fix(aux): add session_search extra_body and concurrency controls

Adds auxiliary.<task>.extra_body config passthrough so reasoning-heavy
OpenAI-compatible providers can receive provider-specific request fields
(e.g. enable_thinking: false on GLM) on auxiliary calls, and bounds
session_search summary fan-out with auxiliary.session_search.max_concurrency
(default 3, clamped 1-5) to avoid 429 bursts on small providers.

- agent/auxiliary_client.py: extract _get_auxiliary_task_config helper,
  add _get_task_extra_body, merge config+explicit extra_body with explicit winning
- hermes_cli/config.py: extra_body defaults on all aux tasks +
  session_search.max_concurrency; _config_version 19 -> 20
- tools/session_search_tool.py: semaphore around _summarize_all gather
- tests: coverage in test_auxiliary_client, test_session_search, test_aux_config
- docs: user-guide/configuration.md + fallback-providers.md

Co-authored-by: Teknium <teknium@nousresearch.com>

tests/hermes_cli/test_aux_config.py

@@ -39,6 +39,15 @@ def test_title_generation_present_in_default_config():
     assert tg["provider"] == "auto"
     assert tg["model"] == ""
     assert tg["timeout"] > 0
+    assert tg["extra_body"] == {}
+
+
+def test_session_search_defaults_include_extra_body_and_concurrency():
+    ss = DEFAULT_CONFIG["auxiliary"]["session_search"]
+    assert ss["provider"] == "auto"
+    assert ss["model"] == ""
+    assert ss["extra_body"] == {}
+    assert ss["max_concurrency"] == 3
 
 
 def test_aux_tasks_keys_all_exist_in_default_config():

tests/hermes_cli/test_config.py

@@ -459,7 +459,7 @@ class TestCustomProviderCompatibility:
             migrate_config(interactive=False, quiet=True)
             raw = yaml.safe_load(config_path.read_text(encoding="utf-8"))
 
-        assert raw["_config_version"] == 19
+        assert raw["_config_version"] == 20
         assert raw["providers"]["openai-direct"] == {
             "api": "https://api.openai.com/v1",
             "api_key": "test-key",
@@ -606,7 +606,7 @@ class TestInterimAssistantMessageConfig:
             migrate_config(interactive=False, quiet=True)
             raw = yaml.safe_load(config_path.read_text(encoding="utf-8"))
 
-        assert raw["_config_version"] == 19
+        assert raw["_config_version"] == 20
         assert raw["display"]["tool_progress"] == "off"
         assert raw["display"]["interim_assistant_messages"] is True
 
@@ -626,6 +626,6 @@ class TestDiscordChannelPromptsConfig:
             migrate_config(interactive=False, quiet=True)
             raw = yaml.safe_load(config_path.read_text(encoding="utf-8"))
 
-        assert raw["_config_version"] == 19
+        assert raw["_config_version"] == 20
         assert raw["discord"]["auto_thread"] is True
         assert raw["discord"]["channel_prompts"] == {}