[integration][auto-dig] actor failure in run 33124557266 #286

New issue

Closed

opened 2026-08-28 03:19:59 +00:00 by nsaspy · 1 comment

nsaspy commented

2026-08-28 03:19:59 +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/33124557266
Consumer head: f9854092a34b60767e95a19ddea4332cdb6720eb
Prolog-RLM ref: 7f0050f524db6de5293163241176ac4660f04349
Auto-Dig target: lost-rob0t/starintel-gpt-auto-dig#2095

Sanitized failure diagnostics

Summary: phase=planner kind=plan_parse_failed message=planner responses did not contain a valid typed plan model_calls=3 prompt_tokens=8121 completion_tokens=6144 total_tokens=14265 cost_usd=0.008158760000000001

Structured Prolog-RLM error

{
  "attempts": 3,
  "cause": {
    "detail": {
      "$term": "invalid_json",
      "args": [
        {
          "$term": "error",
          "args": [
            {
              "$term": "syntax_error",
              "args": [
                {
                  "$term": "json",
                  "args": [
                    "illegal_json"
                  ]
                }
              ]
            },
            {
              "$term": "stream",
              "args": [
                "<stream>(0x7f793c03a560)",
                1,
                58,
                58
              ]
            }
          ]
        }
      ]
    },
    "kind": "invalid_plan",
    "message": "plan could not be normalized",
    "phase": "parse"
  },
  "kind": "plan_parse_failed",
  "message": "planner responses did not contain a valid typed plan",
  "phase": "planner",
  "usage": {
    "completion_tokens": 6144,
    "cost_known": true,
    "cost_usd": 0.008158760000000001,
    "model_calls": 3,
    "prompt_tokens": 8121,
    "tokens_known": true,
    "total_tokens": 14265
  }
}

Sanitized traceback / stderr tail (last 160 lines)

[auto_dig_rlm] 2026-08-27T22:59:16Z phase=start model=openai/gpt-5.6-luna reasoning_effort=max
[auto_dig_rlm] 2026-08-27T22:59:16Z phase=context_loaded chars=9433 file=agent-runs/auto-dig-prolog/2026-08-27-33124557266-1/request.md
[auto_dig_rlm] 2026-08-27T22:59:16Z phase=mcp_session_open servers=[brave,fetch]
[auto_dig_mcp] 2026-08-27T22:59:16Z session_open servers=[brave,fetch]
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=registry_create state=start
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=registry_create state=ok
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=authority_setup state=start
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=authority_setup state=ok
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=mcp_run(brave) state=start
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=mcp_run(brave) state=ok
[auto_dig_mcp] 2026-08-27T22:59:16Z phase=mcp_connect(brave) state=start
[auto_dig_mcp] 2026-08-27T22:59:38Z phase=mcp_connect(brave) state=ok
[auto_dig_mcp] 2026-08-27T22:59:38Z phase=mcp_import(brave) state=start
[auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_import(brave) state=ok
[auto_dig_mcp] 2026-08-27T22:59:39Z mcp_import server=brave imported_tools=8
[auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_run(fetch) state=start
[auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_run(fetch) state=ok
[auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_connect(fetch) state=start
[auto_dig_mcp] 2026-08-27T22:59:43Z phase=mcp_connect(fetch) state=ok
[auto_dig_mcp] 2026-08-27T22:59:43Z phase=mcp_import(fetch) state=start
[auto_dig_mcp] 2026-08-27T22:59:43Z phase=mcp_import(fetch) state=ok
[auto_dig_mcp] 2026-08-27T22:59:43Z mcp_import server=fetch imported_tools=6
[auto_dig_mcp] 2026-08-27T22:59:43Z phase=capability_projection state=start
[auto_dig_mcp] 2026-08-27T22:59:43Z phase=capability_projection state=ok
[auto_dig_mcp] 2026-08-27T22:59:43Z capability_projection count=8
[auto_dig_mcp] 2026-08-27T22:59:43Z session_open state=ok
[auto_dig_rlm] 2026-08-27T22:59:43Z phase=mcp_ready capability_count=8 capabilities=[tool('mcp.brave.brave_news_search'),tool('mcp.brave.brave_video_search'),tool('mcp.brave.brave_web_search'),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] 2026-08-27T22:59:43Z phase=rlm_start token_budget=50000 model_calls=6 tool_calls=8 recursion_depth=2 time_limit=90.0
[auto_dig_rlm] 2026-08-27T23:00:53Z phase=rlm_return
::error title=Auto-Dig Prolog-RLM failure::status=error phase=planner kind=plan_parse_failed message=planner responses did not contain a valid typed plan used=unknown limit=unknown model_calls=3 prompt_tokens=8121 completion_tokens=6144 total_tokens=14265 cost_usd=0.008158760000000001
[auto_dig_rlm] 2026-08-27T23:00:53Z phase=outcome status=error phase=planner kind=plan_parse_failed message=planner responses did not contain a valid typed plan used=unknown limit=unknown model_calls=3 prompt_tokens=8121 completion_tokens=6144 total_tokens=14265 cost_usd=0.008158760000000001
[auto_dig_rlm] 2026-08-27T23:00:53Z phase=result_written file=agent-runs/auto-dig-prolog/2026-08-27-33124557266-1/rlm-result.json
[auto_dig_rlm] 2026-08-27T23:00:53Z phase=trace_written file=agent-runs/auto-dig-prolog/2026-08-27-33124557266-1/rlm-trace.json
[auto_dig_rlm] 2026-08-27T23:00:53Z 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/33124557266 - Consumer head: `f9854092a34b60767e95a19ddea4332cdb6720eb` - Prolog-RLM ref: `7f0050f524db6de5293163241176ac4660f04349` - Auto-Dig target: lost-rob0t/starintel-gpt-auto-dig#2095 ## Sanitized failure diagnostics **Summary:** `phase=planner kind=plan_parse_failed message=planner responses did not contain a valid typed plan model_calls=3 prompt_tokens=8121 completion_tokens=6144 total_tokens=14265 cost_usd=0.008158760000000001` ### Structured Prolog-RLM error ```json { "attempts": 3, "cause": { "detail": { "$term": "invalid_json", "args": [ { "$term": "error", "args": [ { "$term": "syntax_error", "args": [ { "$term": "json", "args": [ "illegal_json" ] } ] }, { "$term": "stream", "args": [ "<stream>(0x7f793c03a560)", 1, 58, 58 ] } ] } ] }, "kind": "invalid_plan", "message": "plan could not be normalized", "phase": "parse" }, "kind": "plan_parse_failed", "message": "planner responses did not contain a valid typed plan", "phase": "planner", "usage": { "completion_tokens": 6144, "cost_known": true, "cost_usd": 0.008158760000000001, "model_calls": 3, "prompt_tokens": 8121, "tokens_known": true, "total_tokens": 14265 } } ``` ### Sanitized traceback / stderr tail (last 160 lines) ```text [auto_dig_rlm] 2026-08-27T22:59:16Z phase=start model=openai/gpt-5.6-luna reasoning_effort=max [auto_dig_rlm] 2026-08-27T22:59:16Z phase=context_loaded chars=9433 file=agent-runs/auto-dig-prolog/2026-08-27-33124557266-1/request.md [auto_dig_rlm] 2026-08-27T22:59:16Z phase=mcp_session_open servers=[brave,fetch] [auto_dig_mcp] 2026-08-27T22:59:16Z session_open servers=[brave,fetch] [auto_dig_mcp] 2026-08-27T22:59:16Z phase=registry_create state=start [auto_dig_mcp] 2026-08-27T22:59:16Z phase=registry_create state=ok [auto_dig_mcp] 2026-08-27T22:59:16Z phase=authority_setup state=start [auto_dig_mcp] 2026-08-27T22:59:16Z phase=authority_setup state=ok [auto_dig_mcp] 2026-08-27T22:59:16Z phase=mcp_run(brave) state=start [auto_dig_mcp] 2026-08-27T22:59:16Z phase=mcp_run(brave) state=ok [auto_dig_mcp] 2026-08-27T22:59:16Z phase=mcp_connect(brave) state=start [auto_dig_mcp] 2026-08-27T22:59:38Z phase=mcp_connect(brave) state=ok [auto_dig_mcp] 2026-08-27T22:59:38Z phase=mcp_import(brave) state=start [auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_import(brave) state=ok [auto_dig_mcp] 2026-08-27T22:59:39Z mcp_import server=brave imported_tools=8 [auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_run(fetch) state=start [auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_run(fetch) state=ok [auto_dig_mcp] 2026-08-27T22:59:39Z phase=mcp_connect(fetch) state=start [auto_dig_mcp] 2026-08-27T22:59:43Z phase=mcp_connect(fetch) state=ok [auto_dig_mcp] 2026-08-27T22:59:43Z phase=mcp_import(fetch) state=start [auto_dig_mcp] 2026-08-27T22:59:43Z phase=mcp_import(fetch) state=ok [auto_dig_mcp] 2026-08-27T22:59:43Z mcp_import server=fetch imported_tools=6 [auto_dig_mcp] 2026-08-27T22:59:43Z phase=capability_projection state=start [auto_dig_mcp] 2026-08-27T22:59:43Z phase=capability_projection state=ok [auto_dig_mcp] 2026-08-27T22:59:43Z capability_projection count=8 [auto_dig_mcp] 2026-08-27T22:59:43Z session_open state=ok [auto_dig_rlm] 2026-08-27T22:59:43Z phase=mcp_ready capability_count=8 capabilities=[tool('mcp.brave.brave_news_search'),tool('mcp.brave.brave_video_search'),tool('mcp.brave.brave_web_search'),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] 2026-08-27T22:59:43Z phase=rlm_start token_budget=50000 model_calls=6 tool_calls=8 recursion_depth=2 time_limit=90.0 [auto_dig_rlm] 2026-08-27T23:00:53Z phase=rlm_return ::error title=Auto-Dig Prolog-RLM failure::status=error phase=planner kind=plan_parse_failed message=planner responses did not contain a valid typed plan used=unknown limit=unknown model_calls=3 prompt_tokens=8121 completion_tokens=6144 total_tokens=14265 cost_usd=0.008158760000000001 [auto_dig_rlm] 2026-08-27T23:00:53Z phase=outcome status=error phase=planner kind=plan_parse_failed message=planner responses did not contain a valid typed plan used=unknown limit=unknown model_calls=3 prompt_tokens=8121 completion_tokens=6144 total_tokens=14265 cost_usd=0.008158760000000001 [auto_dig_rlm] 2026-08-27T23:00:53Z phase=result_written file=agent-runs/auto-dig-prolog/2026-08-27-33124557266-1/rlm-result.json [auto_dig_rlm] 2026-08-27T23:00:53Z phase=trace_written file=agent-runs/auto-dig-prolog/2026-08-27-33124557266-1/rlm-trace.json [auto_dig_rlm] 2026-08-27T23:00:53Z 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 referenced this issue

2026-08-28 03:22:34 +00:00

fix: harden planner context protocol #278

nsaspy referenced this issue

2026-09-02 17:25:38 +00:00

[CI failure] Paid OpenRouter on prolog-rlm-v1 #331

nsaspy referenced this issue

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

[CI failure] CI on rage/277-planner-protocol-context #282

nsaspy commented

2026-09-02 17:26:27 +00:00

Author

Owner

Consumer-side workaround is now being applied in starintel-gpt-auto-dig on branch fix/auto-dig-direct-rlm-2026-08-29:

pin current Prolog-RLM direct runtime a89175bf925df3afa358f8d05a370fe2a03e2117;
bypass typed-plan generation for this research lane and call native rlm_direct/4;
expose the full capability-filtered Brave + Fetch read-only inventory to direct mode;
raise the direct loop to 12 model turns / 24 tool calls / 32 context ops;
set max_total_tokens=315000, i.e. 30% of the routed GPT-5.6 models' current 1,050,000-token context limit;
require the research result to name missing tool/datasource capabilities for follow-up.

The consumer-specific hardcoded model-limit/tool-projection policy is tracked for removal in #296.

Consumer-side workaround is now being applied in `starintel-gpt-auto-dig` on branch `fix/auto-dig-direct-rlm-2026-08-29`: - pin current Prolog-RLM direct runtime `a89175bf925df3afa358f8d05a370fe2a03e2117`; - bypass typed-plan generation for this research lane and call native `rlm_direct/4`; - expose the full capability-filtered Brave + Fetch read-only inventory to direct mode; - raise the direct loop to 12 model turns / 24 tool calls / 32 context ops; - set `max_total_tokens=315000`, i.e. 30% of the routed GPT-5.6 models' current 1,050,000-token context limit; - require the research result to name missing tool/datasource capabilities for follow-up. The consumer-specific hardcoded model-limit/tool-projection policy is tracked for removal in #296.

nsaspy referenced this issue

2026-09-02 17:26:27 +00:00

[CI failure] Paid OpenRouter on prolog-rlm-v1 #331

nsaspy referenced this issue

2026-09-04 22:25:51 +00:00

design: SPEC/PLAN authority architecture and executable design gate #379

nsaspy closed this issue

2026-09-08 01:29:00 +00:00

nsaspy referenced this issue

2026-09-08 01:29:03 +00:00

[CI failure] Paid OpenRouter on prolog-rlm-v1 #285

nsaspy referenced this issue