Tony0410
77250ea8c9
- New incident page documenting CT299 SFTPGo outage (02:18 AWST) - Root cause: swap exhaustion (43Gi, 100%) killed tailscaled; 5 stale lxc-attach PIDs blocked pct start - Resolution: killed PIDs 3037951/3334928/3352203/3402511/4004148, pct stop/start 299 - Updated current-state.md with Recent Changes (2026-09-02), bumped updated to 2026-09-04 - Updated log.md with incident entry - Updated index.md last-updated date No secrets written. Verified end-to-end: tailscale direct, SFTPGo WebAdmin HTTP 401, SFTP banner SSH-2.0-SFTPGo_2.7.0.
5.3 KiB
5.3 KiB
title, type, status, created, updated, verified_on, confidence, tags, sources
| title | type | status | created | updated | verified_on | confidence | tags | sources | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Model Providers | system | active | 2026-07-22 | 2026-08-20 | 2026-08-20 | high |
|
|
Model Providers
Purpose
Inference providers available to Hermes, their routing paths, and notable model updates.
Current Provider Stack
| Provider | URL | Role |
|---|---|---|
custom:litellm |
http://litellm:4000/v1 |
Main inference (slower path, 6–26s/call) |
custom:omni |
http://omni:20128/v1 |
Auxiliary roles (vision, skills, approval, mcp, web_extract, compression) — factory-reset 2026-08-14 |
opencode-zen |
(internal) | Free-tier model access for cron jobs |
charm-hyper |
hyper.charm.land/v1 |
Coding-focused inference (Charmbracelet) — passthrough models, free tier 100 credits/mo |
| Guanaco | ollama:11434 |
LLM proxy/router on CT205 (Ollama stack) |
Default Model
resilient-free— resolves through OmniRoute (changed fromauto/best-freeon 2026-08-14 after factory reset)- Previous default
auto/best-freewas misconfigured — had no combo definition and routed to paidgpt-5.6-sol freellmapi-auto(LiteLLM path) still available but slower
Notable Model Updates
HyperCharm (Charmbracelet) — Provider Research (2026-08-20)
- What: Hyper (hyper.charm.land) is Charmbracelet's LLM inference service, purpose-built for agentic coding models
- OmniRoute integration: Already merged — PR #5961 (2026-07-03) added as
charm-hyperprovider with passthrough models fromhyper.charm.land/v1/models - Free plan: 100 Hypercredits/month (~$5 value), no rollover — use it or lose it monthly
- Credit mechanics: 1 Hypercredit = $0.05; balance queryable via
GET /v1/credits(returns{"balance": 100}) - Catalog pricing (cheap models): deepseek-v4-flash $0.20/$0.40 per 1M in/out, qwen3.7-flash $0.20/$0.80, gemma-4-26b $0.12/$0.42
- No config changes made — research only;
charm-hyperis available but not wired as a Hermes default - Status: Candidate for free-tier OmniRoute combo; passthrough model import means zero maintenance
GPT-5.6 Luna — Model Research (2026-08-14)
- Community consensus: Luna is cleaner/more polished; DeepSeek V4 Flash is more persistent/cheaper
- Luna strengths: visual/UI work, final code review, bounded high-stakes tasks, cleaner structured output
- DeepSeek strengths: automation, persistent executor work, high-volume subtasks, long-context economics
- Key caveat: Provider route matters more than model name —
openai-codex/gpt-5.6-luna,openrouter/openai/gpt-5.6-luna,deepseek/deepseek-v4-flash, andopenrouter/deepseek/deepseek-v4-flashare four different tests - Pricing: Direct OpenAI $0.20/M input, $1.20/M output; OpenRouter $0.10/M input, $0.60/M output
- Context: 1.05M tokens, 128K output, function calling, structured outputs, image input, configurable reasoning effort
- Recommendation: Luna plans and reviews; DeepSeek executes — but test on a clean direct route before judging
Guanaco v0.8.14 (2026-08-14)
- Updated from v0.8.11 on CT205 — three incremental bug-fix releases focused on DSML/tool-call output hygiene
- DSML tag leakage fixes: malformed tool-call output no longer leaks raw syntax junk into model context
- Dashboard performance fix: cached content size, fixed wrong column names in history query
- No new features, no breaking changes — low-risk update
- See systems/guanaco
DeepSeek V4 Flash 0731 (2026-07-31)
- Same model ID:
deepseek-v4-flash— no ID change, just a post-training bump - Same architecture: 284B total params, 13B active per token, 1M context window
- Same pricing: $0.14/M input, $0.28/M output
- Benchmark jump: Terminal Bench 2.1: 82.7 (up from 61.8 preview — 34% relative gain)
- Now surpasses V4-Pro preview (72.1) on agent/coding benchmarks
- Stricter tool name validation: Rejects tool names not matching
^[a-zA-Z0-9_-]+$— may cause issues with OmniRoute-transformed tool names - Impact: Your existing cron jobs using
deepseek-v4-flashget the upgrade automatically. The empty-stream fallback issue (opencode-go/deepseek-v4-flashreturning empty 200s) is a provider plumbing problem, not a model quality problem.
OmniRoute Free-DeepSeek Silent-Stop Mitigation (2026-08-04)
- Free-DeepSeek upstreams returning empty-after-tool responses since Aug 1 → silent turn stops on
deepseek-flash-freeandsmart-route/good-freeacross both instances - Reworked both combos: strategy
priority→fill-first, dropped proven culprits (238d5978/deepseek-v4-flash+-0731,nvidiadeepseek), healthy free models promoted, deepseek demoted to last resort - See incidents/2026-08-04-omniroute-free-deepseek-silent-stops
Context Enforcement
- Three layers: model native → combo
data.config.context_length→ Hermes client cap - Effective context is the minimum of the three
Combo Behavior
priorityretries same provider up tomaxRetries, then errors; it does NOT fall throughfill-firstwalks the list on failureauto/lkgprecalculates per request using health scoring- Same-provider entries in a combo share rate-limit buckets
- Session affinity caches provider in
session_model_history