_CONTEXT_SPILL_LIMIT} to a file, which "
|
||||
"breaks inline injection"
|
||||
)
|
||||
142
tests/hermes/test_plugin.py
Normal file
142
tests/hermes/test_plugin.py
Normal file
@@ -0,0 +1,142 @@
|
||||
import importlib
|
||||
import importlib.util
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
# Point at the plugin directory
|
||||
_PLUGIN_DIR = os.path.abspath(
|
||||
os.path.join(os.path.dirname(__file__), "../../.hermes-plugin")
|
||||
)
|
||||
sys.path.insert(0, _PLUGIN_DIR)
|
||||
|
||||
BOOTSTRAP_MARKER = "superpowers:using-superpowers bootstrap for hermes"
|
||||
|
||||
|
||||
def _load_plugin():
|
||||
"""Re-import plugin module fresh."""
|
||||
if "__init__" in sys.modules:
|
||||
del sys.modules["__init__"]
|
||||
return importlib.import_module("__init__")
|
||||
|
||||
|
||||
def _fire_pre_llm(ctx, **kwargs):
|
||||
hook = ctx._hooks["pre_llm_call"]
|
||||
defaults = {
|
||||
"session_id": "s1",
|
||||
"user_message": "hi",
|
||||
"conversation_history": [],
|
||||
"is_first_turn": False,
|
||||
"model": "test-model",
|
||||
"platform": "cli",
|
||||
}
|
||||
defaults.update(kwargs)
|
||||
return hook(**defaults)
|
||||
|
||||
|
||||
class TestPluginRegistration:
|
||||
def test_register_attaches_only_pre_llm_call_hook(self, mock_ctx):
|
||||
plugin = _load_plugin()
|
||||
plugin.register(mock_ctx)
|
||||
assert list(mock_ctx._hooks.keys()) == ["pre_llm_call"]
|
||||
|
||||
def test_register_registers_every_stock_skill_as_path(self, mock_ctx):
|
||||
plugin = _load_plugin()
|
||||
plugin.register(mock_ctx)
|
||||
# The conftest mock raises on non-Path (mirroring hermes' real
|
||||
# register_skill), so reaching these asserts proves every
|
||||
# registration passed a pathlib.Path.
|
||||
assert "using-superpowers" in mock_ctx._skills
|
||||
assert "brainstorming" in mock_ctx._skills
|
||||
for name, path in mock_ctx._skills.items():
|
||||
assert isinstance(path, Path)
|
||||
assert path.name == "SKILL.md"
|
||||
assert path.parent.name == name
|
||||
assert path.is_file()
|
||||
|
||||
def test_registered_skills_match_skill_directories(self, mock_ctx):
|
||||
plugin = _load_plugin()
|
||||
plugin.register(mock_ctx)
|
||||
skills_root = plugin._skills_dir()
|
||||
expected = {
|
||||
entry
|
||||
for entry in os.listdir(skills_root)
|
||||
if os.path.isfile(os.path.join(skills_root, entry, "SKILL.md"))
|
||||
}
|
||||
assert set(mock_ctx._skills.keys()) == expected
|
||||
|
||||
|
||||
class TestBootstrapInjection:
|
||||
def test_first_turn_returns_bootstrap_context(self, mock_ctx):
|
||||
plugin = _load_plugin()
|
||||
plugin.register(mock_ctx)
|
||||
result = _fire_pre_llm(mock_ctx, is_first_turn=True)
|
||||
assert isinstance(result, dict)
|
||||
content = result["context"]
|
||||
assert BOOTSTRAP_MARKER in content
|
||||
assert content.startswith("<EXTREMELY_IMPORTANT>")
|
||||
assert content.rstrip().endswith("</EXTREMELY_IMPORTANT>")
|
||||
|
||||
def test_later_turns_return_none(self, mock_ctx):
|
||||
plugin = _load_plugin()
|
||||
plugin.register(mock_ctx)
|
||||
assert _fire_pre_llm(mock_ctx, is_first_turn=False) is None
|
||||
assert _fire_pre_llm(mock_ctx, is_first_turn=None) is None
|
||||
|
||||
def test_hook_tolerates_future_kwargs(self, mock_ctx):
|
||||
plugin = _load_plugin()
|
||||
plugin.register(mock_ctx)
|
||||
result = _fire_pre_llm(
|
||||
mock_ctx, is_first_turn=True, telemetry_schema_version=3
|
||||
)
|
||||
assert BOOTSTRAP_MARKER in result["context"]
|
||||
|
||||
|
||||
class TestLayoutResolution:
|
||||
def _stage(self, tmp_path, layout):
|
||||
"""Copy the plugin module + a minimal skills tree in the given layout."""
|
||||
src_skills = Path(_PLUGIN_DIR).parent / "skills"
|
||||
if layout == "clone":
|
||||
plugdir = tmp_path / "superpowers" / ".hermes-plugin"
|
||||
else: # flat: module at the plugin dir root, skills nested inside it
|
||||
plugdir = tmp_path / "superpowers"
|
||||
skills = tmp_path / "superpowers" / "skills"
|
||||
plugdir.mkdir(parents=True, exist_ok=True)
|
||||
shutil.copy(Path(_PLUGIN_DIR) / "__init__.py", plugdir / "__init__.py")
|
||||
for skill in ("using-superpowers", "brainstorming"):
|
||||
shutil.copytree(src_skills / skill, skills / skill)
|
||||
return plugdir
|
||||
|
||||
def _load_from(self, plugdir):
|
||||
spec = importlib.util.spec_from_file_location(
|
||||
f"hermes_plugin_test_{plugdir.parent.name}_{plugdir.name}",
|
||||
plugdir / "__init__.py",
|
||||
)
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(mod)
|
||||
return mod
|
||||
|
||||
def test_clone_layout_resolves_sibling_skills(self, tmp_path, mock_ctx):
|
||||
# git-clone install: .hermes-plugin/ and skills/ are siblings.
|
||||
plugdir = self._stage(tmp_path, "clone")
|
||||
mod = self._load_from(plugdir)
|
||||
mod.register(mock_ctx)
|
||||
assert "using-superpowers" in mock_ctx._skills
|
||||
|
||||
def test_flat_layout_resolves_nested_skills(self, tmp_path, mock_ctx):
|
||||
# flattened install: module at the plugin dir root, skills/ inside it.
|
||||
plugdir = self._stage(tmp_path, "flat")
|
||||
mod = self._load_from(plugdir)
|
||||
mod.register(mock_ctx)
|
||||
assert "using-superpowers" in mock_ctx._skills
|
||||
|
||||
def test_missing_skills_raises_loudly(self, tmp_path, mock_ctx):
|
||||
plugdir = tmp_path / "superpowers"
|
||||
plugdir.mkdir(parents=True)
|
||||
shutil.copy(Path(_PLUGIN_DIR) / "__init__.py", plugdir / "__init__.py")
|
||||
mod = self._load_from(plugdir)
|
||||
with pytest.raises(RuntimeError, match="cannot find the skills"):
|
||||
mod.register(mock_ctx)
|
||||
Reference in New Issue
Block a user