Hermes Agent v0.5.0: /model slash command removed, Hugging Face provider, supply chain audit
The /model slash command is removed from both CLI and gateway in favour of the hermes model subcommand — an interactive workflow break. Also adds Hugging Face as a first-class provider, drops the compromised litellm dependency, and replaces the hardcoded 16K Anthropic output cap with per-model native limits.
PUBLISHED2026-03-28
OBSERVED2026-08-11
AGE4mo
SOURCES1
- Breaking:
/modelslash command removed from CLI and gateway; use thehermes modelsubcommand instead - Hugging Face Inference API as a first-class provider: auth, setup wizard, curated agentic model picker mapped to OpenRouter analogues, live
/modelsprobe (skipped for providers with 8+ curated models) - Nous Portal expanded to 400+ models through a single provider endpoint
- Anthropic output limits: per-model native caps (128K Opus 4.6, 64K Sonnet 4.6) replace a hardcoded 16K
max_tokens, fixing truncated responses and thinking-budget exhaustion on the direct API; useless continuation retries now skipped when reasoning consumes all output tokens - Supply chain: compromised
litellmdependency removed, dependency version ranges pinned,uv.lockregenerated with hashes, CI workflow scanning PRs for supply-chain attack patterns, CVE bumps - Telegram Private Chat Topics with per-topic skill binding for isolated project workflows
- Native Modal SDK backend replaces the swe-rex dependency, eliminating tunnels
- Plugin lifecycle hooks now fire:
pre_llm_call,post_llm_call,on_session_start,on_session_end GPT_TOOL_USE_GUIDANCEstops GPT models describing intended actions instead of calling tools; stale budget warnings stripped from history- Nix flake with uv2nix build and a NixOS module with persistent container mode
- Provider fixes:
customprovider no longer remapped toopenrouter, Alibaba default endpoint corrected, MiniMax/v1→/anthropicauto-correction overridable, OAuth token refresh migrated toplatform.claude.com - Retry, fallback, and compression lifecycle events now surface to the user
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.