inventory_id: inventory-agent
schema_version: 1
last_updated_at: "2026-08-02"

scope:
  type: shared_agent_host_profiles
  description: Agent-specific host configuration, observed defaults, and environment-scoped status. Node, provider, endpoint, workspace, and SSH details remain in the referenced environment inventory.

policy:
  secret_values_tracked: false
  host_connection_values_owned_by: environment_inventory
  provider_runtime_source_of_truth: environment_inventory
  agent_provider_compatibility_observations: allowed
  node_reference_policy: reference_only

source_inventories:
  common: agent-test/inventory.yaml
  dev: agent-test/inventory-dev.yaml
  dev-corp: agent-test/inventory-dev-corp.yaml

environments:
  dev:
    source_inventory: agent-test/inventory-dev.yaml
    agents:
      claude:
        status: not_configured
        note: No Claude host profile is recorded in the dev inventory.
      codex:
        status: node_reference_only
        node_ref: mac-codex-node
        note: The CLI adapter and MLX provider runtime remain owned by the referenced dev node inventory.
      pi:
        status: configured
        host_binding: not_recorded
        observed_at: "2026-07-24"
        config_scope: host_local_pi_agent
        config_dir: /config/.pi/agent
        current_default_provider: iop
        current_default_model: laguna-s:2.1
        current_default_thinking_level: high
        current_default_api: openai-completions
        current_default_base_url: http://toki-labs.com:18083/v1
        current_default_auth_header: true
        sampling_policy:
          explicit_parameters: false
          source: dev_laguna_provider_defaults
          provider_default:
            temperature: 0.7
            top_p: 0.95
            top_k: 20
          omitted_fields:
            - temperature
            - top_p
            - top_k
            - repeat_penalty
          note: Pi omits these fields and the selected GX10 Laguna provider applies the model baseline.
        api_key_value_tracked: false
        endpoint_policy: current default Pi route is IOP Edge provider iop with model laguna-s:2.1. Pi does not bypass Edge to the GX10 vLLM endpoint.
        local_pi_providers_at_observation:
          - iop
        direct_providers_removed_at_observation:
          - iop-gemma
          - ornith-direct
          - ornith-lemonade
        iop_provider_models_at_observation:
          - qwen3.6:35b
          - ornith:35b
          - ornith-fast
          - laguna-s:2.1
        pi_model_parameters:
          provider: iop
          model_id: laguna-s:2.1
          display_name: IOP Poolside Laguna S 2.1
          api: openai-completions
          context_window: 262144
          max_tokens: 65536
          reasoning: true
          thinking_level: high
          thinking_format: chat-template
          enable_thinking_source: thinking.enabled
          preserve_thinking: true
        current_laguna_parameter_alignment:
          model_alias: laguna-s:2.1
          pi_context_window: 262144
          edge_context_window: 262144
          pi_max_tokens: 65536
          edge_default_max_tokens: 65536
          pi_output_budget_within_edge_limit: true
          edge_model_group_registered: true
          edge_group_min_max_tokens: 0
          gx10_edge_capacity: 4
          gx10_long_context_capacity: 1
          reasoning_parser: poolside_v1
          tool_call_parser: poolside_v1
          quantization: nvfp4
          dflash_speculative_tokens: 7
          chat_template_container_path: /run/iop/laguna-s-2.1-thinking.jinja
          thinking_generation_prefix: "<think>\n"
          note: The active GX10 runtime uses the official Laguna S 2.1 NVFP4 checkpoint and quantization-matched DFlash NVFP4 draft. Its local chat-template override adds a newline after the generation-prefix think tag so enabled requests do not immediately emit the closing think tag.
        qwen_runtime_parameter_alignment:
          alignment_policy: Pi model parameters must be kept in sync with the Edge model catalog and each provider runtime profile. Do not optimize or debug Pi behavior from the endpoint URL alone; verify the alias-to-served-model mapping, context window, max token budget, thinking/reasoning parser, chat template kwargs, and provider capacity/sequence limits together.
          common_requirements:
            model_alias: qwen3.6:35b
            pi_context_window: 262144
            edge_context_window: 262144
            pi_max_tokens: 32768
            edge_default_max_tokens: 32768
            edge_min_max_tokens: 32768
            pi_reasoning: true
            edge_reasoning_policy: model_native_thinking
            required_template_policy: Qwen providers keep default_chat_template_kwargs.enable_thinking=true
            required_reasoning_parser: qwen3
          engine_matrix:
            previous_gx10-vllm:
              status: historical_replaced_by_laguna_s_2_1
              runtime_type: vllm
              served_model: nvidia/Qwen3.6-35B-A3B-NVFP4
              context_match: pi contextWindow 262144 maps to vLLM max_model_len 262144
              output_budget_match: pi maxTokens 32768 maps to provider default_max_tokens 32768
              thinking_match: pi reasoning=true and thinking_level=high map to reasoning_parser=qwen3 and default_chat_template_kwargs.enable_thinking=true
              concurrency_match: provider capacity 4 maps to runtime max_num_seqs 4
              tool_parser_profile: qwen3_xml
            mac-mlx-vllm:
              runtime_type: vllm-mlx
              served_model: mlx-community/Qwen3.6-35B-A3B-4bit
              context_match: pi contextWindow 262144 maps to vLLM-MLX max_request_tokens 262144 and max_kv_size 262144
              output_budget_match: pi maxTokens 32768 maps to provider default_max_tokens 32768
              thinking_match: pi reasoning=true and thinking_level=high map to reasoning_parser=qwen3 and default_chat_template_kwargs.enable_thinking=true
              concurrency_match: provider capacity 2 maps to runtime max_num_seqs 2
              tool_parser_profile: qwen
            onexplayer-lemonade:
              runtime_type: lemonade
              served_model: Qwen3.6-35B-A3B-MTP-GGUF
              current_runtime_override_2026_07_12: OneXPlayer Lemonade was switched to Ornith-1.0-35B-GGUF-llamacpp-tp1-Q5_K_M for direct Ornith validation; it is not a valid Qwen provider-pool member until Edge provider config is updated.
              context_match: Qwen should use the same Lemonade unified KV profile when re-enabled; keep total ctx_size 524288, omit -np, and pass --kv-unified to avoid the prior fixed 174848-token slot partitioning.
              output_budget_match: pi maxTokens 32768 maps to load default_max_tokens 32768
              thinking_match: pi reasoning=true and thinking_level=high uses model-native thinking; Lemonade load keeps MTP disabled and tool_choice_auto_verified=true
              concurrency_match: provider capacity remains capped at 3 for IOP admission; with unified KV, Lemonade auto slots may report 4 runtime slots, so Edge admission must remain the concurrency guard.
              tool_parser_profile: lemonade_qwen_tool_choice_auto_verified
              qwen_reenable_profile:
                status: applicable_not_reloaded_while_ornith_q5_is_active
                ctx_size: 524288
                llamacpp_args: "--spec-type none -cb -fa on -b 4096 -ub 1024 --kv-unified"
                removed_args: "-np 3"
                expected_slot_n_ctx: 262144
                expected_capacity: 3
                expected_long_context_capacity: 2
                validation_basis: Same Lemonade llama.cpp backend and current Ornith Q5 runtime validated --kv-unified with auto slots reporting n_ctx 262144; Qwen still needs smoke validation after it is reloaded.
          separation_note: These alignment rules are for the dev Qwen3.6 provider pool only. Gemma4 and DiffusionGemma use separate provider/model profiles and must not inherit Qwen parser/template/context assumptions.
        provider_passthrough:
          default: pure_passthrough
          selector: none; request model/provider capability determines passthrough vs normalized execution
          verification: Chat Completions streaming probe returned HTTP 200 through the provider tunnel with provider body preserved and no IOP response envelope injected.
        previous_qwen_provider_pool_routing:
          status: historical_gx10_and_onexplayer_no_longer_in_qwen_group
          observed_at: "2026-07-09"
          caller_shape: Pi-compatible OpenAI Chat Completions streaming requests to provider/model iop/qwen3.6:35b
          concurrent_requests: 10
          peak_total_in_flight: 9
          peak_total_queued_snapshot_units: 3
          final_recovery: in_flight_0_queued_0
          provider_peaks:
            gx10-vllm:
              runtime_type: vllm
              served_model: nvidia/Qwen3.6-35B-A3B-NVFP4
              capacity: 4
              max_in_flight: 4
              max_queued: 1
            mac-mlx-vllm:
              runtime_type: vllm-mlx
              served_model: mlx-community/Qwen3.6-35B-A3B-4bit
              capacity: 2
              max_in_flight: 2
              max_queued: 1
            onexplayer-lemonade:
              runtime_type: lemonade
              served_model: Qwen3.6-35B-A3B-MTP-GGUF
              capacity: 3
              max_in_flight: 3
              max_queued: 1
        non_default_local_provider:
          provider: iop-gemma
          status: removed_from_pi_models_json_2026_07_12
          api: openai-completions
          base_url: http://192.168.0.91:8002/v1
          served_model: nvidia/diffusiongemma-26B-A4B-it-NVFP4
          reasoning: false
          current_runtime_status: stopped_2026_07_12_endpoint_now_serves_laguna_s_2_1
        spark_laguna_direct_profile:
          observed_at: "2026-07-24"
          provider: gx10-vllm
          status: active_through_iop_edge
          family: poolside_laguna
          api: openai-completions
          base_url: http://192.168.0.91:8001/v1
          model_id: laguna-s:2.1
          display_name: Poolside Laguna S 2.1 NVFP4
          context_window: 262144
          max_tokens: 65536
          reasoning: true
          endpoint_policy: Pi connects through IOP Edge under laguna-s:2.1 and does not use the direct GX10 endpoint.
          api_key_value_tracked: false
          pi_current_default_at_observation:
            default_provider: iop
            default_model: laguna-s:2.1
            default_api: openai-completions
            default_base_url: http://toki-labs.com:18083/v1
            default_thinking_level: high
            thinking_format: chat-template
            enable_thinking_source: thinking.enabled
            preserve_thinking: true
          runtime_summary:
            host: toki@192.168.0.91
            container_name: iop-vllm-laguna-s21
            docker_image: iop-vllm-laguna-s21:v0.25.1-cu130
            docker_image_id: sha256:4eb2bb71c0ffc6ceb54dd3381030169f5e24ac1477fb1faa1ba90e57e6996331
            vllm_version: 0.25.1
            torch_version: 2.11.0+cu130
            transformers_version: 5.12.1
            compressed_tensors_version: 0.17.0
            flashinfer_python_version: 0.6.15.dev20260712
            gpu: NVIDIA GB10
            endpoint: http://192.168.0.91:8001/v1
            hf_model: poolside/Laguna-S-2.1-NVFP4
            hf_url: https://huggingface.co/poolside/Laguna-S-2.1-NVFP4
            hf_revision: 07614121b31898586430f189d27a25a0be310843
            hf_cache_snapshot_path: /models/.cache/huggingface/hub/models--poolside--Laguna-S-2.1-NVFP4/snapshots/07614121b31898586430f189d27a25a0be310843
            draft_model: poolside/Laguna-S-2.1-DFlash-NVFP4
            draft_url: https://huggingface.co/poolside/Laguna-S-2.1-DFlash-NVFP4
            draft_revision: 723794750422b3efbf3a7b3af76dffb4ba035943
            served_model_name: laguna-s:2.1
            quantization: nvfp4
            vllm_quantization_backend: compressed-tensors
            dtype: bfloat16
            max_model_len: 262144
            max_num_seqs: 4
            gpu_memory_utilization: 0.70
            enable_prefix_caching: true
            enable_chunked_prefill: true
            enable_auto_tool_choice: true
            tool_call_parser: poolside_v1
            reasoning_parser: poolside_v1
            chat_template_host_path: /home/toki/iop-gx10-vllm/laguna-s-2.1-thinking.jinja
            chat_template_container_path: /run/iop/laguna-s-2.1-thinking.jinja
            thinking_generation_prefix: "<think>\n"
            default_chat_template_kwargs:
              enable_thinking: true
            generation_config_override:
              temperature: 0.7
              top_p: 0.95
            speculative_config:
              method: dflash
              num_speculative_tokens: 7
              model: poolside/Laguna-S-2.1-DFlash-NVFP4
            attention_backend: FLASHINFER
            kv_cache_dtype: float8_e4m3fn
            available_kv_cache_memory_gib: 13.08
            gpu_kv_cache_tokens: 373711
            max_concurrency_for_262144_token_requests: 1.43
            docker_runtime:
              recreated_at: "2026-07-24"
              host_port: 8001
              container_port: 8000
              network_mode: bridge
              ipc_mode: host
              restart_policy: "no"
              bind_mounts:
                /home/toki/Data/models: /models
                /home/toki/Data/vllm/cache/laguna-s21: /root/.cache
                /home/toki/iop-gx10-vllm/laguna-s-2.1-thinking.jinja: /run/iop/laguna-s-2.1-thinking.jinja
          smoke:
            direct_models: passed
            direct_chat_completions: passed
            edge_chat_completions: passed
            pi_agentic_tool_reasoning_stream: passed
            reasoning_field: reasoning
            pi_high_result: thinking_start, thinking_delta, and thinking_end observed
            pi_off_result: no thinking event and final text observed
            simple_no_tool_reasoning_note: The previous stock generation prefix closed the think block immediately. The current local template uses a trailing newline and a simple Pi high request emits a non-empty thinking block.
        previous_spark_ornith_direct_profile:
          observed_at: "2026-07-12"
          provider: ornith-direct
          status: historical_runtime_replaced_by_laguna_s_2_1
          family: spark_ornith
          api: openai-completions
          base_url: http://192.168.0.91:8001/v1
          model_id: ornith:35b
          display_name: Ornith 1.0 35B FP8 Direct vLLM
          context_window: 262144
          max_tokens: 32768
          reasoning: true
          endpoint_policy: Historical observation only. The endpoint now serves laguna-s:2.1 through IOP Edge.
          api_key_value_tracked: false
          pi_current_default_at_observation:
            default_provider: iop
            default_model: ornith:35b
            default_api: openai-completions
            default_base_url: http://toki-labs.com:18083/v1
          qwen_parameter_alignment:
            pi_context_window: 262144
            pi_max_tokens: 32768
            context_match: matches the dev Qwen Pi contextWindow and vLLM max_model_len value
            output_budget_match: matches the dev Qwen Pi maxTokens/default_max_tokens value
          runtime_summary:
            host: toki@192.168.0.91
            container_name: iop-vllm-ornith35b-fp8
            docker_image: vllm/vllm-openai:nightly-aarch64
            docker_image_id: sha256:a720df3e84a89d7db47a3b7a0511cb5b312e203fc4956f7493df248299267a6f
            vllm_image_tag_env: vllm/vllm-openai:nightly-a346d589f5932d4234bf5bf8718f10e26d187021
            vllm_version: 0.23.1rc1.dev223+ga346d589f
            vllm_build_commit: a346d589f5932d4234bf5bf8718f10e26d187021
            vllm_build_url: https://buildkite.com/vllm/release-v2/builds/2923
            torch_version: 2.11.0+cu130
            transformers_version: 5.12.1
            compressed_tensors_version: 0.17.0
            flashinfer_python_version: 0.6.12
            cuda_version_env: 13.0.2
            gpu: NVIDIA GB10
            nvidia_driver_version: 580.126.09
            endpoint: http://192.168.0.91:8001/v1
            hf_model: deepreinforce-ai/Ornith-1.0-35B-FP8
            hf_url: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-FP8
            hf_revision: 1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
            hf_ref: main
            revision_argument: not_set_uses_repo_default_main_at_container_start
            tokenizer_revision_argument: not_set_uses_model_revision
            hf_home: /models/.cache/huggingface
            hf_cache_snapshot_path: /models/.cache/huggingface/hub/models--deepreinforce-ai--Ornith-1.0-35B-FP8/snapshots/1ab57ce0b44950e498a88756f40ad1ed4d0f30ca
            served_model_name: ornith:35b
            openai_models_root: deepreinforce-ai/Ornith-1.0-35B-FP8
            openai_models_max_model_len: 262144
            quantization: fp8
            vllm_quantization_backend: compressed-tensors
            model_type: qwen3_5_moe
            model_architecture: Qwen3_5MoeForConditionalGeneration
            quantization_config_source: model config.json compressed-tensors W8A8 FP8, weight channel strategy, input activation token strategy, linear_attn/embed/lm_head/shared gates ignored
            dtype: bfloat16
            max_model_len: 262144
            max_num_seqs: 4
            max_num_batched_tokens: vllm_default_not_overridden
            gpu_memory_utilization: 0.50
            enable_prefix_caching: true
            enable_chunked_prefill: true
            async_scheduling: true
            tensor_parallel_size: 1
            pipeline_parallel_size: 1
            data_parallel_size: 1
            load_format: auto
            download_dir: null
            kv_cache_dtype: auto
            enforce_eager: false
            seed: 0
            enable_auto_tool_choice: true
            tool_call_parser: qwen3_xml
            reasoning_parser: qwen3
            reasoning_parser_enable_in_reasoning: false
            trust_remote_code: true
            language_model_only: true
            attention_backend: FLASH_ATTN
            sampling_backend: FlashInfer top-p/top-k
            fp8_linear_kernel: CutlassFP8ScaledMMLinearKernel for CompressedTensorsW8A8Fp8
            fp8_moe_backend: TRITON
            generation_config_override:
              temperature: 0.6
              top_k: 20
              top_p: 0.95
              eos_token_id:
                - 248046
                - 248044
              bos_token_id: 248044
            docker_runtime:
              created_at: "2026-07-12T08:41:04Z"
              entrypoint:
                - vllm
                - serve
              container_port: 8000
              host_port: 8001
              network_mode: bridge
              ipc_mode: private
              shm_size_bytes: 67108864
              restart_policy: "no"
              gpu_device_request: all
              bind_mounts:
                /home/toki/Data/models: /models
                /home/toki/Data/vllm/templates: /templates
            model_load_memory_gib: 34.43
            model_load_seconds: 196.929359
            weight_download_seconds: not_observed_cache_hit_restart
            cuda_graph_memory_estimated_gib: 0.13
            cuda_graph_pool_memory_actual_gib: 0.07
            available_kv_cache_memory_gib: 20.79
            gpu_kv_cache_tokens: 1060912
            max_concurrency_for_262144_token_requests: 4.05
            startup_warnings:
              - vLLM command does not pin --revision; the recorded hf_revision is the downloaded snapshot observed in cache.
              - Prefix caching in Mamba cache align mode is experimental for this architecture.
              - Default MoE config for NVIDIA_GB10 FP8 was not found; vLLM used default MoE config, which may affect performance.
              - Model generation_config overrides vLLM defaults unless callers provide sampling params or vLLM is relaunched with --generation-config vllm.
          official_4bit_gguf_status:
            hf_model: deepreinforce-ai/Ornith-1.0-35B-GGUF
            hf_url: https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF
            hf_revision: c2e1703039380de4ce6820e97afd185682d3c16c
            hf_ref: main
            hf_cache_snapshot_path: /models/.cache/huggingface/hub/models--deepreinforce-ai--Ornith-1.0-35B-GGUF/snapshots/c2e1703039380de4ce6820e97afd185682d3c16c
            file: ornith-1.0-35b-Q4_K_M.gguf
            status: not_active
            reason: current vLLM GGUF plugin path exposed /v1/models but failed semantic generation smoke; active working runtime uses the official FP8 vLLM model instead.
          smoke:
            english_final_answer: passed
            korean_final_answer: passed
            pi_direct_cli: passed
            output_throughput:
              method: completion_tokens divided by end-to-end request wall time, max_tokens=768
              average_completion_tok_s: 29.8
              run_completion_tok_s:
                - 29.65
                - 30.62
                - 29.15
              note: vLLM logs showed aggregate generation throughput around 50-61 tok/s with two running requests.
        ornith_lemonade_direct_profile:
          observed_at: "2026-07-12"
          provider: ornith-lemonade
          status: removed_from_pi_models_json_2026_07_12_runtime_still_active_as_onexplayer_iop_ornith_provider
          family: spark_ornith
          api: openai-completions
          base_url: http://192.168.0.59:13305/v1
          model_id: Ornith-1.0-35B-GGUF-llamacpp-tp1-Q5_K_M
          display_name: Ornith 1.0 35B Q5 Direct Lemonade
          context_window: 262144
          max_tokens: 32768
          reasoning: true
          config_file: /config/.pi/agent/models.json
          default_profile_changed: true
          pi_default_provider_after_add: iop
          pi_default_model_after_add: ornith:35b
          endpoint_policy: Pi no longer connects directly to the OneXPlayer Lemonade OpenAI-compatible endpoint. This runtime remains reachable through IOP Edge under ornith:35b.
          api_key_value_tracked: false
          runtime_alignment:
            lemonade_runtime_model: Ornith-1.0-35B-GGUF-llamacpp-tp1-Q5_K_M
            lemonade_response_model: ornith-1.0-35b-Q5_K_M.gguf
            quantization: Q5_K_M
            ctx_size: 524288
            kv_policy: unified_kv_with_np_omitted
            observed_slot_n_ctx: 262144
            iop_capacity_guard: 3
            long_context_capacity: 2
          smoke:
            endpoint_direct_chat_completions: passed
            request_model: Ornith-1.0-35B-GGUF-llamacpp-tp1-Q5_K_M
            response_model: ornith-1.0-35b-Q5_K_M.gguf
            finish_reason: stop
            content: "4"
            completion_tokens: 2
        separation_note: The host Pi default is Laguna S 2.1 through IOP Edge. Keep Laguna, Qwen, Ornith, and dev-corp Gemma parser/template/runtime settings separate.
      agy:
        status: not_configured
        note: No agy host profile is recorded in the dev inventory.
  dev-corp:
    source_inventory: agent-test/inventory-dev-corp.yaml
    agents:
      claude:
        status: not_configured
      codex:
        status: not_configured
      pi:
        status: not_configured
      agy:
        status: not_configured