b3nw
3b7d6bb67c
- workspace: capmetro-monitor, github-notifications, model-selector - workspace-security: vt-monitor, monitor-unauthorized - workspace-home: cron-manager, monitor-unauthorized - extensions: vt-sentinel (VT-Sentinel plugin) Includes sync.sh for pull/push, README, AGENTS.md, .gitignore.
87 lines
2.6 KiB
Markdown
87 lines
2.6 KiB
Markdown
---
|
|
name: model-selector
|
|
description: Safely change an agent's primary and fallback models by validating IDs against the live LLM proxy model list. Use for model switches, fallback chain updates, and model-availability troubleshooting.
|
|
---
|
|
|
|
# Model Selector
|
|
|
|
## Core Rules
|
|
|
|
1. Validate model IDs against `/v1/models` before proposing changes.
|
|
2. Keep at least 2 fallback models.
|
|
3. Do not remove a primary model without setting a replacement.
|
|
4. Use exact IDs from the model catalog; do not guess.
|
|
5. Prefer provider diversity in fallbacks.
|
|
6. Get explicit user approval before writing config.
|
|
7. Treat `/model` as temporary; it creates per-session overrides.
|
|
8. After backend default changes, clear session pins and reset active sessions.
|
|
|
|
## Workflow
|
|
|
|
### 1) Fetch Available Models
|
|
|
|
```bash
|
|
bash {baseDir}/scripts/list-models.sh
|
|
bash {baseDir}/scripts/list-models.sh --providers
|
|
```
|
|
|
|
### 2) Validate Candidate IDs
|
|
|
|
```bash
|
|
bash {baseDir}/scripts/validate-model.sh "nvidia_nim/moonshotai/kimi-k2.5"
|
|
```
|
|
|
|
### 3) Inspect Current Configuration
|
|
|
|
```bash
|
|
bash {baseDir}/scripts/show-current.sh
|
|
```
|
|
|
|
### 4) Apply Backend Model Changes
|
|
|
|
```bash
|
|
# Primary only
|
|
bash {baseDir}/scripts/update-model.sh --primary "nanogpt/moonshotai/kimi-k2.5"
|
|
|
|
# Fallbacks only
|
|
bash {baseDir}/scripts/update-model.sh --fallbacks "nvidia_nim/moonshotai/kimi-k2.5,chutes/zai-org/GLM-5-TEE"
|
|
|
|
# Primary + fallbacks
|
|
bash {baseDir}/scripts/update-model.sh \
|
|
--primary "nanogpt/moonshotai/kimi-k2.5" \
|
|
--fallbacks "nvidia_nim/moonshotai/kimi-k2.5,chutes/zai-org/GLM-5-TEE"
|
|
```
|
|
|
|
### 5) Required Rollout Sequence (Do Not Skip)
|
|
|
|
1. Clear per-session model pins so defaults can apply.
|
|
2. Restart gateway so in-memory runtime state reloads config.
|
|
3. In active channels/threads, run `/reset` (or `/new`) before testing.
|
|
|
|
Use pin cleanup helper:
|
|
|
|
```bash
|
|
# Clear all session model pins for an agent
|
|
bash {baseDir}/scripts/clear-session-model-pins.sh --agent home
|
|
|
|
# Clear only one channel session family
|
|
bash {baseDir}/scripts/clear-session-model-pins.sh --agent home --channel 1470162839284224184
|
|
```
|
|
|
|
## Model ID Format
|
|
|
|
- Catalog ID format: `<provider>/<model-path>`
|
|
- Config reference format: `llm-proxy/<catalog-id>`
|
|
|
|
Examples:
|
|
- `nanogpt/moonshotai/kimi-k2.5` -> `llm-proxy/nanogpt/moonshotai/kimi-k2.5`
|
|
- `nvidia_nim/moonshotai/kimi-k2.5` -> `llm-proxy/nvidia_nim/moonshotai/kimi-k2.5`
|
|
|
|
For `/model` inside a session, use catalog IDs (without `llm-proxy/`).
|
|
|
|
## Troubleshooting Quick Checks
|
|
|
|
1. Model missing: rerun `list-models.sh` and validate exact ID.
|
|
2. Old model still used: clear session pins + restart gateway + `/reset`.
|
|
3. Unexpected fallbacks: confirm fallback chain order in `show-current.sh`.
|