[integration][auto-dig] actor failure in run 33254149585 #315

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

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/33254149585
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=114 total_tokens=2926 cost_usd=0.00083965

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 research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!",
        "reasoning_details": [
          {
            "format": "azure-openai-responses-v1",
            "index": 0,
            "summary": "**Inspecting context for research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!",
            "type": "reasoning.summary"
          },
          {
            "data": "gAAAAABqktltC015pGEIeLYvVApBPh3aPR_oXqzfgjPLO6gNdTCYk18rqGDsxxCASTcQFkRX7RusMeUsMiDh4v2NF1bv7Er_IUFNMv6KpncORw3-rY4D04pIK7aMPgBqvCKP1_qH1W9kRTflg15bnqbDhQHd2zAnduPFJalSjhHHEr6fG4YFiYSScSCDuXMAew82_Rv70qQKPRQLg-zRwyJPlhRJUKkbbvt99cu_ErG9qlDQhEhIHhNAced4OOfyhLchkqV_G-9HH5R17mp5GRf52hDJC-FT7bvrR8trvr1uqj4pD-ZoKlbbevtWAaDUL6LG-2oT0DCk5ze9X7bRo9EHCXYg6SurFwVYeHz8pvW6gNV8bRetH5dYfU01rKmc85RPMxhC8KD0OuROAFpAMazyrW29ojWjv0SQvq-PP05KvqZ-C3nd-oshZgoT1qBUYdQYt0O3XAQ3eSM9O_vZxCz3GfnJhDhbUpICpTADyda8FdMJ_DGA9tY4F5vYzm0L2kBRJ84MhZF5YM_sRMH48mbnJa-fChJD_7WAlf4sBV12iOxCjTjaejDBP7gCjuHT2s0A9wSieUld-XKohFSwwZabxK31cvev1AeZf-f8d59AbKLSKNUkwnSLtAYXUI3QC9D_JgsNGNCC9w-ktPahI6z9c8dVhYU262ALoZ92RqXw3-naz1hJElw3THaS_VvJZD-lmaTNB0yU-UxGrfrJjJEGxWeyY6GYCLfohY92-017fcotanNjzbqIfPOQQEuvmQIzmPIIEBw9aSeW4RBwsNFFts9OGgDU-nDeymE5SBjUclgSm89IIkflUXTUDO4mQJm1lwSFgFzRt4o9MH2oOuB8lWwUCUTUyAkMVU3BgUaOXVuqSZCeQEAB4VoYmria_vOPZ9D2CHzTuGIRjWCkQFeQB1meEDxFfoimA5YWrK2eXFo6nkD3AXPpfUGSFNm0gnuI-gHWJ4h8v1bDlAvRV0VBOt7_DdaudEbNk-96EMZVJlFbUBmS56bRbDZYbXtTwgkQ1Cs_nWwn_u8v6nA1rAqA57L6EFk5LkmlnOUBv6mXBX2EJlUeqdhn5OhSlIvTMYD_C3apC0F9U3rFM3QXPfewGYifz8iZyJIFNnxVNIfy5MarEo162Kb7RIlhSXbMuVgcuJPfrdPk3ahtfoG9-8Nr8xeQGTCqPT6E25qdUvbjcpvJ_PCHwaQvvjKRLHC9v2d9KNBu8K36ofBGp5BSZPEEUNmDOiV1x4lgBgRCCwxmDdj7V2leEi9C7v8j7oG_RlGwmehL2MdTZVMc0P89djlRGQLth5fym_jI-gY3nn56qnnX6cAZCClkw-gqf28KxF5BOCHFNcpSg_YDN1zeJR54kjLGDoGfJMyVMSWUyBXBSw_Yk8UB57fPQjFhWGJMxdhEFFo5WC-kwqOWNPzlmtJyHK1YXJM7x3ksv3kSJVCm1-1sc74VsMk=.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9",
            "format": "azure-openai-responses-v1",
            "id": "rs_0d4b94347fc66adb016a92d96a591481958f0e3ca886ff1795",
            "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_op0il9jCAxUETYIq6Rad2TNc",
            "index": 0,
            "type": "function"
          }
        ]
      },
      "finish_reason": "tool_calls",
      "metadata": {
        "http_status": 200,
        "provider": "openrouter",
        "response_received": true
      },
      "provider": "openrouter",
      "reasoning": "**Inspecting context for research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!",
      "reasoning_details": [
        {
          "format": "azure-openai-responses-v1",
          "index": 0,
          "summary": "**Inspecting context for research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!",
          "type": "reasoning.summary"
        },
        {
          "data": "gAAAAABqktltC015pGEIeLYvVApBPh3aPR_oXqzfgjPLO6gNdTCYk18rqGDsxxCASTcQFkRX7RusMeUsMiDh4v2NF1bv7Er_IUFNMv6KpncORw3-rY4D04pIK7aMPgBqvCKP1_qH1W9kRTflg15bnqbDhQHd2zAnduPFJalSjhHHEr6fG4YFiYSScSCDuXMAew82_Rv70qQKPRQLg-zRwyJPlhRJUKkbbvt99cu_ErG9qlDQhEhIHhNAced4OOfyhLchkqV_G-9HH5R17mp5GRf52hDJC-FT7bvrR8trvr1uqj4pD-ZoKlbbevtWAaDUL6LG-2oT0DCk5ze9X7bRo9EHCXYg6SurFwVYeHz8pvW6gNV8bRetH5dYfU01rKmc85RPMxhC8KD0OuROAFpAMazyrW29ojWjv0SQvq-PP05KvqZ-C3nd-oshZgoT1qBUYdQYt0O3XAQ3eSM9O_vZxCz3GfnJhDhbUpICpTADyda8FdMJ_DGA9tY4F5vYzm0L2kBRJ84MhZF5YM_sRMH48mbnJa-fChJD_7WAlf4sBV12iOxCjTjaejDBP7gCjuHT2s0A9wSieUld-XKohFSwwZabxK31cvev1AeZf-f8d59AbKLSKNUkwnSLtAYXUI3QC9D_JgsNGNCC9w-ktPahI6z9c8dVhYU262ALoZ92RqXw3-naz1hJElw3THaS_VvJZD-lmaTNB0yU-UxGrfrJjJEGxWeyY6GYCLfohY92-017fcotanNjzbqIfPOQQEuvmQIzmPIIEBw9aSeW4RBwsNFFts9OGgDU-nDeymE5SBjUclgSm89IIkflUXTUDO4mQJm1lwSFgFzRt4o9MH2oOuB8lWwUCUTUyAkMVU3BgUaOXVuqSZCeQEAB4VoYmria_vOPZ9D2CHzTuGIRjWCkQFeQB1meEDxFfoimA5YWrK2eXFo6nkD3AXPpfUGSFNm0gnuI-gHWJ4h8v1bDlAvRV0VBOt7_DdaudEbNk-96EMZVJlFbUBmS56bRbDZYbXtTwgkQ1Cs_nWwn_u8v6nA1rAqA57L6EFk5LkmlnOUBv6mXBX2EJlUeqdhn5OhSlIvTMYD_C3apC0F9U3rFM3QXPfewGYifz8iZyJIFNnxVNIfy5MarEo162Kb7RIlhSXbMuVgcuJPfrdPk3ahtfoG9-8Nr8xeQGTCqPT6E25qdUvbjcpvJ_PCHwaQvvjKRLHC9v2d9KNBu8K36ofBGp5BSZPEEUNmDOiV1x4lgBgRCCwxmDdj7V2leEi9C7v8j7oG_RlGwmehL2MdTZVMc0P89djlRGQLth5fym_jI-gY3nn56qnnX6cAZCClkw-gqf28KxF5BOCHFNcpSg_YDN1zeJR54kjLGDoGfJMyVMSWUyBXBSw_Yk8UB57fPQjFhWGJMxdhEFFo5WC-kwqOWNPzlmtJyHK1YXJM7x3ksv3kSJVCm1-1sc74VsMk=.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9",
          "format": "azure-openai-responses-v1",
          "id": "rs_0d4b94347fc66adb016a92d96a591481958f0e3ca886ff1795",
          "index": 1,
          "type": "reasoning.encrypted"
        }
      ],
      "requested_model": "openai/gpt-5.6-luna",
      "response_id": "gen-1788008808-rzJaU3t0bPyn1B6ViH9l",
      "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_op0il9jCAxUETYIq6Rad2TNc",
          "index": 0,
          "type": "function"
        }
      ],
      "usage": {
        "completion_tokens": 114,
        "cost": 0.00083965,
        "present": true,
        "prompt_tokens": 2812,
        "total_tokens": 2926
      }
    }
  ],
  "output_bytes": 0,
  "phase": "native_call",
  "tool_calls": 0,
  "trajectory": [
    {
      "http_status": 200,
      "provider": "openrouter",
      "response_id": "gen-1788008808-rzJaU3t0bPyn1B6ViH9l",
      "selected_model": "openai/gpt-5.6-luna",
      "sequence": 1,
      "type": "model",
      "usage": {
        "completion_tokens": 114,
        "cost_known": true,
        "cost_usd": 0.00083965,
        "model_calls": 1,
        "prompt_tokens": 2812,
        "tokens_known": true,
        "total_tokens": 2926
      }
    }
  ],
  "usage": {
    "completion_tokens": 114,
    "cost_known": true,
    "cost_usd": 0.00083965,
    "model_calls": 1,
    "prompt_tokens": 2812,
    "tokens_known": true,
    "total_tokens": 2926
  }
}

Sanitized traceback / stderr tail (last 160 lines)

[auto_dig_rlm] 2026-08-29T13:06:35Z phase=start mode=direct model=openai/gpt-5.6-luna reasoning_effort=max
[auto_dig_rlm] 2026-08-29T13:06:35Z phase=context_loaded chars=9433 file=agent-runs/auto-dig-prolog/2026-08-29-33254149585-1/request.md
[auto_dig_rlm] 2026-08-29T13:06:35Z phase=mcp_session_open servers=[brave,fetch]
[auto_dig_mcp] 2026-08-29T13:06:35Z session_open servers=[brave,fetch]
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=registry_create state=start
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=registry_create state=ok
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=authority_setup state=start
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=authority_setup state=ok
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=mcp_run(brave) state=start
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=mcp_run(brave) state=ok
[auto_dig_mcp] 2026-08-29T13:06:35Z phase=mcp_connect(brave) state=start
[auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_connect(brave) state=ok
[auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_import(brave) state=start
[auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_import(brave) state=ok
[auto_dig_mcp] 2026-08-29T13:06:42Z mcp_import server=brave imported_tools=8
[auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_run(fetch) state=start
[auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_run(fetch) state=ok
[auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_connect(fetch) state=start
[auto_dig_mcp] 2026-08-29T13:06:48Z phase=mcp_connect(fetch) state=ok
[auto_dig_mcp] 2026-08-29T13:06:48Z phase=mcp_import(fetch) state=start
[auto_dig_mcp] 2026-08-29T13:06:48Z phase=mcp_import(fetch) state=ok
[auto_dig_mcp] 2026-08-29T13:06:48Z mcp_import server=fetch imported_tools=6
[auto_dig_mcp] 2026-08-29T13:06:48Z phase=capability_projection state=start
[auto_dig_mcp] 2026-08-29T13:06:48Z phase=capability_projection state=ok
[auto_dig_mcp] 2026-08-29T13:06:48Z capability_projection count=14
[auto_dig_mcp] 2026-08-29T13:06:48Z session_open state=ok
[auto_dig_rlm] 2026-08-29T13:06:48Z 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] 2026-08-29T13:06:48Z 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] 2026-08-29T13:06:54Z 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=114 total_tokens=2926 cost_usd=0.00083965
[auto_dig_rlm] 2026-08-29T13:06:54Z 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=114 total_tokens=2926 cost_usd=0.00083965
[auto_dig_rlm] 2026-08-29T13:06:54Z phase=result_written file=agent-runs/auto-dig-prolog/2026-08-29-33254149585-1/rlm-result.json
[auto_dig_rlm] 2026-08-29T13:06:54Z phase=trace_written file=agent-runs/auto-dig-prolog/2026-08-29-33254149585-1/rlm-trace.json
[auto_dig_rlm] 2026-08-29T13:06:54Z 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 integration failure diagnostics - Consumer: `lost-rob0t/starintel-gpt-auto-dig` - Workflow run: https://github.com/lost-rob0t/starintel-gpt-auto-dig/actions/runs/33254149585 - 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=114 total_tokens=2926 cost_usd=0.00083965` ### 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 research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!", "reasoning_details": [ { "format": "azure-openai-responses-v1", "index": 0, "summary": "**Inspecting context for research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!", "type": "reasoning.summary" }, { "data": "gAAAAABqktltC015pGEIeLYvVApBPh3aPR_oXqzfgjPLO6gNdTCYk18rqGDsxxCASTcQFkRX7RusMeUsMiDh4v2NF1bv7Er_IUFNMv6KpncORw3-rY4D04pIK7aMPgBqvCKP1_qH1W9kRTflg15bnqbDhQHd2zAnduPFJalSjhHHEr6fG4YFiYSScSCDuXMAew82_Rv70qQKPRQLg-zRwyJPlhRJUKkbbvt99cu_ErG9qlDQhEhIHhNAced4OOfyhLchkqV_G-9HH5R17mp5GRf52hDJC-FT7bvrR8trvr1uqj4pD-ZoKlbbevtWAaDUL6LG-2oT0DCk5ze9X7bRo9EHCXYg6SurFwVYeHz8pvW6gNV8bRetH5dYfU01rKmc85RPMxhC8KD0OuROAFpAMazyrW29ojWjv0SQvq-PP05KvqZ-C3nd-oshZgoT1qBUYdQYt0O3XAQ3eSM9O_vZxCz3GfnJhDhbUpICpTADyda8FdMJ_DGA9tY4F5vYzm0L2kBRJ84MhZF5YM_sRMH48mbnJa-fChJD_7WAlf4sBV12iOxCjTjaejDBP7gCjuHT2s0A9wSieUld-XKohFSwwZabxK31cvev1AeZf-f8d59AbKLSKNUkwnSLtAYXUI3QC9D_JgsNGNCC9w-ktPahI6z9c8dVhYU262ALoZ92RqXw3-naz1hJElw3THaS_VvJZD-lmaTNB0yU-UxGrfrJjJEGxWeyY6GYCLfohY92-017fcotanNjzbqIfPOQQEuvmQIzmPIIEBw9aSeW4RBwsNFFts9OGgDU-nDeymE5SBjUclgSm89IIkflUXTUDO4mQJm1lwSFgFzRt4o9MH2oOuB8lWwUCUTUyAkMVU3BgUaOXVuqSZCeQEAB4VoYmria_vOPZ9D2CHzTuGIRjWCkQFeQB1meEDxFfoimA5YWrK2eXFo6nkD3AXPpfUGSFNm0gnuI-gHWJ4h8v1bDlAvRV0VBOt7_DdaudEbNk-96EMZVJlFbUBmS56bRbDZYbXtTwgkQ1Cs_nWwn_u8v6nA1rAqA57L6EFk5LkmlnOUBv6mXBX2EJlUeqdhn5OhSlIvTMYD_C3apC0F9U3rFM3QXPfewGYifz8iZyJIFNnxVNIfy5MarEo162Kb7RIlhSXbMuVgcuJPfrdPk3ahtfoG9-8Nr8xeQGTCqPT6E25qdUvbjcpvJ_PCHwaQvvjKRLHC9v2d9KNBu8K36ofBGp5BSZPEEUNmDOiV1x4lgBgRCCwxmDdj7V2leEi9C7v8j7oG_RlGwmehL2MdTZVMc0P89djlRGQLth5fym_jI-gY3nn56qnnX6cAZCClkw-gqf28KxF5BOCHFNcpSg_YDN1zeJR54kjLGDoGfJMyVMSWUyBXBSw_Yk8UB57fPQjFhWGJMxdhEFFo5WC-kwqOWNPzlmtJyHK1YXJM7x3ksv3kSJVCm1-1sc74VsMk=.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9", "format": "azure-openai-responses-v1", "id": "rs_0d4b94347fc66adb016a92d96a591481958f0e3ca886ff1795", "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_op0il9jCAxUETYIq6Rad2TNc", "index": 0, "type": "function" } ] }, "finish_reason": "tool_calls", "metadata": { "http_status": 200, "provider": "openrouter", "response_received": true }, "provider": "openrouter", "reasoning": "**Inspecting context for research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!", "reasoning_details": [ { "format": "azure-openai-responses-v1", "index": 0, "summary": "**Inspecting context for research**\n\nI need to clarify the context of the user's initial input to answer the task effectively. It seems like the user message is generic, so I should examine the input for any embedded details. I have access to tools that can help me research broadly, which I should use to uncover relevant information. I\u2019ll start by performing a context peek to see the metadata and understand what the research topic is. This will guide my next steps!", "type": "reasoning.summary" }, { "data": "gAAAAABqktltC015pGEIeLYvVApBPh3aPR_oXqzfgjPLO6gNdTCYk18rqGDsxxCASTcQFkRX7RusMeUsMiDh4v2NF1bv7Er_IUFNMv6KpncORw3-rY4D04pIK7aMPgBqvCKP1_qH1W9kRTflg15bnqbDhQHd2zAnduPFJalSjhHHEr6fG4YFiYSScSCDuXMAew82_Rv70qQKPRQLg-zRwyJPlhRJUKkbbvt99cu_ErG9qlDQhEhIHhNAced4OOfyhLchkqV_G-9HH5R17mp5GRf52hDJC-FT7bvrR8trvr1uqj4pD-ZoKlbbevtWAaDUL6LG-2oT0DCk5ze9X7bRo9EHCXYg6SurFwVYeHz8pvW6gNV8bRetH5dYfU01rKmc85RPMxhC8KD0OuROAFpAMazyrW29ojWjv0SQvq-PP05KvqZ-C3nd-oshZgoT1qBUYdQYt0O3XAQ3eSM9O_vZxCz3GfnJhDhbUpICpTADyda8FdMJ_DGA9tY4F5vYzm0L2kBRJ84MhZF5YM_sRMH48mbnJa-fChJD_7WAlf4sBV12iOxCjTjaejDBP7gCjuHT2s0A9wSieUld-XKohFSwwZabxK31cvev1AeZf-f8d59AbKLSKNUkwnSLtAYXUI3QC9D_JgsNGNCC9w-ktPahI6z9c8dVhYU262ALoZ92RqXw3-naz1hJElw3THaS_VvJZD-lmaTNB0yU-UxGrfrJjJEGxWeyY6GYCLfohY92-017fcotanNjzbqIfPOQQEuvmQIzmPIIEBw9aSeW4RBwsNFFts9OGgDU-nDeymE5SBjUclgSm89IIkflUXTUDO4mQJm1lwSFgFzRt4o9MH2oOuB8lWwUCUTUyAkMVU3BgUaOXVuqSZCeQEAB4VoYmria_vOPZ9D2CHzTuGIRjWCkQFeQB1meEDxFfoimA5YWrK2eXFo6nkD3AXPpfUGSFNm0gnuI-gHWJ4h8v1bDlAvRV0VBOt7_DdaudEbNk-96EMZVJlFbUBmS56bRbDZYbXtTwgkQ1Cs_nWwn_u8v6nA1rAqA57L6EFk5LkmlnOUBv6mXBX2EJlUeqdhn5OhSlIvTMYD_C3apC0F9U3rFM3QXPfewGYifz8iZyJIFNnxVNIfy5MarEo162Kb7RIlhSXbMuVgcuJPfrdPk3ahtfoG9-8Nr8xeQGTCqPT6E25qdUvbjcpvJ_PCHwaQvvjKRLHC9v2d9KNBu8K36ofBGp5BSZPEEUNmDOiV1x4lgBgRCCwxmDdj7V2leEi9C7v8j7oG_RlGwmehL2MdTZVMc0P89djlRGQLth5fym_jI-gY3nn56qnnX6cAZCClkw-gqf28KxF5BOCHFNcpSg_YDN1zeJR54kjLGDoGfJMyVMSWUyBXBSw_Yk8UB57fPQjFhWGJMxdhEFFo5WC-kwqOWNPzlmtJyHK1YXJM7x3ksv3kSJVCm1-1sc74VsMk=.eyJlbmRwb2ludF9zbHVnIjoib3BlbmFpL2dwdC01LjYtbHVuYS0yMDI2MDcwOXxhenVyZSJ9", "format": "azure-openai-responses-v1", "id": "rs_0d4b94347fc66adb016a92d96a591481958f0e3ca886ff1795", "index": 1, "type": "reasoning.encrypted" } ], "requested_model": "openai/gpt-5.6-luna", "response_id": "gen-1788008808-rzJaU3t0bPyn1B6ViH9l", "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_op0il9jCAxUETYIq6Rad2TNc", "index": 0, "type": "function" } ], "usage": { "completion_tokens": 114, "cost": 0.00083965, "present": true, "prompt_tokens": 2812, "total_tokens": 2926 } } ], "output_bytes": 0, "phase": "native_call", "tool_calls": 0, "trajectory": [ { "http_status": 200, "provider": "openrouter", "response_id": "gen-1788008808-rzJaU3t0bPyn1B6ViH9l", "selected_model": "openai/gpt-5.6-luna", "sequence": 1, "type": "model", "usage": { "completion_tokens": 114, "cost_known": true, "cost_usd": 0.00083965, "model_calls": 1, "prompt_tokens": 2812, "tokens_known": true, "total_tokens": 2926 } } ], "usage": { "completion_tokens": 114, "cost_known": true, "cost_usd": 0.00083965, "model_calls": 1, "prompt_tokens": 2812, "tokens_known": true, "total_tokens": 2926 } } ``` ### Sanitized traceback / stderr tail (last 160 lines) ```text [auto_dig_rlm] 2026-08-29T13:06:35Z phase=start mode=direct model=openai/gpt-5.6-luna reasoning_effort=max [auto_dig_rlm] 2026-08-29T13:06:35Z phase=context_loaded chars=9433 file=agent-runs/auto-dig-prolog/2026-08-29-33254149585-1/request.md [auto_dig_rlm] 2026-08-29T13:06:35Z phase=mcp_session_open servers=[brave,fetch] [auto_dig_mcp] 2026-08-29T13:06:35Z session_open servers=[brave,fetch] [auto_dig_mcp] 2026-08-29T13:06:35Z phase=registry_create state=start [auto_dig_mcp] 2026-08-29T13:06:35Z phase=registry_create state=ok [auto_dig_mcp] 2026-08-29T13:06:35Z phase=authority_setup state=start [auto_dig_mcp] 2026-08-29T13:06:35Z phase=authority_setup state=ok [auto_dig_mcp] 2026-08-29T13:06:35Z phase=mcp_run(brave) state=start [auto_dig_mcp] 2026-08-29T13:06:35Z phase=mcp_run(brave) state=ok [auto_dig_mcp] 2026-08-29T13:06:35Z phase=mcp_connect(brave) state=start [auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_connect(brave) state=ok [auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_import(brave) state=start [auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_import(brave) state=ok [auto_dig_mcp] 2026-08-29T13:06:42Z mcp_import server=brave imported_tools=8 [auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_run(fetch) state=start [auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_run(fetch) state=ok [auto_dig_mcp] 2026-08-29T13:06:42Z phase=mcp_connect(fetch) state=start [auto_dig_mcp] 2026-08-29T13:06:48Z phase=mcp_connect(fetch) state=ok [auto_dig_mcp] 2026-08-29T13:06:48Z phase=mcp_import(fetch) state=start [auto_dig_mcp] 2026-08-29T13:06:48Z phase=mcp_import(fetch) state=ok [auto_dig_mcp] 2026-08-29T13:06:48Z mcp_import server=fetch imported_tools=6 [auto_dig_mcp] 2026-08-29T13:06:48Z phase=capability_projection state=start [auto_dig_mcp] 2026-08-29T13:06:48Z phase=capability_projection state=ok [auto_dig_mcp] 2026-08-29T13:06:48Z capability_projection count=14 [auto_dig_mcp] 2026-08-29T13:06:48Z session_open state=ok [auto_dig_rlm] 2026-08-29T13:06:48Z 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] 2026-08-29T13:06:48Z 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] 2026-08-29T13:06:54Z 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=114 total_tokens=2926 cost_usd=0.00083965 [auto_dig_rlm] 2026-08-29T13:06:54Z 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=114 total_tokens=2926 cost_usd=0.00083965 [auto_dig_rlm] 2026-08-29T13:06:54Z phase=result_written file=agent-runs/auto-dig-prolog/2026-08-29-33254149585-1/rlm-result.json [auto_dig_rlm] 2026-08-29T13:06:54Z phase=trace_written file=agent-runs/auto-dig-prolog/2026-08-29-33254149585-1/rlm-trace.json [auto_dig_rlm] 2026-08-29T13:06:54Z 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 closed this issue

2026-09-02 17:25:37 +00:00

nsaspy commented

2026-09-02 17:26:32 +00:00

Author

Owner

One-off failure notification for auto-dig run 33254149585; superseded by subsequent successful schedule runs in starintel-gpt-auto-dig (2026-08-30 17:25, 2026-08-31 17:05 and 19:29).

nsaspy referenced this issue

2026-09-04 22:26:04 +00:00

fix: align context_peek selector contract with projected schema #376

nsaspy referenced this issue

2026-09-04 22:26:09 +00:00

fix: isolate recoverable native preflight faults per call #375