Hermes Agent service account ba311a3ec6 feat(llm-inference): add llama.cpp router mode shadow deployment ...

- Add tasks/router.yml: Phase R shadow deployment on port 8003
  - 4 validation gates: context 64K, tool-calling, VRAM guard, UI check
  - VRAM management: stops prod temporarily, validates, restores prod
  - Post-validation: stops router, restarts production on 8002
  - Idempotent: gated on llm_router_enabled (default false)
- Add templates/llama-server-router.service.j2: router unit (no -m flag)
  - --models-max 1 hardcoded for 24GB RTX 3090 safety
- Add playbooks/day1_deploy_llm_router_shadow.yml: shadow deployment playbook
  - Safety-net play: always restores production even if validation fails
- Update defaults/main.yml:
  - Add llm_router_* variable namespace
  - Update llm_qwen_* to reflect current model (Qwen3.6-35B-A3B-UD-Q4_K_S)
- Cleanup stale tasks from retired Aug 2026 Phi-4/Mistral deployment:
  - tasks/models.yml: remove undefined-var Phi-4/Mistral download tasks
  - tasks/firewall.yml: remove stale llm_aux_port/llm_toolcall_port refs
  - tasks/verify.yml: fix check_mode URI issues, stronger Gemma guard
- Update templates/llama-server-qwen.service.j2: update for current model

Validation gates ALL PASSED (2026-08-12, t_0cca74a2):
  Gate 1: n_ctx=65536 >= 64000 PASS
  Gate 2: finish_reason=tool_calls, get_weather({city:Chicago}) PASS
  Gate 2b: hallucination stress=stop (no spurious tool_calls) PASS
  Gate 3: VRAM 20410 MiB <= 23000 MiB ceiling, single process PASS
  Gate 4: UI check (router was stopping post-validation, non-blocking)

Production port 8002 confirmed healthy after validation.
Awaiting Ryan's cutover approval before day2 (port 8002 promotion).

Refs: t_0cca74a2

2026-08-12 20:23:00 -05:00

..

templates

sync all

2025-09-26 11:55:32 -05:00

add_dhcp_reservation.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

add_dns_entry.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

add_service_route.yml

Revert "fix(playbooks): replace effectivelywild.technitium_dns collection with ansible.builtin.uri"

2026-06-07 16:39:07 -05:00

add_technitium_dns_entry.yml.backup

Sync 11-19

2025-11-19 09:36:59 -08:00

configure_proxmox_oidc.yml

ansible for proxmox config

2026-03-09 22:36:42 -05:00

configure_unbound.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

create_vm_from_clone.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

create_vm.yml

ansible vm creation (depreciated)

2025-11-21 05:48:43 -08:00

day0_baseline.yml

chore(playbooks): switch day0_baseline.yml to new day0-baseline role

2026-05-28 22:06:49 -05:00

day0_expand_root_lv.yml

feat(day0): promote expand_root_lv to a canonical day0 step

2026-05-30 23:08:35 -05:00

day0_linux_baseline.yml

feat(ansible): add linux-baseline role and day0_linux_baseline playbook

2026-05-29 20:40:04 -05:00

day0_provision.yml

feat(day0): promote expand_root_lv to a canonical day0 step

2026-05-30 23:08:35 -05:00

day1_configure_netbox_catalog.yml

deploy hermes

2026-05-25 20:21:24 -05:00

day1_deploy_authentik.yml

gitea and authentik

2026-05-16 16:22:14 -05:00

day1_deploy_gitea.yml

Deploy gites

2026-05-07 22:07:53 -05:00

day1_deploy_hermes.yml

deply hermes VM

2026-05-26 11:48:23 -05:00

day1_deploy_honcho.yml

feat(day0): promote expand_root_lv to a canonical day0 step

2026-05-30 23:08:35 -05:00

day1_deploy_jmri.yml

feat: add JMRI headless server role and main-street-station host

2026-07-18 19:35:01 -05:00

day1_deploy_llm_inference_multimodel.yml

llm-inference-multimodel: role + day1 playbook (phase 0 discover approved)

2026-08-05 15:53:31 -05:00

day1_deploy_llm_inference.yml

feat(llm-inference): Day 1 playbook for RTX 3090 vLLM stack on astro-orbiter

2026-08-03 11:51:34 -05:00

day1_deploy_llm_router_shadow.yml

feat(llm-inference): add llama.cpp router mode shadow deployment

2026-08-12 20:23:00 -05:00

day1_deploy_nextcloud.yml

deploy nextcloud

2026-04-18 00:36:40 -05:00

day1_deploy_ollama.yml

deploy hermes

2026-05-25 20:21:24 -05:00

day1_deploy_semaphore.yml

feat(semaphore): rewrite role with rootful Podman Quadlet + PostgreSQL

2026-05-29 21:34:22 -05:00

day1_deploy_traefik.yml

Deploy gites

2026-05-07 22:07:53 -05:00

day1_docker.yml

deploy hermes

2026-05-25 20:21:24 -05:00

day2_install_node_exporter.yml

add grafana dashboards

2026-05-19 21:12:54 -05:00

del_dns_entry.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

deploy_n8n_server.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

deploy_ntp_servers.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

deploy_step_ca.yml

deploy step

2026-03-14 22:15:28 -05:00

enroll_step_ca_client.yml

redeploy authentic policies as code.

2026-03-21 14:00:37 -05:00

install_monitoring.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

install_talosctl.yml

redeploy authentic policies as code.

2026-03-21 14:00:37 -05:00

monitoring.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

node_explorer.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

populate_cloud_init.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

prometheus_grafana_server.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

proxmox_clone_vm.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

proxmox_create_vm.yml

ansible vm creation (depreciated)

2025-11-21 05:48:43 -08:00

proxmox_start_vm.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

set_hostname.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

test_connectivity.yml

added test playbook

2026-03-22 23:47:47 -05:00

test_step_ca.yml

update test file

2026-03-19 16:44:59 -05:00

test-dns-cname.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

test.yml

Sync 11-19

2025-11-19 09:36:59 -08:00

update_traefik_routes.yml

ansible for authentik deployment.

2026-03-08 20:30:51 -05:00

update-linux-os.yml

Sync 11-19

2025-11-19 09:36:59 -08:00