fix(dev): OneX Ornith 슬롯을 admission과 일치시킨다

agent-test/dev/edge-smoke.md

@@ -91,8 +91,8 @@ Claude Anthropic-compatible 단일 요청 Agent 실행을 검증할 때는 Claud
   - served model: `Ornith-1.0-35B-GGUF-llamacpp-tp1-Q5_K_M`
   - capacity baseline: `1` (agent 장문 요청의 provider 독점 실행 기준)
   - priority baseline: `2`
-  - load baseline: checkpoint `LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q5_K_M`, backend `vulkan`, ctx size `524288`, `llamacpp_args="--spec-type none -cb -fa on -b 4096 -ub 1024 --kv-unified --temp 0.6 --top-p 0.95 --top-k 20"`, `save_options=true`
-  - long-context admission baseline: `total_context_tokens=524288`, `long_context_capacity=1` (`-np` 고정 분할을 제거하고 `--kv-unified`를 사용하되, IOP admission은 agent 장문 요청의 동시 prefill 간섭을 막기 위해 1개로 제한한다. `/slots`는 auto slots 4개와 slot `n_ctx=262144`를 보고한다)
+  - load baseline: checkpoint `LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q5_K_M`, backend `vulkan`, ctx size `262144`, `llamacpp_args="--spec-type none -np 1 -cb -fa on -b 4096 -ub 1024 --kv-unified --temp 0.6 --top-p 0.95 --top-k 20"`, `save_options=true`
+  - long-context admission baseline: `total_context_tokens=262144`, `long_context_capacity=1` (IOP의 provider 직렬 admission과 llama-server의 `-np 1`을 일치시켜 agent turn별 prefix cache가 서로 다른 slot에 분산되지 않게 한다. `/slots`는 slot 1개와 `n_ctx=262144`를 보고한다)
   - workspace: `C:/Users/r0bin/iop-field`
 - RTX5090 Lemonade node: `rtx5090-lemonade-node` / `rtx5090-lemonade`
   - SSH/user: `ssh iop-dev-rtx5090`

agent-test/dev/node-smoke.md

@@ -76,8 +76,8 @@ dev-runtime의 실제 4-node 연결을 점검할 때는 원격 runner `ssh toki@
   - served model: `Ornith-1.0-35B-GGUF-llamacpp-tp1-Q5_K_M`
   - capacity baseline: `1` (agent 장문 요청의 provider 독점 실행 기준)
   - priority baseline: `2`
-  - load baseline: checkpoint `LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q5_K_M`, backend `vulkan`, ctx size `524288`, `llamacpp_args="--spec-type none -cb -fa on -b 4096 -ub 1024 --kv-unified --temp 0.6 --top-p 0.95 --top-k 20"`, `save_options=true`
-  - long-context admission baseline: `total_context_tokens=524288`, `long_context_capacity=1` (`-np` 고정 분할을 제거하고 `--kv-unified`를 사용하되, IOP admission은 agent 장문 요청의 동시 prefill 간섭을 막기 위해 1개로 제한한다. `/slots`는 auto slots 4개와 slot `n_ctx=262144`를 보고한다)
+  - load baseline: checkpoint `LordNeel/Ornith-1.0-35B-GGUF-llamacpp-tp1:Q5_K_M`, backend `vulkan`, ctx size `262144`, `llamacpp_args="--spec-type none -np 1 -cb -fa on -b 4096 -ub 1024 --kv-unified --temp 0.6 --top-p 0.95 --top-k 20"`, `save_options=true`
+  - long-context admission baseline: `total_context_tokens=262144`, `long_context_capacity=1` (IOP의 provider 직렬 admission과 llama-server의 `-np 1`을 일치시켜 agent turn별 prefix cache가 서로 다른 slot에 분산되지 않게 한다. `/slots`는 slot 1개와 `n_ctx=262144`를 보고한다)
   - workspace: `C:/Users/r0bin/iop-field`
 - RTX5090 Lemonade node: `rtx5090-lemonade-node` / `rtx5090-lemonade`
   - SSH/user: `ssh iop-dev-rtx5090`

agent-test/inventory-dev.yaml

@@ -1177,13 +1177,14 @@ nodes:
           iop_capacity_guard: 3
           long_context_capacity: 2
           validation_required_after_load: true
-          validation_basis: Same Lemonade llama.cpp backend and current Ornith Q5 runtime confirmed --kv-unified with omitted -np prevents fixed ctx_size/parallel partitioning.
+          validation_basis: This inactive Qwen profile requires separate validation before re-enable; do not derive its parallelism from the current single-slot Ornith profile.
       capacity: 1
       priority: 2
       # Long-context admission policy (maps to edge.yaml nodes[].providers[]).
-      # Ornith Q5 direct runtime keeps ctx_size=524288 and removes fixed -np
-      # partitioning by using llama.cpp unified KV. Do NOT raise ctx_size above 524288.
-      total_context_tokens: 524288
+      # IOP admits one Ornith request at a time, so llama.cpp also uses one slot.
+      # This keeps agent-turn prefix cache on the same slot instead of scattering
+      # it across auto slots. Do NOT raise ctx_size above 262144.
+      total_context_tokens: 262144
       long_context_capacity: 1
       load:
         endpoint: http://192.168.0.59:13305/v1/load
@@ -1196,13 +1197,13 @@ nodes:
         gguf_file_size_bytes: 24729130848
         cache_snapshot_path: C:/Users/r0bin/.cache/huggingface/hub/models--LordNeel--Ornith-1.0-35B-GGUF-llamacpp-tp1/snapshots/c50d5d4407f70e43208dee836c66bb8a05c1be91
         backend: vulkan
-        ctx_size: 524288
-        llamacpp_args: "--spec-type none -cb -fa on -b 4096 -ub 1024 --kv-unified --temp 0.6 --top-p 0.95 --top-k 20"
-        observed_process_args: "--ctx-size 524288 --port 8001 --jinja --context-shift --keep 16 --reasoning-format auto --no-webui --no-mmap -ngl 99 --kv-unified --spec-type none --temp 0.6 --top-k 20 --top-p 0.95 -b 4096 -cb -fa on -ub 1024"
-        observed_total_slots: 4
-        observed_total_ctx_size: 524288
+        ctx_size: 262144
+        llamacpp_args: "--spec-type none -np 1 -cb -fa on -b 4096 -ub 1024 --kv-unified --temp 0.6 --top-p 0.95 --top-k 20"
+        observed_process_args: "--ctx-size 262144 --port 8001 --jinja --context-shift --keep 16 --reasoning-format auto --no-webui --no-mmap -ngl 99 --kv-unified --spec-type none --temp 0.6 --top-k 20 --top-p 0.95 -b 4096 -cb -fa on -np 1 -ub 1024"
+        observed_total_slots: 1
+        observed_total_ctx_size: 262144
         observed_slot_n_ctx: 262144
-        context_per_slot_note: -np is intentionally omitted; llama.cpp auto slots with --kv-unified avoid the prior fixed 524288/3 partition and report 262144-token slot windows backed by shared KV.
+        context_per_slot_note: -np 1 matches the IOP provider capacity and preserves one reusable prefix-cache lineage across agent turns.
         residency:
           observed_at: "2026-07-12"
           process_resident_policy: keep llama-server loaded until explicit lemonade unload or service/process restart
@@ -1262,15 +1263,15 @@ nodes:
         recoverable_backup: C:/Users/r0bin/iop-field/IOP-OnexNode.pre-manual-lemonade-20260725T234232Z.xml
       manual_remote_llm_toggle:
         script: C:/Users/r0bin/iop-field/remote-llm-toggle.ps1
-        script_sha256: cd04150b460da9d3157e9431f0b25f2d80e63f957a7a14448feb6925b3ada11f
+        script_sha256: d1729c7928978d1d547f8ed20f86ef25a75cc4e0228857e332c0530541abd9c7
         log: C:/Users/r0bin/iop-field/onex-remote-llm-toggle.log
         default_action: toggle_by_complete_stack_readiness
         process_start: Win32_Process.Create
         readiness_requires:
           - LemonadeServer.exe running and health status ok
-          - exact Ornith model with Vulkan ctx_size 524288 profile
+          - exact Ornith model with Vulkan ctx_size 262144 and -np 1 profile
           - public listener 0.0.0.0:13305
-          - four llama slots with n_ctx 262144
+          - one llama slot with n_ctx 262144
           - iop-node.exe running and established Edge TCP connection to port 18084
         up_sequence:
           - start LemonadeServer.exe
@@ -1291,14 +1292,14 @@ nodes:
           icon: C:/Users/r0bin/AppData/Roaming/Microsoft/Installer/{221D1879-DDCE-4E14-AC7C-ACA9F084FE21}/LemonadeIcon,0
           boot_autostart: false
         validation:
-          observed_at: "2026-07-26"
+          observed_at: "2026-08-13"
           default_toggle_down: passed
           default_toggle_up: passed
           final_state: ready
           listener_public: passed
           model_profile_valid: passed
           edge_connected: passed
-          slots: 4x262144
+          slots: 1x262144
   - id: rtx5090-lemonade-node
     alias: rtx5090-lemonade
     role: lemonade-provider