nsaspy/prolog-rlm
1
0
Fork 0
Code Issues 83 Pull requests 10 Projects Releases Packages Wiki Activity Actions

[integration][auto-dig] actor failure in run 33259315535 #314

New issue
Closed
opened 2026-09-02 17:25:37 +00:00 by nsaspy · 1 comment
nsaspy commented 2026-09-02 17:25:37 +00:00
Owner
Copy link

Auto-Dig integration failure diagnostics

Sanitized failure diagnostics

Summary: phase=native_call kind=malformed_arguments message=native call batch failed preflight model_calls=1 prompt_tokens=2812 completion_tokens=181 total_tokens=2993 cost_usd=0.00092005

Structured Prolog-RLM error

{
  "cause": {
    "detail": {
      "$term": "unexpected_fields",
      "args": [
        [
          "index"
        ]
      ]
    },
    "kind": "malformed_arguments",
    "message": "native context arguments are malformed",
    "phase": "schema"
  },
  "context_calls": 0,
  "iterations": 1,
  "kind": "malformed_arguments",
  "message": "native call batch failed preflight",
  "model_responses": [
    {
      "assistant": {
        "content": "",
        "reasoning": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.",
        "reasoning_details": [
          {
            "format": "azure-openai-responses-v1",
            "index": 0,
            "summary": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.",
            "type": "reasoning.summary"
          },
          {
            "data": "gAAAAABqkvWDW1JvUohGo7Hyx33TUJCq_CZHfbwffH8ic7JjhBeZTEMLmYQ9WyFTJqjXhZGirPCXRm25BxYUUH3JWgpmJVy5vUSdMqOwCz5fZAlQfxdOjUiBk8xb9kbdWWreJkza7RUh2OP3KH0PyleIysz5SNJKUlorTxWUFOk9HNYM15vz_WWP5RyO10--jC33hlxEP25JQUFFK5rKRM2lWeiXhN_f3aPw23viZZK-LR03SLFZr8x6j4lzROHC4bro23wCiEwokt0jq0iSSHGTFEbZ1ZH4lsOs_tOei2_wozilUWtuJgCDqAxrqk-ehOnnn7ZUYREaWQpN6mwNwsCwIPnN6aeo5liMvBJW4myIR80tq2JG31F4BpO2DHO-S2riz6er5JxyNMd-aqMExM3Bp7MdvsvEoXFDMDVSm0RbF7MX9-c16MUzsMkbFDanJ-ZL4IM_EB-aaAtHm8sE7TDUzaUGOimldL0RIwGGubkelAf3sHSR0iQy4k9T0b3TYlK4tiukzN51jdt2jDRBkh7oHjcV-F2t4aNMHnRRRWBtLdkje3IYggxMNX7UX5xb74krHLIQCo7LwGwVUEuqz_91jkemzOeacXPQVSm77hxqif-TtX-HyiL0-Zyg-hMlC8PiF3s_JoNttLvPfzXB-PvwPh33uyEt51WH_HpxFEvwWs-6Lql2EllIQDQME7lN9YgV3xIt6VYPvWDop-ygETfo32JCHi271k7IhjObWuxL9pAYfS0Ynhry9s2MplbSXBpzNlrhsxWznyO_ljg7NowLX0JgrmZmlEcOF42XBEefrJhKSrW9m6Pao7Jm7tWbfaZwRkQkXsdLfQwU_DtA5jRlJvBhiw5P9uFMcAEzhJ1XGnIyHY68py6cAJsJWxshIGVwg0yzG2baCrBaW9Wrz28oCmhbU0hcVcxzRgvXhtix68W1p-Rg7AGuQFzeHV_CSrrPXM9K4-ZYNXjihKYkyz7luxeYe8lKhYGJzImBYNpJbmMxoenjwO9Ju38Y0zlGpVwN7MbeZMaSxVW01fCEGjv6O5K7nvT8w7FwU_-qhz5vWRQVYnu269-97i7TWOtGqZRR0lxx1VXmQH8XGhavS5bpoN_YUH0whoyY6cYmES34j9Bo4ee-gGEforGXx-koYIllpRNBsq8_PN0rAaIKyn1YdTR1OXwl4wrKnbgWh-HfFy4A0iPo59J8XLBHpKgrafnJszEAJTnkRAGINBPLaO9w1hTXG6hTVJapZUXBkcxF4f5B55K4kbC8cLLY8pNgbNwSH1i2xN-s_mFjJD9z8N0ftIt_PnHvF9VLkwx0IQ6lt529xaA3pbWM-5TM9lcy7k4M03HuR-yE.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9",
            "format": "azure-openai-responses-v1",
            "id": "rs_0f596b490682313b016a92f5814294819090832d9cf8234822",
            "index": 1,
            "type": "reasoning.encrypted"
          }
        ],
        "role": "assistant",
        "tool_calls": [
          {
            "function": {
              "arguments": "{\"context\":\"input\",\"selector\":{\"count\":20,\"index\":0,\"type\":\"head\"}}",
              "name": "context_peek"
            },
            "id": "call_kWpAixU1PU2hhTf22WWzrjXV",
            "index": 0,
            "type": "function"
          },
          {
            "function": {
              "arguments": "{\"context\":\"input\",\"selector\":{\"count\":10,\"index\":0,\"type\":\"tail\"}}",
              "name": "context_peek"
            },
            "id": "call_pywO74QJCdIEkwCmgVGYKYXW",
            "index": 1,
            "type": "function"
          },
          {
            "function": {
              "arguments": "{\"context\":\"input\",\"selector\":{\"count\":1,\"index\":0,\"type\":\"metadata\"}}",
              "name": "context_peek"
            },
            "id": "call_rG9RqsWR8tja5EEFvfVCWzT5",
            "index": 2,
            "type": "function"
          }
        ]
      },
      "finish_reason": "tool_calls",
      "metadata": {
        "http_status": 200,
        "provider": "openrouter",
        "response_received": true
      },
      "provider": "openrouter",
      "reasoning": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.",
      "reasoning_details": [
        {
          "format": "azure-openai-responses-v1",
          "index": 0,
          "summary": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.",
          "type": "reasoning.summary"
        },
        {
          "data": "gAAAAABqkvWDW1JvUohGo7Hyx33TUJCq_CZHfbwffH8ic7JjhBeZTEMLmYQ9WyFTJqjXhZGirPCXRm25BxYUUH3JWgpmJVy5vUSdMqOwCz5fZAlQfxdOjUiBk8xb9kbdWWreJkza7RUh2OP3KH0PyleIysz5SNJKUlorTxWUFOk9HNYM15vz_WWP5RyO10--jC33hlxEP25JQUFFK5rKRM2lWeiXhN_f3aPw23viZZK-LR03SLFZr8x6j4lzROHC4bro23wCiEwokt0jq0iSSHGTFEbZ1ZH4lsOs_tOei2_wozilUWtuJgCDqAxrqk-ehOnnn7ZUYREaWQpN6mwNwsCwIPnN6aeo5liMvBJW4myIR80tq2JG31F4BpO2DHO-S2riz6er5JxyNMd-aqMExM3Bp7MdvsvEoXFDMDVSm0RbF7MX9-c16MUzsMkbFDanJ-ZL4IM_EB-aaAtHm8sE7TDUzaUGOimldL0RIwGGubkelAf3sHSR0iQy4k9T0b3TYlK4tiukzN51jdt2jDRBkh7oHjcV-F2t4aNMHnRRRWBtLdkje3IYggxMNX7UX5xb74krHLIQCo7LwGwVUEuqz_91jkemzOeacXPQVSm77hxqif-TtX-HyiL0-Zyg-hMlC8PiF3s_JoNttLvPfzXB-PvwPh33uyEt51WH_HpxFEvwWs-6Lql2EllIQDQME7lN9YgV3xIt6VYPvWDop-ygETfo32JCHi271k7IhjObWuxL9pAYfS0Ynhry9s2MplbSXBpzNlrhsxWznyO_ljg7NowLX0JgrmZmlEcOF42XBEefrJhKSrW9m6Pao7Jm7tWbfaZwRkQkXsdLfQwU_DtA5jRlJvBhiw5P9uFMcAEzhJ1XGnIyHY68py6cAJsJWxshIGVwg0yzG2baCrBaW9Wrz28oCmhbU0hcVcxzRgvXhtix68W1p-Rg7AGuQFzeHV_CSrrPXM9K4-ZYNXjihKYkyz7luxeYe8lKhYGJzImBYNpJbmMxoenjwO9Ju38Y0zlGpVwN7MbeZMaSxVW01fCEGjv6O5K7nvT8w7FwU_-qhz5vWRQVYnu269-97i7TWOtGqZRR0lxx1VXmQH8XGhavS5bpoN_YUH0whoyY6cYmES34j9Bo4ee-gGEforGXx-koYIllpRNBsq8_PN0rAaIKyn1YdTR1OXwl4wrKnbgWh-HfFy4A0iPo59J8XLBHpKgrafnJszEAJTnkRAGINBPLaO9w1hTXG6hTVJapZUXBkcxF4f5B55K4kbC8cLLY8pNgbNwSH1i2xN-s_mFjJD9z8N0ftIt_PnHvF9VLkwx0IQ6lt529xaA3pbWM-5TM9lcy7k4M03HuR-yE.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9",
          "format": "azure-openai-responses-v1",
          "id": "rs_0f596b490682313b016a92f5814294819090832d9cf8234822",
          "index": 1,
          "type": "reasoning.encrypted"
        }
      ],
      "requested_model": "openai/gpt-5.6-luna",
      "response_id": "gen-1788015999-ffnAr3BC64Htz5117lzj",
      "selected_model": "openai/gpt-5.6-luna",
      "text": "",
      "tool_calls": [
        {
          "function": {
            "arguments": "{\"context\":\"input\",\"selector\":{\"count\":20,\"index\":0,\"type\":\"head\"}}",
            "name": "context_peek"
          },
          "id": "call_kWpAixU1PU2hhTf22WWzrjXV",
          "index": 0,
          "type": "function"
        },
        {
          "function": {
            "arguments": "{\"context\":\"input\",\"selector\":{\"count\":10,\"index\":0,\"type\":\"tail\"}}",
            "name": "context_peek"
          },
          "id": "call_pywO74QJCdIEkwCmgVGYKYXW",
          "index": 1,
          "type": "function"
        },
        {
          "function": {
            "arguments": "{\"context\":\"input\",\"selector\":{\"count\":1,\"index\":0,\"type\":\"metadata\"}}",
            "name": "context_peek"
          },
          "id": "call_rG9RqsWR8tja5EEFvfVCWzT5",
          "index": 2,
          "type": "function"
        }
      ],
      "usage": {
        "completion_tokens": 181,
        "cost": 0.00092005,
        "present": true,
        "prompt_tokens": 2812,
        "total_tokens": 2993
      }
    }
  ],
  "output_bytes": 0,
  "phase": "native_call",
  "tool_calls": 0,
  "trajectory": [
    {
      "http_status": 200,
      "provider": "openrouter",
      "response_id": "gen-1788015999-ffnAr3BC64Htz5117lzj",
      "selected_model": "openai/gpt-5.6-luna",
      "sequence": 1,
      "type": "model",
      "usage": {
        "completion_tokens": 181,
        "cost_known": true,
        "cost_usd": 0.00092005,
        "model_calls": 1,
        "prompt_tokens": 2812,
        "tokens_known": true,
        "total_tokens": 2993
      }
    }
  ],
  "usage": {
    "completion_tokens": 181,
    "cost_known": true,
    "cost_usd": 0.00092005,
    "model_calls": 1,
    "prompt_tokens": 2812,
    "tokens_known": true,
    "total_tokens": 2993
  }
}

Sanitized traceback / stderr tail (last 160 lines)

[auto_dig_rlm] 2026-08-29T15:06:25Z phase=start mode=direct model=openai/gpt-5.6-luna reasoning_effort=max
[auto_dig_rlm] 2026-08-29T15:06:25Z phase=context_loaded chars=9433 file=agent-runs/auto-dig-prolog/2026-08-29-33259315535-1/request.md
[auto_dig_rlm] 2026-08-29T15:06:25Z phase=mcp_session_open servers=[brave,fetch]
[auto_dig_mcp] 2026-08-29T15:06:25Z session_open servers=[brave,fetch]
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=registry_create state=start
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=registry_create state=ok
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=authority_setup state=start
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=authority_setup state=ok
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=mcp_run(brave) state=start
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=mcp_run(brave) state=ok
[auto_dig_mcp] 2026-08-29T15:06:25Z phase=mcp_connect(brave) state=start
[auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_connect(brave) state=ok
[auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_import(brave) state=start
[auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_import(brave) state=ok
[auto_dig_mcp] 2026-08-29T15:06:33Z mcp_import server=brave imported_tools=8
[auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_run(fetch) state=start
[auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_run(fetch) state=ok
[auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_connect(fetch) state=start
[auto_dig_mcp] 2026-08-29T15:06:39Z phase=mcp_connect(fetch) state=ok
[auto_dig_mcp] 2026-08-29T15:06:39Z phase=mcp_import(fetch) state=start
[auto_dig_mcp] 2026-08-29T15:06:39Z phase=mcp_import(fetch) state=ok
[auto_dig_mcp] 2026-08-29T15:06:39Z mcp_import server=fetch imported_tools=6
[auto_dig_mcp] 2026-08-29T15:06:39Z phase=capability_projection state=start
[auto_dig_mcp] 2026-08-29T15:06:39Z phase=capability_projection state=ok
[auto_dig_mcp] 2026-08-29T15:06:39Z capability_projection count=14
[auto_dig_mcp] 2026-08-29T15:06:39Z session_open state=ok
[auto_dig_rlm] 2026-08-29T15:06:39Z phase=mcp_ready capability_count=14 capabilities=[tool('mcp.brave.brave_image_search'),tool('mcp.brave.brave_llm_context'),tool('mcp.brave.brave_local_search'),tool('mcp.brave.brave_news_search'),tool('mcp.brave.brave_place_search'),tool('mcp.brave.brave_summarizer'),tool('mcp.brave.brave_video_search'),tool('mcp.brave.brave_web_search'),tool('mcp.fetch.fetch_html'),tool('mcp.fetch.fetch_json'),tool('mcp.fetch.fetch_markdown'),tool('mcp.fetch.fetch_readable'),tool('mcp.fetch.fetch_txt'),tool('mcp.fetch.fetch_youtube_transcript')]
[auto_dig_rlm] 2026-08-29T15:06:39Z phase=direct_start context_window=1050000 token_budget=315000 model_calls=12 tool_calls=24 context_ops=32 iterations=24 time_limit=300.0
[auto_dig_rlm] 2026-08-29T15:06:43Z phase=direct_return
::error title=Auto-Dig Prolog-RLM failure::status=error phase=native_call kind=malformed_arguments message=native call batch failed preflight used=unknown limit=unknown model_calls=1 prompt_tokens=2812 completion_tokens=181 total_tokens=2993 cost_usd=0.00092005
[auto_dig_rlm] 2026-08-29T15:06:43Z phase=outcome status=error phase=native_call kind=malformed_arguments message=native call batch failed preflight used=unknown limit=unknown model_calls=1 prompt_tokens=2812 completion_tokens=181 total_tokens=2993 cost_usd=0.00092005
[auto_dig_rlm] 2026-08-29T15:06:43Z phase=result_written file=agent-runs/auto-dig-prolog/2026-08-29-33259315535-1/rlm-result.json
[auto_dig_rlm] 2026-08-29T15:06:43Z phase=trace_written file=agent-runs/auto-dig-prolog/2026-08-29-33259315535-1/rlm-trace.json
[auto_dig_rlm] 2026-08-29T15:06:43Z phase=finish exit_code=1

Diagnostics are sanitized at emission time. Raw environment dumps and raw provider payloads are never included in issue-bound output.

<!-- auto-dig-failure-report:33259315535-1 --> ## Auto-Dig integration failure diagnostics - Consumer: `lost-rob0t/starintel-gpt-auto-dig` - Workflow run: https://github.com/lost-rob0t/starintel-gpt-auto-dig/actions/runs/33259315535 - Consumer head: `a4b73884d1556cf8eb3bc1ec924d4dd947800733` - Prolog-RLM ref: `eb2411afdaf981a0a121f55b7ddf23dc9fcef812` - Auto-Dig target: lost-rob0t/starintel-gpt-auto-dig#2095 ## Sanitized failure diagnostics **Summary:** `phase=native_call kind=malformed_arguments message=native call batch failed preflight model_calls=1 prompt_tokens=2812 completion_tokens=181 total_tokens=2993 cost_usd=0.00092005` ### Structured Prolog-RLM error ```json { "cause": { "detail": { "$term": "unexpected_fields", "args": [ [ "index" ] ] }, "kind": "malformed_arguments", "message": "native context arguments are malformed", "phase": "schema" }, "context_calls": 0, "iterations": 1, "kind": "malformed_arguments", "message": "native call batch failed preflight", "model_responses": [ { "assistant": { "content": "", "reasoning": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.", "reasoning_details": [ { "format": "azure-openai-responses-v1", "index": 0, "summary": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.", "type": "reasoning.summary" }, { "data": "gAAAAABqkvWDW1JvUohGo7Hyx33TUJCq_CZHfbwffH8ic7JjhBeZTEMLmYQ9WyFTJqjXhZGirPCXRm25BxYUUH3JWgpmJVy5vUSdMqOwCz5fZAlQfxdOjUiBk8xb9kbdWWreJkza7RUh2OP3KH0PyleIysz5SNJKUlorTxWUFOk9HNYM15vz_WWP5RyO10--jC33hlxEP25JQUFFK5rKRM2lWeiXhN_f3aPw23viZZK-LR03SLFZr8x6j4lzROHC4bro23wCiEwokt0jq0iSSHGTFEbZ1ZH4lsOs_tOei2_wozilUWtuJgCDqAxrqk-ehOnnn7ZUYREaWQpN6mwNwsCwIPnN6aeo5liMvBJW4myIR80tq2JG31F4BpO2DHO-S2riz6er5JxyNMd-aqMExM3Bp7MdvsvEoXFDMDVSm0RbF7MX9-c16MUzsMkbFDanJ-ZL4IM_EB-aaAtHm8sE7TDUzaUGOimldL0RIwGGubkelAf3sHSR0iQy4k9T0b3TYlK4tiukzN51jdt2jDRBkh7oHjcV-F2t4aNMHnRRRWBtLdkje3IYggxMNX7UX5xb74krHLIQCo7LwGwVUEuqz_91jkemzOeacXPQVSm77hxqif-TtX-HyiL0-Zyg-hMlC8PiF3s_JoNttLvPfzXB-PvwPh33uyEt51WH_HpxFEvwWs-6Lql2EllIQDQME7lN9YgV3xIt6VYPvWDop-ygETfo32JCHi271k7IhjObWuxL9pAYfS0Ynhry9s2MplbSXBpzNlrhsxWznyO_ljg7NowLX0JgrmZmlEcOF42XBEefrJhKSrW9m6Pao7Jm7tWbfaZwRkQkXsdLfQwU_DtA5jRlJvBhiw5P9uFMcAEzhJ1XGnIyHY68py6cAJsJWxshIGVwg0yzG2baCrBaW9Wrz28oCmhbU0hcVcxzRgvXhtix68W1p-Rg7AGuQFzeHV_CSrrPXM9K4-ZYNXjihKYkyz7luxeYe8lKhYGJzImBYNpJbmMxoenjwO9Ju38Y0zlGpVwN7MbeZMaSxVW01fCEGjv6O5K7nvT8w7FwU_-qhz5vWRQVYnu269-97i7TWOtGqZRR0lxx1VXmQH8XGhavS5bpoN_YUH0whoyY6cYmES34j9Bo4ee-gGEforGXx-koYIllpRNBsq8_PN0rAaIKyn1YdTR1OXwl4wrKnbgWh-HfFy4A0iPo59J8XLBHpKgrafnJszEAJTnkRAGINBPLaO9w1hTXG6hTVJapZUXBkcxF4f5B55K4kbC8cLLY8pNgbNwSH1i2xN-s_mFjJD9z8N0ftIt_PnHvF9VLkwx0IQ6lt529xaA3pbWM-5TM9lcy7k4M03HuR-yE.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9", "format": "azure-openai-responses-v1", "id": "rs_0f596b490682313b016a92f5814294819090832d9cf8234822", "index": 1, "type": "reasoning.encrypted" } ], "role": "assistant", "tool_calls": [ { "function": { "arguments": "{\"context\":\"input\",\"selector\":{\"count\":20,\"index\":0,\"type\":\"head\"}}", "name": "context_peek" }, "id": "call_kWpAixU1PU2hhTf22WWzrjXV", "index": 0, "type": "function" }, { "function": { "arguments": "{\"context\":\"input\",\"selector\":{\"count\":10,\"index\":0,\"type\":\"tail\"}}", "name": "context_peek" }, "id": "call_pywO74QJCdIEkwCmgVGYKYXW", "index": 1, "type": "function" }, { "function": { "arguments": "{\"context\":\"input\",\"selector\":{\"count\":1,\"index\":0,\"type\":\"metadata\"}}", "name": "context_peek" }, "id": "call_rG9RqsWR8tja5EEFvfVCWzT5", "index": 2, "type": "function" } ] }, "finish_reason": "tool_calls", "metadata": { "http_status": 200, "provider": "openrouter", "response_received": true }, "provider": "openrouter", "reasoning": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.", "reasoning_details": [ { "format": "azure-openai-responses-v1", "index": 0, "summary": "**Inspecting context for task clarity**\n\nI need to figure out the task at hand by examining the input labeled \"input.\" It looks like I'll have to do some research based on its content. I want to utilize tools like web search and fetch information from primary sources. Since the actual task isn't clear from the context, inspecting the metadata or perhaps slicing through it could help. I'll consider checking the head or tail for more clues.", "type": "reasoning.summary" }, { "data": "gAAAAABqkvWDW1JvUohGo7Hyx33TUJCq_CZHfbwffH8ic7JjhBeZTEMLmYQ9WyFTJqjXhZGirPCXRm25BxYUUH3JWgpmJVy5vUSdMqOwCz5fZAlQfxdOjUiBk8xb9kbdWWreJkza7RUh2OP3KH0PyleIysz5SNJKUlorTxWUFOk9HNYM15vz_WWP5RyO10--jC33hlxEP25JQUFFK5rKRM2lWeiXhN_f3aPw23viZZK-LR03SLFZr8x6j4lzROHC4bro23wCiEwokt0jq0iSSHGTFEbZ1ZH4lsOs_tOei2_wozilUWtuJgCDqAxrqk-ehOnnn7ZUYREaWQpN6mwNwsCwIPnN6aeo5liMvBJW4myIR80tq2JG31F4BpO2DHO-S2riz6er5JxyNMd-aqMExM3Bp7MdvsvEoXFDMDVSm0RbF7MX9-c16MUzsMkbFDanJ-ZL4IM_EB-aaAtHm8sE7TDUzaUGOimldL0RIwGGubkelAf3sHSR0iQy4k9T0b3TYlK4tiukzN51jdt2jDRBkh7oHjcV-F2t4aNMHnRRRWBtLdkje3IYggxMNX7UX5xb74krHLIQCo7LwGwVUEuqz_91jkemzOeacXPQVSm77hxqif-TtX-HyiL0-Zyg-hMlC8PiF3s_JoNttLvPfzXB-PvwPh33uyEt51WH_HpxFEvwWs-6Lql2EllIQDQME7lN9YgV3xIt6VYPvWDop-ygETfo32JCHi271k7IhjObWuxL9pAYfS0Ynhry9s2MplbSXBpzNlrhsxWznyO_ljg7NowLX0JgrmZmlEcOF42XBEefrJhKSrW9m6Pao7Jm7tWbfaZwRkQkXsdLfQwU_DtA5jRlJvBhiw5P9uFMcAEzhJ1XGnIyHY68py6cAJsJWxshIGVwg0yzG2baCrBaW9Wrz28oCmhbU0hcVcxzRgvXhtix68W1p-Rg7AGuQFzeHV_CSrrPXM9K4-ZYNXjihKYkyz7luxeYe8lKhYGJzImBYNpJbmMxoenjwO9Ju38Y0zlGpVwN7MbeZMaSxVW01fCEGjv6O5K7nvT8w7FwU_-qhz5vWRQVYnu269-97i7TWOtGqZRR0lxx1VXmQH8XGhavS5bpoN_YUH0whoyY6cYmES34j9Bo4ee-gGEforGXx-koYIllpRNBsq8_PN0rAaIKyn1YdTR1OXwl4wrKnbgWh-HfFy4A0iPo59J8XLBHpKgrafnJszEAJTnkRAGINBPLaO9w1hTXG6hTVJapZUXBkcxF4f5B55K4kbC8cLLY8pNgbNwSH1i2xN-s_mFjJD9z8N0ftIt_PnHvF9VLkwx0IQ6lt529xaA3pbWM-5TM9lcy7k4M03HuR-yE.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9", "format": "azure-openai-responses-v1", "id": "rs_0f596b490682313b016a92f5814294819090832d9cf8234822", "index": 1, "type": "reasoning.encrypted" } ], "requested_model": "openai/gpt-5.6-luna", "response_id": "gen-1788015999-ffnAr3BC64Htz5117lzj", "selected_model": "openai/gpt-5.6-luna", "text": "", "tool_calls": [ { "function": { "arguments": "{\"context\":\"input\",\"selector\":{\"count\":20,\"index\":0,\"type\":\"head\"}}", "name": "context_peek" }, "id": "call_kWpAixU1PU2hhTf22WWzrjXV", "index": 0, "type": "function" }, { "function": { "arguments": "{\"context\":\"input\",\"selector\":{\"count\":10,\"index\":0,\"type\":\"tail\"}}", "name": "context_peek" }, "id": "call_pywO74QJCdIEkwCmgVGYKYXW", "index": 1, "type": "function" }, { "function": { "arguments": "{\"context\":\"input\",\"selector\":{\"count\":1,\"index\":0,\"type\":\"metadata\"}}", "name": "context_peek" }, "id": "call_rG9RqsWR8tja5EEFvfVCWzT5", "index": 2, "type": "function" } ], "usage": { "completion_tokens": 181, "cost": 0.00092005, "present": true, "prompt_tokens": 2812, "total_tokens": 2993 } } ], "output_bytes": 0, "phase": "native_call", "tool_calls": 0, "trajectory": [ { "http_status": 200, "provider": "openrouter", "response_id": "gen-1788015999-ffnAr3BC64Htz5117lzj", "selected_model": "openai/gpt-5.6-luna", "sequence": 1, "type": "model", "usage": { "completion_tokens": 181, "cost_known": true, "cost_usd": 0.00092005, "model_calls": 1, "prompt_tokens": 2812, "tokens_known": true, "total_tokens": 2993 } } ], "usage": { "completion_tokens": 181, "cost_known": true, "cost_usd": 0.00092005, "model_calls": 1, "prompt_tokens": 2812, "tokens_known": true, "total_tokens": 2993 } } ``` ### Sanitized traceback / stderr tail (last 160 lines) ```text [auto_dig_rlm] 2026-08-29T15:06:25Z phase=start mode=direct model=openai/gpt-5.6-luna reasoning_effort=max [auto_dig_rlm] 2026-08-29T15:06:25Z phase=context_loaded chars=9433 file=agent-runs/auto-dig-prolog/2026-08-29-33259315535-1/request.md [auto_dig_rlm] 2026-08-29T15:06:25Z phase=mcp_session_open servers=[brave,fetch] [auto_dig_mcp] 2026-08-29T15:06:25Z session_open servers=[brave,fetch] [auto_dig_mcp] 2026-08-29T15:06:25Z phase=registry_create state=start [auto_dig_mcp] 2026-08-29T15:06:25Z phase=registry_create state=ok [auto_dig_mcp] 2026-08-29T15:06:25Z phase=authority_setup state=start [auto_dig_mcp] 2026-08-29T15:06:25Z phase=authority_setup state=ok [auto_dig_mcp] 2026-08-29T15:06:25Z phase=mcp_run(brave) state=start [auto_dig_mcp] 2026-08-29T15:06:25Z phase=mcp_run(brave) state=ok [auto_dig_mcp] 2026-08-29T15:06:25Z phase=mcp_connect(brave) state=start [auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_connect(brave) state=ok [auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_import(brave) state=start [auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_import(brave) state=ok [auto_dig_mcp] 2026-08-29T15:06:33Z mcp_import server=brave imported_tools=8 [auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_run(fetch) state=start [auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_run(fetch) state=ok [auto_dig_mcp] 2026-08-29T15:06:33Z phase=mcp_connect(fetch) state=start [auto_dig_mcp] 2026-08-29T15:06:39Z phase=mcp_connect(fetch) state=ok [auto_dig_mcp] 2026-08-29T15:06:39Z phase=mcp_import(fetch) state=start [auto_dig_mcp] 2026-08-29T15:06:39Z phase=mcp_import(fetch) state=ok [auto_dig_mcp] 2026-08-29T15:06:39Z mcp_import server=fetch imported_tools=6 [auto_dig_mcp] 2026-08-29T15:06:39Z phase=capability_projection state=start [auto_dig_mcp] 2026-08-29T15:06:39Z phase=capability_projection state=ok [auto_dig_mcp] 2026-08-29T15:06:39Z capability_projection count=14 [auto_dig_mcp] 2026-08-29T15:06:39Z session_open state=ok [auto_dig_rlm] 2026-08-29T15:06:39Z phase=mcp_ready capability_count=14 capabilities=[tool('mcp.brave.brave_image_search'),tool('mcp.brave.brave_llm_context'),tool('mcp.brave.brave_local_search'),tool('mcp.brave.brave_news_search'),tool('mcp.brave.brave_place_search'),tool('mcp.brave.brave_summarizer'),tool('mcp.brave.brave_video_search'),tool('mcp.brave.brave_web_search'),tool('mcp.fetch.fetch_html'),tool('mcp.fetch.fetch_json'),tool('mcp.fetch.fetch_markdown'),tool('mcp.fetch.fetch_readable'),tool('mcp.fetch.fetch_txt'),tool('mcp.fetch.fetch_youtube_transcript')] [auto_dig_rlm] 2026-08-29T15:06:39Z phase=direct_start context_window=1050000 token_budget=315000 model_calls=12 tool_calls=24 context_ops=32 iterations=24 time_limit=300.0 [auto_dig_rlm] 2026-08-29T15:06:43Z phase=direct_return ::error title=Auto-Dig Prolog-RLM failure::status=error phase=native_call kind=malformed_arguments message=native call batch failed preflight used=unknown limit=unknown model_calls=1 prompt_tokens=2812 completion_tokens=181 total_tokens=2993 cost_usd=0.00092005 [auto_dig_rlm] 2026-08-29T15:06:43Z phase=outcome status=error phase=native_call kind=malformed_arguments message=native call batch failed preflight used=unknown limit=unknown model_calls=1 prompt_tokens=2812 completion_tokens=181 total_tokens=2993 cost_usd=0.00092005 [auto_dig_rlm] 2026-08-29T15:06:43Z phase=result_written file=agent-runs/auto-dig-prolog/2026-08-29-33259315535-1/rlm-result.json [auto_dig_rlm] 2026-08-29T15:06:43Z phase=trace_written file=agent-runs/auto-dig-prolog/2026-08-29-33259315535-1/rlm-trace.json [auto_dig_rlm] 2026-08-29T15:06:43Z phase=finish exit_code=1 ``` > Diagnostics are sanitized at emission time. Raw environment dumps and raw provider payloads are never included in issue-bound output.
nsaspy commented 2026-09-02 17:26:33 +00:00
Author
Owner
Copy link

One-off failure notification for auto-dig run 33259315535; superseded by subsequent successful schedule runs in starintel-gpt-auto-dig (2026-08-30 17:25, 2026-08-31 17:05 and 19:29).

One-off failure notification for auto-dig run 33259315535; superseded by subsequent successful schedule runs in starintel-gpt-auto-dig (2026-08-30 17:25, 2026-08-31 17:05 and 19:29).
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
feat/prolog-rlm-language
codex/claude-api-provider
codex/symbolic-experts
codex/openai-api-provider
feat/zai-provider-protocols
hardening/project-semantic-20260911
hardening/ws7-nix-ci-pinning
chore/track-prolog
rage/98-semantic-project-knowledge
fix/339-agent-zero-skill-graph
ci/tree-sitter-runner-labels
issue-293
research/text-streaming
docs/agent-editor-handoff
icon-add
hydra/fleet-jobs-20260904
rage/355-d6-11-plan-native-dispatch
cd/nix-installer-action-url
issue-355
rage/97-query-capture-apis
research/expert-direct-tool-projection
rage/96-versioned-syntax-facts
fix/direct-deadline-typing
dogfood/auto-dig-native-tools
feature/rage-feature-freeze
fix/323-native-batch-cardinality
fix/328-direct-user-namespace-text-string
fix/transient-provider-retry-2026-09-01
fix/openrouter-dotted-tool-result-name
rage/325-native-call-isolation
fix/316-original-batch-effect-isolation
fix/313-per-call-preflight
fix/312-peek-schema-contract
docs/agents-worktree-rule
fix/child-native-capability-narrowing
test/paid-lane-glm-53-flash
docs/spec-seeded-symbolic-plans
rage/290-spec-plan-authority
fix/304-context-peek-selector-contract
fix/298-native-any-json-schema
rage/288-spec-plan-graph-executor
feat/spec-plan-flow-api
prolog-rlm-v1
gpt-5-6-sol-high/questions-for-rlm-prolog-and-lambda-rlm
rage/277-planner-protocol-context
research-approval/rlm-research-026-task-deadlines-20260827135838
research-approval/rlm-research-025-lem-ui-20260827135751
rage/183-live-operator-behavior
agent/127-agentprolog-config
recovery/132-agentprolog-monorepo
rage/223-durable-context-mount-recovery
rage/223-constraint-benchmark-recovery
research-approval/rlm-research-011-managed-context-tool-discovery-20260827054019
feat/research-approval-schema
agent/rrlm-control-plane-research
docs/219-adrrd-review
salvage/231-runtime-status
salvage/231-runtime-status-run
tmp
tmp2
tmp3
rage/245-planner-structural-retry
rage/168-skill-selection-eval
rage/250-skill-catalog-graph
rage/56-result-acceptance
rage/172-parent-resume-replan
rage/175-deadline-policy-recovery
rage/257-provider-tool-choice-normalization
agent/tool-result-projection-presets
fix/234-numeric-schema-bounds
feature/231-rlm-cli-reference-harness
feature/223-durable-context-mounts
feature/223-real-constraint-benchmark
feature/223-real-constraint-benchmark-clean
feature/223-real-constraint-benchmark-final
feature/223-real-constraint-benchmark-impl
feature/223-real-constraint-benchmark-now
feature/223-real-constraint-benchmark-tdd
feature/223-real-constraint-benchmark-work
rage/176-root-planner-tool-projection
rage/172-typed-delegation-policy
rage/175-subagent-deadline-policy
rage/206-prompt-command-runtime
rage/203-subagent-skill-role-provenance
rage/200-permanent-rlm-context
fix/190-cli-help-success
archive/pr-132-agentprolog-config-20260827
feature/117-prolog-skill-activation-linear
feature/117-prolog-skill-activation
fix/194-completion-budget-usage
fix/191-capability-filtered-tool-schemas
fix/185-reasoning-effort
ci/report-workflow-failures-20260825
cleanup/186-remove-legacy-harnesses
fix/185-reasoning-routing
agent/evolution-async-evaluator
rage/181-binding-replay-race
agent/124-deepseek-harness-prolog
rage/144-fallback-closure
rage/164-conversation-metadata
agent/subagent-supervised-call-conformance
fix/160-context-adapter-closed-data
codex/move-agent-zero-adaptor
codex/sol-high-integration
fix/151-plunit-gate
fix/165-evolution-closed-data
fix/162-async-control-exceptions
fix/158-prompt-compiler-closed-dicts
fix/151-plunit-main-ownership
fix/156-registry-destroy-hooks
fix/154-anonymous-dict-canonicalization
fix/flake-lock-reproducibility
agent/issue-142-evolution-kernel
agent/141-flake-runtime-package
agent/rlm-subagent-runtime
agent/144-subagent-fallback-a
agent/107-bound-adapter-metadata
validation/clean-pack-install
fix/45-authoritative-nested-model-events
fix/46-router-safe-live-streaming
agent/prompt-context-compiler
agent/42-canonical-recursive-fingerprints
agent/136-static-load-errors-fail-ci
agent/44-completion-error-usage
fix/67-loader-registry-cleanup
agent/opentui-solid-reference-client-current
agent/95-project-source-registry
feature/issue-117-prolog-skill-compiler
backlog/roadmap-86-merged
agent/opentui-solid-reference-client
79-tool-effect-boundary
agent/prolog-agent-ui-research
agent/conversation-cold-context
agent/94-tree-sitter-ffi
agent/conversation-warm-context
111-opentui-solid-reference-client
109-prolog-agent-ui-v1
agent/conversation-runtime
agent/spec-mode-language
agent/spec-verify-foundation
agent/prompt-compiler-research
reconcile-backlog-postmerge
reconcile-backlog-issues
agent/prolog-agent-roadmap
feature/issue-84-effect-store-migration
fix/issue-80-effect-substrate-adversarial-hardening
feature/issue-57-effect-identity
agent/mcp-declaration-security
agent/external-tool-category-boundary
feature/issue-53-authority-pending-async
feature/issue-54-agent-graph-canonical-async
feature/issue-54-tools-mcp-canonical-async
feature/issue-54-async-canonical-runtime
agent/dual-sync-async-runtime
agent/reconcile-todo-status
feature/issue-20-deep-recursion-experiments
feature/issue-19-cli-demo-trace
feature/issue-18-benchmark-conformance
feature/issue-17-adaptive-recursion
feature/issue-16-durable-artifacts
feature/issue-15-mcp-2026-dual-version
feature/issue-14-mcp-2025-11-25
hotfix/live-tool-native-openrouter
feature/issue-13-chain-runtime
fix/stable-live-repair-gate
fix/live-repair-strategy-parser
feature/issue-12-durable-graph
feature/issue-11-agent-supervision
feature/issue-10-structured-outcomes-repair
feature/issue-9-rlm-completion
feature/issue-8-capability-tools
feature/issue-7-typed-plan-runtime
feature/issue-6-context-store
fix/openrouter-reasoning-response
fix/live-openrouter-smoke-stability
feature/issue-5-openrouter-provider
feature/issue-4-swi-bootstrap
agent/agentic-harness-research
agent/prolog-rlm-foundation
No results found.
Labels
Clear labels   
bug
Something isn't working

  
documentation
Improvements or additions to documentation

  
duplicate
This issue or pull request already exists

  
enhancement
New feature or request

  
good first issue
Good for newcomers

  
help wanted
Extra attention is needed

  
invalid
This doesn't seem right

  
question
Further information is requested

  
wontfix
This will not be worked on

No labels
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
nsaspy/prolog-rlm#314
No description provided.