Wiki audit 2026-09-30: managed-runtime dependency incident, cron fleet reconciliation, provider/model refresh

This commit is contained in:
Tony0410
2026-09-30 19:38:49 +08:00
parent 389de2119b
commit 58312cb434
8 changed files with 245 additions and 75 deletions
+19 -17
View File
@@ -3,11 +3,11 @@ title: Hermes Agent
type: system
status: active
created: 2026-07-22
updated: 2026-07-25
verified_on: 2026-07-25
updated: 2026-09-30
verified_on: 2026-09-30
confidence: high
tags: [system, hermes, agent, llm]
sources: [raw/configs/hermes-config-sanitized.txt]
sources: [live-hermes-version, live-config]
---
# Hermes Agent
@@ -16,15 +16,15 @@ sources: [raw/configs/hermes-config-sanitized.txt]
Primary personal agent for Anthony. Runs automation, research, communication, knowledge management, browser control, and scheduled tasks.
## Current Status
- **Version:** v0.19.0 (2026.7.20), upstream `9ecacd6b`
- **Version:** v0.21.5+3837.gbfda74c (2026.9.24), upstream `27062c34` — verified 2026-09-30
- **Install method:** git
- **Python:** 3.11.15
- **OpenAI SDK:** 2.24.0
- **Upstream status:** Up to date
- **Upstream status:** Update available (`hermes update`)
- **Install directory:** `/home/hermes/.hermes/hermes-agent`
- **Managed runtimes:** 10 uv-managed venvs under `~/.hermes/installs/019d0d114d22b7e6/environments/<hash>/venv`. Dependency guard `hermes-runtime-deps-guard.sh` verifies `dotenv` + `mnemosyne` in every venv every 15 min — see [[incidents/2026-09-28-hermes-managed-runtime-deps]].
- **Community resources:** [Hermes Registry](https://babylondreams.de/hermes-registry/) — third-party plugins, skills, and extensions
- **Binary:** `/home/hermes/.local/bin/hermes`
- **Config:** `~/.hermes/config.yaml` (version 33)
- **Config:** `~/.hermes/config.yaml`
- **Profile:** `default` (`~/.hermes/profiles/default/`)
## Location
@@ -33,9 +33,9 @@ Primary personal agent for Anthony. Runs automation, research, communication, kn
- **Working directory:** `/home/hermes/workspace`
## Providers & Routing
- **Default provider:** `custom:litellm` → `http://litellm:4000/v1`
- **Fallback provider:** `custom:omniroute` → `http://omniroute:20128/v1`
- **Default model:** `freellmapi-auto`
- **Default provider:** `custom` → `http://100.78.63.20:20128` (OmniRoute) — verified 2026-09-30
- **Default model:** `smart-route` — verified 2026-09-30
- **History:** as at 2026-07-22 this was `custom:litellm` → `litellm:4000` with model `freellmapi-auto`
- **Provider model count:** ~3430 (omniroute), ~1512 (litellm)
- **free-stack combo (OmniRoute):** Nemotron 3 Ultra 550B configured with `max_tokens: 8192`, `reasoning_effort: medium`, `chat_template_kwargs.force_nonempty_content: true` (see [[omniroute]])
- See [[model-providers]] for full breakdown.
@@ -72,9 +72,9 @@ Primary personal agent for Anthony. Runs automation, research, communication, kn
- See [[terminal-backend]] for details.
## Skills
- **Total installed:** 66
- **Total installed:** 341 (per stocktake 2026-09-25)
- Key skills: hermes, hermes-gateway-troubleshooting, hermes-mcp-troubleshooting, hermes-api-vault, omniroute, job-search-automation, weekly-review, fresh-rss-intelligence-filter, etc.
- See [[skills-index]] for categorized list.
- See [[skills-index]] for categorized list (auto-regenerated daily).
## Multi-Profile Multiplexer
@@ -105,7 +105,7 @@ The `allowed_chats` gate runs on the **default profile's adapter** before `profi
- **Discord:** enabled, streaming true
- **Slack:** enabled
- **Email:** connected
- **Mattermost:** connected
- **Mattermost:** connected; gateway warning on 2026-08-15 was caused by a disabled system-level `hermes-gateway.service` unit, not a live duplicate gateway. Only the user-level service is active.
- **ntfy:** connected
- **Google Chat:** available (`hermes-google_chat`)
- **QQ:** available (`hermes-qqbot`)
@@ -113,9 +113,9 @@ The `allowed_chats` gate runs on the **default profile's adapter** before `profi
- See [[messaging-integrations]] for details.
## Scheduled Tasks
- **Cron jobs:** 25 active jobs
- **Cron jobs:** 30 total (27 enabled, 3 disabled) — verified 2026-09-30
- Delivery targets: Telegram (primary), Discord, origin, local
- Notable: Birthday checker, job radar, newsletter digests, GitHub trending, mnemosyne health/watchdog/backup, AgentMail watcher
- Notable: Birthday checker, job radar, newsletter digests, GitHub trending, mnemosyne health/watchdog/backup, AgentMail watcher, skills stock-take regeneration
- See [[scheduled-tasks]] for full table.
## Dependencies
@@ -126,9 +126,11 @@ The `allowed_chats` gate runs on the **default profile's adapter** before `profi
- Telegram bot token, Discord token, etc. (stored outside wiki)
## Known Issues
- Router migration incomplete
- Managed-runtime venvs previously drifted on dependencies, breaking cron workers — now guarded every 15 min. See [[incidents/2026-09-28-hermes-managed-runtime-deps]].
- Daily Marketing Job Radar pinned to a model its upstream plan rejects (`gpt-5.6-terra` → 403 `MODEL_NOT_IN_PLAN`). See [[systems/scheduled-tasks]].
- Telegram thread delivery failures on `telegram:1793951355` (thread `34795` not found).
- **Two wiki trees drift:** `/home/hermes/workspace/agent-estate-wiki` (Gitea + Quartz source, pages at root) and `/home/hermes/wiki/agent-estate-wiki` (Obsidian/Ignis vault, pages under `wiki/`). They are separate git repos with different history. See [[current-state]].
- Browser persistence not yet fully verified
- Obsidian Git plugin auto-sync caused conflicts during vault reorganization
## Related
- [[model-providers]]