docs(sillytavern): apply DEV-1482 review findings (DEV-1430)

Applies eight review findings from the DEV-1482 integration review. All
scoped to docs/v3/guides/integrations/sillytavern.mdx; no code changes.

- DOC-3: curl -fsSL in install command (fails loud on 4xx/5xx)
- DOC-4: Note now reflects installer auto-config + manual-fallback
- DOC-6: LLM-backend prerequisite callout at top of Quick Start
- DOC-14: restart step warns about live-session clobbering
- DOC-5: Global Config intro names resolution order + precedence;
  disambiguates "sillytavern" workspace vs hosts.sillytavern key
- DOC-7: new Peer Observability subsection (asymmetric default)
- DOC-2: route count in Architecture diagram 7 → 9
- DOC-8: troubleshooting row for "plugin on disk, drawer absent"

Findings index + rationale: plastic-labs/sillytavern-honcho#3
This commit is contained in:
lilyplasticlabs 2026-04-21 14:56:06 -04:00
parent 4cda36c860
commit 1e7a3461e5
1 changed files with 21 additions and 6 deletions

View File

@ -11,6 +11,10 @@ The extension has two parts: a **client extension** (browser) that hooks into Si
## Quick Start
<Note>
Honcho stores memory; it doesn't generate text. You'll also need an LLM backend (OpenAI, Claude, OpenRouter, local llama.cpp, etc.) connected via SillyTavern's plug icon in the top nav. Configure that separately before expecting replies in chat.
</Note>
### Step 1: Get Your Honcho API Key
1. Go to **[app.honcho.dev](https://app.honcho.dev)**
@ -23,7 +27,7 @@ From your **SillyTavern directory**:
**macOS / Linux:**
```bash
bash <(curl -s https://raw.githubusercontent.com/plastic-labs/sillytavern-honcho/main/install.sh)
bash <(curl -fsSL https://raw.githubusercontent.com/plastic-labs/sillytavern-honcho/main/install.sh)
```
**Windows (PowerShell):**
@ -32,7 +36,7 @@ irm https://raw.githubusercontent.com/plastic-labs/sillytavern-honcho/main/insta
```
<Note>
Server plugins must be enabled. The installer checks for this, but if you haven't already, add `enableServerPlugins: true` to your `config.yaml`.
Server plugins must be enabled for the Honcho plugin to load. The installer configures this automatically on fresh checkouts; if you skipped the installer or started SillyTavern before running it, manually set `enableServerPlugins: true` in `config.yaml` and restart.
</Note>
The installer:
@ -43,7 +47,7 @@ The installer:
### Step 3: Restart SillyTavern
Stop and restart SillyTavern so the server plugin loads.
Stop and restart SillyTavern so the server plugin loads. If you have in-progress chats open, save them first — the running session ends when you stop the server.
### Step 4: Configure
@ -56,7 +60,11 @@ Open **Extensions** (puzzle piece icon) and expand **Honcho Memory**:
## Global Config (Multi-Tool Setups)
If you already use Honcho with other tools (Claude Code, Cursor, Hermes), the extension auto-populates settings from `~/.honcho/config.json`:
If you already use Honcho with other tools (Claude Code, Cursor, Hermes), the extension reads from `~/.honcho/config.json` on startup when resolvable keys are present. Resolution order: `hosts.sillytavern.apiKey` → root-level `apiKey` → fall through to the Extensions-panel key if neither resolves. The Extensions-panel key (SillyTavern's secret manager) takes priority at request time, so entering one in the UI overrides the config file without touching it.
Note that "sillytavern" appears in two namespaces here: as the Honcho workspace ID (a Honcho concept — what you see in the dashboard) and as the `hosts.sillytavern` host key in the config file (a local convention for which tool's settings are which).
Flat form:
```json
{
@ -67,7 +75,9 @@ If you already use Honcho with other tools (Claude Code, Cursor, Hermes), the ex
}
```
Config reads fall back from `hosts.sillytavern` to root-level globals. Writes are always scoped to `hosts.sillytavern` -- the extension never mutates settings for other tools.
Writes are always scoped to `hosts.sillytavern` — the extension never mutates settings for other tools.
Nested form (when multiple tools share the file):
```jsonc
{
@ -112,6 +122,10 @@ In tool call mode, the extension registers three function tools that the LLM can
This mode works best with models that support function calling. The LLM decides when to query memory rather than firing on every turn.
### Peer Observability
By default, only the user peer accumulates derived memory — Honcho observes the user's messages and derives conclusions across sessions. The AI character's persona comes from its character card, not from peer derivation. If you want the character to have its own Honcho-derived state, configure it as an additional peer in session setup.
### Peer Modes
| Mode | Behavior |
@ -143,7 +157,7 @@ Browser (Client Extension) Server (Plugin)
+-----------------------+ +------------------------------+
| index.js | fetch() | plugin/index.js |
| | ------------> | |
| - Settings UI | /api/plugins/ | - Express router (7 routes) |
| - Settings UI | /api/plugins/ | - Express router (9 routes) |
| - Event hooks | honcho-proxy | - Honcho SDK (@honcho-ai/sdk)|
| - Prompt injection | | - API key from ST secrets or |
| - Tool registration | | ~/.honcho/config.json |
@ -161,6 +175,7 @@ The server plugin reads API credentials from SillyTavern's secrets store first,
| 403 on plugin requests | Set Honcho API key in extension settings or `~/.honcho/config.json` |
| SDK import error | Run `cd plugins/honcho-proxy && npm install` |
| Extension loads but nothing happens | Enable the checkbox and ensure workspace ID is set |
| Plugin on disk but "Honcho Memory" drawer doesn't appear at all | Set `enableServerPlugins: true` in `config.yaml`; the panel can't show plugins the server never loaded |
---