fix(auxiliary): route direct-create aux callers through call_llm

hermes_cli/config.py

@@ -1700,6 +1700,18 @@ def _ensure_hermes_home_managed(home: Path):
             "extra_body": {},
             "reasoning_effort": "",  # per-task thinking level: none|minimal|low|medium|high|xhigh|max|ultra (empty = provider default)
         },
+        # Goal judge — evaluates whether a /goal run's latest response
+        # satisfies the goal/contract, and drafts goal contracts. Short
+        # structured-JSON calls; a fast cheap model is fine.
+        "goal_judge": {
+            "provider": "auto",
+            "model": "",
+            "base_url": "",
+            "api_key": "",
+            "timeout": 60,
+            "extra_body": {},
+            "reasoning_effort": "",  # per-task thinking level: none|minimal|low|medium|high|xhigh|max|ultra (empty = provider default)
+        },
         # Curator — skill-usage review fork. Timeout is generous because the
         # review pass can take several minutes on reasoning models (umbrella
         # building over hundreds of candidate skills). "auto" = use main chat

hermes_cli/goals.py

@@ -878,20 +878,11 @@ def judge_goal(
         return "continue", "empty response (nothing to evaluate)", False, None
 
     try:
-        from agent.auxiliary_client import get_auxiliary_extra_body, get_text_auxiliary_client
+        from agent.auxiliary_client import call_llm
     except Exception as exc:
         logger.debug("goal judge: auxiliary client import failed: %s", exc)
         return "continue", "auxiliary client unavailable", False, None
 
-    try:
-        client, model = get_text_auxiliary_client("goal_judge")
-    except Exception as exc:
-        logger.debug("goal judge: get_text_auxiliary_client failed: %s", exc)
-        return "continue", "auxiliary client unavailable", False, None
-
-    if client is None or not model:
-        return "continue", "no auxiliary client configured", False, None
-
     # Build the prompt. Priority: contract > subgoals > plain. When both a
     # contract and subgoals exist, the subgoals are appended into the
     # contract block as extra criteria so the judge sees a single source of
@@ -935,16 +926,18 @@ def judge_goal(
         )
 
     try:
-        resp = client.chat.completions.create(
-            model=model,
+        # Route through call_llm so auxiliary.goal_judge.* config
+        # (provider/model/base_url, extra_body, reasoning_effort, retries)
+        # all apply — the direct-create path dropped extra_body (#35566).
+        resp = call_llm(
+            task="goal_judge",
             messages=[
                 {"role": "system", "content": JUDGE_SYSTEM_PROMPT},
                 {"role": "user", "content": prompt},
             ],
             temperature=0,
             max_tokens=_goal_judge_max_tokens(),
             timeout=timeout,
-            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info("goal judge: API call failed (%s) — falling through to continue", exc)
@@ -999,31 +992,22 @@ def draft_contract(objective: str, *, timeout: float = DEFAULT_JUDGE_TIMEOUT) ->
         return None
 
     try:
-        from agent.auxiliary_client import get_auxiliary_extra_body, get_text_auxiliary_client
+        from agent.auxiliary_client import call_llm
     except Exception as exc:
         logger.debug("goal draft: auxiliary client import failed: %s", exc)
         return None
 
     try:
-        client, model = get_text_auxiliary_client("goal_judge")
-    except Exception as exc:
-        logger.debug("goal draft: get_text_auxiliary_client failed: %s", exc)
-        return None
-
-    if client is None or not model:
-        return None
-
-    try:
-        resp = client.chat.completions.create(
-            model=model,
+        # Route through call_llm — same #35566 fix as the judge call above.
+        resp = call_llm(
+            task="goal_judge",
             messages=[
                 {"role": "system", "content": DRAFT_CONTRACT_SYSTEM_PROMPT},
                 {"role": "user", "content": f"Objective:\n{_truncate(objective, 4000)}"},
             ],
             temperature=0,
             max_tokens=_goal_judge_max_tokens(),
             timeout=timeout,
-            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info("goal draft: API call failed (%s)", exc)

hermes_cli/kanban_decompose.py

@@ -298,23 +298,11 @@ def decompose_task(
     roster, valid_names = _build_roster()
 
     try:
-        from agent.auxiliary_client import (  # type: ignore
-            get_auxiliary_extra_body,
-            get_text_auxiliary_client,
-        )
+        from agent.auxiliary_client import call_llm  # type: ignore
     except Exception as exc:
         logger.debug("decompose: auxiliary client import failed: %s", exc)
         return DecomposeOutcome(task_id, False, "auxiliary client unavailable")
 
-    try:
-        client, model = get_text_auxiliary_client("kanban_decomposer")
-    except Exception as exc:
-        logger.debug("decompose: get_text_auxiliary_client failed: %s", exc)
-        return DecomposeOutcome(task_id, False, "auxiliary client unavailable")
-
-    if client is None or not model:
-        return DecomposeOutcome(task_id, False, "no auxiliary client configured")
-
     user_msg = _USER_TEMPLATE.format(
         task_id=task.id,
         title=_truncate(task.title or "", 400),
@@ -324,16 +312,19 @@ def decompose_task(
     )
 
     try:
-        resp = client.chat.completions.create(
-            model=model,
+        # Route through call_llm so auxiliary.kanban_decomposer.* config
+        # (provider/model/base_url, extra_body, reasoning_effort, retries)
+        # all apply — the previous direct client.chat.completions.create()
+        # path dropped auxiliary.<task>.extra_body entirely (#35566).
+        resp = call_llm(
+            task="kanban_decomposer",
             messages=[
                 {"role": "system", "content": _SYSTEM_PROMPT},
                 {"role": "user", "content": user_msg},
             ],
             temperature=0.3,
             max_tokens=4000,
             timeout=timeout or 180,
-            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info(

hermes_cli/kanban_specify.py

@@ -162,39 +162,30 @@ def specify_task(
         )
 
     try:
-        from agent.auxiliary_client import get_auxiliary_extra_body, get_text_auxiliary_client
+        from agent.auxiliary_client import call_llm
     except Exception as exc:  # pragma: no cover — import smoke test
         logger.debug("specify: auxiliary client import failed: %s", exc)
         return SpecifyOutcome(task_id, False, "auxiliary client unavailable")
 
-    try:
-        client, model = get_text_auxiliary_client("triage_specifier")
-    except Exception as exc:
-        logger.debug("specify: get_text_auxiliary_client failed: %s", exc)
-        return SpecifyOutcome(task_id, False, "auxiliary client unavailable")
-
-    if client is None or not model:
-        return SpecifyOutcome(
-            task_id, False, "no auxiliary client configured"
-        )
-
     user_msg = _USER_TEMPLATE.format(
         task_id=task.id,
         title=_truncate(task.title or "", 400),
         body=_truncate(task.body or "(no body)", 4000),
     )
 
     try:
-        resp = client.chat.completions.create(
-            model=model,
+        # Route through call_llm so auxiliary.triage_specifier.* config
+        # (provider/model/base_url, extra_body, reasoning_effort, retries)
+        # all apply — the direct-create path dropped extra_body (#35566).
+        resp = call_llm(
+            task="triage_specifier",
             messages=[
                 {"role": "system", "content": _SYSTEM_PROMPT},
                 {"role": "user", "content": user_msg},
             ],
             temperature=0.3,
             max_tokens=HERMES_KANBAN_SPECIFY_MAX_TOKENS,
             timeout=timeout or 120,
-            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info(

hermes_cli/profile_describer.py

@@ -210,23 +210,11 @@ def describe_profile(
         model, provider = None, None
 
     try:
-        from agent.auxiliary_client import (  # type: ignore
-            get_auxiliary_extra_body,
-            get_text_auxiliary_client,
-        )
+        from agent.auxiliary_client import call_llm  # type: ignore
     except Exception as exc:
         logger.debug("describe: auxiliary client import failed: %s", exc)
         return DescribeOutcome(canon, False, "auxiliary client unavailable")
 
-    try:
-        client, aux_model = get_text_auxiliary_client("profile_describer")
-    except Exception as exc:
-        logger.debug("describe: get_text_auxiliary_client failed: %s", exc)
-        return DescribeOutcome(canon, False, "auxiliary client unavailable")
-
-    if client is None or not aux_model:
-        return DescribeOutcome(canon, False, "no auxiliary client configured")
-
     user_msg = _USER_TEMPLATE.format(
         name=canon,
         model=(model or "(unset)"),
@@ -237,16 +225,18 @@ def describe_profile(
     )
 
     try:
-        resp = client.chat.completions.create(
-            model=aux_model,
+        # Route through call_llm so auxiliary.profile_describer.* config
+        # (provider/model/base_url, extra_body, reasoning_effort, retries)
+        # all apply — the direct-create path dropped extra_body (#35566).
+        resp = call_llm(
+            task="profile_describer",
             messages=[
                 {"role": "system", "content": _SYSTEM_PROMPT},
                 {"role": "user", "content": user_msg},
             ],
             temperature=0.3,
             max_tokens=400,
             timeout=timeout or 60,
-            extra_body=get_auxiliary_extra_body() or None,
         )
     except Exception as exc:
         logger.info("describe: API call failed for %s (%s)", canon, exc)