test(hermes): realign suite with the pre_llm_call mechanism; slim docs to the README section

The 20-test suite still exercised the dead on_session_start/inject_message
mechanism (17 failures against the rewritten plugin). Rewritten for the
real contract: pre_llm_call registration + first-turn-only context return,
register_skill receiving pathlib.Path (the conftest mock now raises on str,
mirroring hermes' AttributeError that silently disables a plugin), both
install layouts resolving skills, loud failure when skills are missing,
tool mapping sourced verbatim from hermes-tools.md, and a bootstrap-size
guard against hermes' 10k-char context spill threshold. 19 tests, passing.

Install docs collapse into the README section per maintainer direction:
docs/README.hermes.md and .hermes-plugin/INSTALL.md are gone; the README
carries the two-line install plus the compaction caveat. plugin.yaml
version aligned to 6.1.1.
This commit is contained in:
Jesse Vincent
2026-07-23 16:05:54 -07:00
parent 178528c03e
commit b6613057ae
7 changed files with 185 additions and 179 deletions

View File

@@ -1,30 +0,0 @@
# Hermes Agent — Superpowers Plugin
## Install
```bash
hermes plugins install obra/superpowers --enable
```
Restart any active Hermes sessions after installing.
## Smoke check
Start a new session and send:
> What are your superpowers?
The model should describe brainstorming, TDD, debugging, and planning skills.
If it doesn't, the bootstrap isn't loading — reinstall and restart.
## Acceptance test
Send in a fresh session:
> Let's make a react todo list
The `brainstorming` skill must trigger and run its flow before any code is written.
## Uninstall
```bash
hermes plugins remove superpowers
```

View File

@@ -1,5 +1,5 @@
name: superpowers
version: 6.0.3
version: 6.1.1
description: Superpowers skills and workflow bootstrap for Hermes Agent
author: obra
provides_hooks: