diff --git a/agent-ops/skills/project/dev-corp-runtime-deploy/SKILL.md b/agent-ops/skills/project/dev-corp-runtime-deploy/SKILL.md index 3896439..a74e443 100644 --- a/agent-ops/skills/project/dev-corp-runtime-deploy/SKILL.md +++ b/agent-ops/skills/project/dev-corp-runtime-deploy/SKILL.md @@ -60,7 +60,7 @@ dev-corp provider pool을 현재 dev-runtime과 같은 구조로 배포한다. - 2026-07-08 재확인 기준 DGX Spark 02는 Docker `vllm-gemma4` image `vllm/vllm-openai:v0.24.0`, host/container `8004`, text-only/eager profile과 `default_chat_template_kwargs.enable_thinking=true`로 동작하며 mac-mini와 node-local `/health`, `/v1/models`, 직접 API auto/streaming tool-call smoke를 통과했다. startup log에서 GPU KV cache `1,452,633` tokens, full-context concurrency `5.54x`를 확인했다. - 2026-07-02 mac-mini native Control Plane `18002/19004/19005` 관측값은 historical evidence다. 2026-07-09 현재 dev-corp Edge source of truth는 public `digitalplatform-iop.cloud`이고, current runner에서 public host SSH와 public Control Plane status 접근은 확인되지 않았다. - 2026-07-09 기준 dev-corp provider-pool Edge OpenAI-compatible capacity smoke 표준은 public `http://digitalplatform-iop.cloud:18086/v1/chat/completions` 15개 동시 요청이다. `/v1/responses`는 OpenAI-compatible provider model group raw passthrough parity 전까지 미지원이므로 성공 기준에서 제외한다. -- 2026-07-09 public Edge 재연결 검증에서 DGX Spark 01/02와 Mac Studio node를 `digitalplatform-iop.cloud:18087`로 변경한 뒤 `/v1/chat/completions` 15개 동시 요청이 15/15 성공했다. 같은 날 current passthrough source로 public Edge를 재빌드/재시작한 뒤 기본 streaming `/v1/chat/completions` 15/15에서 provider reasoning delta가 유지됐고 transformed `chatcmpl-manual` ID는 0/15였다. 원격 evidence는 `build/dev-corp-runtime/logs/public_passthrough_chat_15_20260709_180115.json`이다. 2026-07-08 `/v1/responses` 통과 기록은 mac-mini provider-pool runtime 기준 legacy evidence로만 본다. +- 2026-07-09 public Edge 재연결 검증에서 DGX Spark 01/02와 Mac Studio node를 `digitalplatform-iop.cloud:18087`로 변경한 뒤 `/v1/chat/completions` 15개 동시 요청이 15/15 성공했다. 같은 날 current passthrough source로 public Edge를 재빌드/재시작하고 최신 node 바이너리를 DGX Spark 01/02와 Mac Studio에 배포한 뒤 기본 streaming `/v1/chat/completions` 15/15에서 provider reasoning delta가 유지됐고 transformed `chatcmpl-manual` ID는 0/15였다. 원격 evidence는 `build/dev-corp-runtime/logs/public_latest_edge_node_chat_15_20260709_181222.json`이다. 2026-07-08 `/v1/responses` 통과 기록은 mac-mini provider-pool runtime 기준 legacy evidence로만 본다. ## 실행 절차 diff --git a/agent-test/dev-corp/edge-smoke.md b/agent-test/dev-corp/edge-smoke.md index d4463c5..95cde38 100644 --- a/agent-test/dev-corp/edge-smoke.md +++ b/agent-test/dev-corp/edge-smoke.md @@ -108,6 +108,7 @@ Mac Studio의 `http://192.168.2.3:8005/v1` mlx-vlm DiffusionGemma endpoint는 - mac-mini checkout/runtime is a runner and must not be used as Edge source of truth unless explicitly doing a local-runner comparison. - On 2026-07-09 the three provider nodes were moved from mac-mini/reverse-tunnel Edge addresses to `digitalplatform-iop.cloud:18087`, and public `/v1/chat/completions` 15-concurrency smoke passed 15/15. - On 2026-07-09 after rebuilding the public Edge from the current passthrough source, default streaming `/v1/chat/completions` preserved provider reasoning deltas for 15/15 concurrent requests; transformed `chatcmpl-manual` IDs were 0/15. Evidence: `build/dev-corp-runtime/logs/public_passthrough_chat_15_20260709_180115.json`. +- On 2026-07-09 after deploying latest node binaries to DGX Spark 01/02 and Mac Studio, public streaming `/v1/chat/completions` again passed 15/15 with provider reasoning deltas preserved and transformed `chatcmpl-manual` IDs 0/15. Evidence: `build/dev-corp-runtime/logs/public_latest_edge_node_chat_15_20260709_181222.json`. - Mac Studio provider catalog `type`은 최신 config validator 기준으로 `openai_compat`를 사용한다. 실제 provider runtime은 vLLM-MLX이고 `runtime_type: vllm-mlx`로 추적한다. - `/v1/chat/completions` capacity smoke 표준: 15개 동시 요청을 public `http://digitalplatform-iop.cloud:18086/v1`로 보낸다. 2026-07-09 public Edge 재연결 검증에서는 15/15 성공했다. - `/v1/responses`는 OpenAI-compatible provider model group raw passthrough parity 전까지 미지원이므로 provider-pool capacity 성공 기준에서 제외한다. diff --git a/agent-test/dev-corp/inventory.yaml b/agent-test/dev-corp/inventory.yaml index 93394b2..596737f 100644 --- a/agent-test/dev-corp/inventory.yaml +++ b/agent-test/dev-corp/inventory.yaml @@ -57,10 +57,25 @@ edge: public_chat_completions_15: ok: 15 concurrent_requests: 15 - elapsed_sec: 5.721 + elapsed_sec: 5.678 passthrough_reasoning_stream_seen: 15 transformed_manual_id_count: 0 - remote_log: build/dev-corp-runtime/logs/public_passthrough_chat_15_20260709_180115.json + remote_log: build/dev-corp-runtime/logs/public_latest_edge_node_chat_15_20260709_181222.json + latest_node_binary_deploy: + observed_at: "2026-07-09T18:12:22+09:00" + source_ref: e8c240ea23a29f1568326b6d162913863b3dca33 + linux_arm64_sha256: 02441a57f97238bd650a568896c876fb32c94fcace0073f6068509ef90ac4327 + darwin_arm64_sha256: 95c59ee0dacb134dc2c6d46fb34f2dac49c33d7da38abe96157583822364f57a + nodes: + corp-dgx-spark-01-vllm-node: + pid_after_restart: 545848 + binary_sha256: 02441a57f97238bd650a568896c876fb32c94fcace0073f6068509ef90ac4327 + corp-dgx-spark-02-vllm-node: + pid_after_restart: 701517 + binary_sha256: 02441a57f97238bd650a568896c876fb32c94fcace0073f6068509ef90ac4327 + corp-mac-studio-mlx-vllm-node: + pid_after_restart: 87325 + binary_sha256: 95c59ee0dacb134dc2c6d46fb34f2dac49c33d7da38abe96157583822364f57a note: public /v1/responses remains unsupported for OpenAI-compatible provider model groups until raw passthrough parity is implemented; use /v1/chat/completions for provider-pool capacity smoke. latest_bootstrap_domain_fix: observed_at: "2026-07-09" @@ -248,7 +263,7 @@ model: route: public_digitalplatform_edge host: digitalplatform-iop.cloud edge_addr: digitalplatform-iop.cloud:18087 - source_ref: public_edge_source_ref_not_confirmed_by_current_runner + source_ref: e8c240ea23a29f1568326b6d162913863b3dca33 default_thinking_token_budget: 1024 control_plane_enabled: unknown control_plane_status_url: http://digitalplatform-iop.cloud:18002/edges/dev-corp-edge/status @@ -256,7 +271,7 @@ model: capacity_snapshot_note: public Control Plane status was not accessible from the current runner; HTTP 15/15 smoke and node connection logs are current evidence, while in_flight/queued snapshot evidence remains legacy 2026-07-08 mac-mini runtime data. runtime: runner_checkout: /Users/fe/agent-work/iop-dev-corp - remote_log: build/dev-corp-runtime/logs/public_domain_chat_15_20260709_172253.json + remote_log: build/dev-corp-runtime/logs/public_latest_edge_node_chat_15_20260709_181222.json node_connection: node_edge_addr: digitalplatform-iop.cloud:18087 moved_from: @@ -271,9 +286,10 @@ model: ok: 15 timeout_errors: 0 http_errors: 0 - elapsed_sec: 25.516 - request_median_sec: 22.933 - text_length_median: 2338 + elapsed_sec: 5.678 + request_median_sec: 2.98 + passthrough_reasoning_stream_seen: 15 + transformed_manual_id_count: 0 responses: supported: false observed_http_status: 400