Merge origin/main: sync Qwen3-8B no_think variant to Ansible repo (t_36e8ba68)

Resolved conflicts between local bafd76a (t_c5cef2b2, Qwen3-8B single-variant)
and origin/main 5cf4468 (t_664289a0, Qwen3-8B dual-thinking deployment).

Conflict resolution strategy: took origin/main version throughout — it is the
authoritative result from t_664289a0 which deployed the live no_think config to
astro-orbiter and already reflects the correct production state.

Changes incorporated from origin/main:
- defaults/main.yml: Qwen3-8B-Q4_K_M-no_think model entry (port 8107, n_gpu_layers=99,
  chat_template_file), row6 matrix entry, dual-thinking comment block.
- templates/llama-server-router-preset.ini.j2: [Qwen3-8B-Q4_K_M] with sleep-idle-seconds=60
  plus new [Qwen3-8B-Q4_K_M-no_think] section with chat-template-file directive.
- templates/qwen3-no-think.jinja.j2: new file — Qwen3 template with enable_thinking=false.
- tasks/models.yml: template deploy task for qwen3-no-think.jinja (chat_templates tag).
- tasks/swapmode.yml: GATE 2 assert updated to 7 models.
- templates/llama-swap-config.yaml.j2: chat_template_file flag support.

Also pulled in monitoring defaults (llm_monitoring_enabled, VRAM exporter settings,
Grafana dashboard vars, Prometheus scrape config) from origin/main monitoring branch.

ansible/host_vars/astro-orbiter/vars.yml

@@ -34,26 +34,27 @@ common_root_lv: ubuntu-lv
 # (t_33acbb2e) so the router can keep more than one GGUF resident on-demand
 # and LRU-evict when needed.
 #
-# VRAM NOTE (t_33acbb2e, updated t_55c164f5, updated t_34b96e83, updated t_f5f7e9ad, updated t_441470b9):
-# With models-max=4 and all 5 GGUFs registered, worst case is all 5 loaded simultaneously:
-#   Qwen3.8-27B Q4_K_M:               ~23.3GB (weights ~17.1GB + KV ~6.2GB @ 128K ctx, q4_0) ← UPDATED
+# VRAM NOTE (t_33acbb2e, updated t_55c164f5, updated t_34b96e83, updated t_f5f7e9ad, updated t_441470b9, updated t_c5cef2b2):
+# With models-max=4 and all 6 GGUFs registered, worst case is all 6 loaded simultaneously:
+#   Qwen3.8-27B Q4_K_M:               ~20.0GB (weights ~17.1GB + KV ~2.9GB @ 65536 ctx, q4_0) ← CORRECTED (ctx rolled back from 128K to 65536, t_c9fed26c 2026-08-18)
 #   Phi-3.5-mini-instruct Q8_0:       ~4.3GB  (weights ~3.8GB + KV ~0.5GB @ 32K ctx)
 #   Meta-Llama-3.1-8B Q4_K_M:        ~5.6GB  (weights ~4.6GB + KV ~0.2GB @ 8K ctx)
 #   Qwen2.5-Coder-14B Q4_K_M:        ~9.0GB  (weights ~8.4GB + KV ~0.6GB @ 16K ctx)
 #   nomic-embed-text-v1.5 Q4_K_M:    ~0.09GB (~84MB, embedding only — no KV cache)
-#   Total worst-case:                 ~42.3GB  >>  24GB RTX 3090
+#   Qwen3-8B Q4_K_M:                 ~5.5GB  (weights ~4.68GB + KV ~0.5GB @ 32K ctx, q4_0)
+#   Total worst-case:                 ~44.5GB  >>  24GB RTX 3090
 #
 # OOM RISK: Full co-residency is impossible on 24GB. LRU eviction prevents this
-# in practice: models-max=4 means the router can REGISTER 5 models but only keeps
+# in practice: models-max=4 means the router can REGISTER 6 models but only keeps
 # up to 4 LOADED simultaneously — the router will evict the LRU model when a new
 # one is needed. nomic-embed-text-v1.5 is pinned via sleep-idle-seconds=-1 and
 # load-on-startup=true but it uses only ~84MB, so it never meaningfully changes
 # the budget. In single-user homelab operation, only one generative model is active
 # at a time alongside the always-resident embedding model.
-# Qwen3.8-27B alone uses ~23.1GB (weights+KV); co-residency with Coder (~9GB) = ~32GB > 24GB.
-# LRU eviction handles this automatically — the router evicts the idle model before
-# loading the new one. Ryan should be aware this means model-switching always incurs
-# a ~30-60s cold-load latency when switching between Qwen3.8-27B and any other model.
+# Qwen3.8-27B alone uses ~17,804 MiB (weights+KV @ 65536 ctx); co-residency
+# with Coder (~9GB) = ~27GB > 24GB. LRU eviction handles this automatically.
+# Ryan should be aware this means model-switching always incurs a ~30-60s
+# cold-load latency when switching between Qwen3.8-27B and any other model.
 # Proceeding to models-max=4 as instructed; flagged for Ryan's attention.
 # Router --models-max override for astro-orbiter.
 # UPDATED (t_f5f7e9ad, 2026-08-16): Set to 2 because Qwen3.8-27B-Q4_K_M
@@ -67,13 +68,16 @@ common_root_lv: ubuntu-lv
 # This avoids an LRU eviction race with nomic-embed at startup.
 # UPDATED (t_72646029, 2026-08-17): CPU offload for Coder + Llama changes the
 # constraint. Coder and Llama now use CPU inference (n-gpu-layers=0). GPU-resident
-# VRAM: Qwen3.8 (~20,302 MiB at 128K ctx) + nomic-embed (558 MiB, pinned) plus the
-# CUDA-context buffers llama.cpp 6ea215d allocates for the CPU models (~1.4-1.7GB
-# each) = ~24,004 MiB steady-state, below the 24,576 MiB physical limit.
+# VRAM: Qwen3.8 (~17,804 MiB at 65536 ctx) + nomic-embed (558 MiB, pinned) plus
+# the CUDA-context buffers llama.cpp 6ea215d allocates for the CPU models (~1.4-1.7GB
+# each) = ~20,004 MiB steady-state, below the 24,576 MiB physical limit.
+# CORRECTED (t_c5cef2b2, 2026-08-19): ctx-size was rolled back from 131072 to 65536
+# (t_c9fed26c 2026-08-18). Qwen3.8 VRAM at 65536: 17,804 MiB (not 20,302 MiB).
 # models-max raised to 4: nomic (slot 1, pinned) + Qwen3.8 (slot 2, GPU) +
-# Llama (slot 3, CPU) + Coder (slot 4, CPU). Phi (GPU, ~8.3GB) can still be
-# requested but evicts Qwen3.8 due to VRAM constraint. models-max=4
-# is required so CPU-offloaded models count as loaded without evicting Qwen3.8.
+# Llama (slot 3, CPU) + Coder (slot 4, CPU). Phi (GPU, ~8.3GB) and new
+# Qwen3-8B (GPU, ~5.5GB) can also be requested but evict Qwen3.8 due to VRAM.
+# models-max=4 is required so CPU-offloaded models count as loaded without
+# evicting Qwen3.8.
 llm_router_models_max: 4
 
 llm_staged_models:
@@ -93,4 +97,15 @@ llm_staged_models:
     url: "https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/nomic-embed-text-v1.5.Q4_K_M.gguf"
     size_bytes: 84106624
     source_repo: "nomic-ai/nomic-embed-text-v1.5-GGUF"
+  # Added t_c5cef2b2 (2026-08-19, War Machine): Qwen3-8B dense 8B model for
+  # aux tasks (routing, rewriting, structured extraction, tool-call construction).
+  # Source: bartowski/Qwen_Qwen3-8B-GGUF (public, no auth). HF filename is
+  # Qwen_Qwen3-8B-Q4_K_M.gguf; stored locally as Qwen3-8B-Q4_K_M.gguf.
+  # Exact size verified from HF manifest (content-length): 5,027,784,224 bytes.
+  # VRAM: ~4.68GB weights + ~0.5GB KV @ 32K ctx (q4_0) ≈ 5.2GB total.
+  # Thinking mode ON by default; use /no_think for latency-sensitive aux tasks.
+  - filename: "Qwen3-8B-Q4_K_M.gguf"
+    url: "https://huggingface.co/bartowski/Qwen_Qwen3-8B-GGUF/resolve/main/Qwen_Qwen3-8B-Q4_K_M.gguf"
+    size_bytes: 5027784224
+    source_repo: "bartowski/Qwen_Qwen3-8B-GGUF"
 

ansible/roles/llm-inference-multimodel/defaults/main.yml

@@ -314,6 +314,7 @@ llm_swapmode_models:
     sleep_idle_seconds: 60
     chat_template_file: "{{ llm_models_dir }}/templates/qwen3-no-think.jinja"
 
+
 # llama-swap matrix routing configuration
 # Each row defines a set of models that can be co-resident and hot-swappable
 # Syntax: "model1 & model2" = both models in same row (via v250 expression DSL)

ansible/roles/llm-inference-multimodel/templates/llama-server-router-preset.ini.j2

@@ -259,4 +259,4 @@ batch-size         = {{ llm_router_batch_size }}
 ubatch-size        = {{ llm_router_ubatch_size }}
 parallel           = {{ llm_router_parallel }}
 chat-template-file = {{ llm_models_dir }}/templates/qwen3-no-think.jinja
-sleep-idle-seconds = 60
+sleep-idle-seconds = 60