common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix(aux): add session_search extra_body and concurrency controls

Browse Source 
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>
This commit is contained in:
helix4u
2026-04-20 00:44:32 -07:00
committed by Teknium
parent 904f20d622
commit 6ab78401c9
8 changed files with 207 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
agent/auxiliary_client.py
View File

@@ -2313,7 +2313,6 @@ def _resolve_task_provider_model(
to "custom" and the task uses that direct endpoint. api_mode is one of
"chat_completions", "codex_responses", or None (auto-detect).
"""
config = {}
cfg_provider = None
cfg_model = None
cfg_base_url = None
@@ -2321,16 +2320,7 @@ def _resolve_task_provider_model(
cfg_api_mode = None
if task:
try:
from hermes_cli.config import load_config
config = load_config()
except ImportError:
config = {}
aux = config.get("auxiliary", {}) if isinstance(config, dict) else {}
task_config = aux.get(task, {}) if isinstance(aux, dict) else {}
if not isinstance(task_config, dict):
task_config = {}
task_config = _get_auxiliary_task_config(task)
cfg_provider = str(task_config.get("provider", "")).strip() or None
cfg_model = str(task_config.get("model", "")).strip() or None
cfg_base_url = str(task_config.get("base_url", "")).strip() or None
@@ -2360,17 +2350,25 @@ def _resolve_task_provider_model(
_DEFAULT_AUX_TIMEOUT = 30.0
def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float:
"""Read timeout from auxiliary.{task}.timeout in config, falling back to *default*."""
def _get_auxiliary_task_config(task: str) -> Dict[str, Any]:
"""Return the config dict for auxiliary.<task>, or {} when unavailable."""
if not task:
return default
return {}
try:
from hermes_cli.config import load_config
config = load_config()
except ImportError:
return default
return {}
aux = config.get("auxiliary", {}) if isinstance(config, dict) else {}
task_config = aux.get(task, {}) if isinstance(aux, dict) else {}
return task_config if isinstance(task_config, dict) else {}
def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float:
"""Read timeout from auxiliary.{task}.timeout in config, falling back to *default*."""
if not task:
return default
task_config = _get_auxiliary_task_config(task)
raw = task_config.get("timeout")
if raw is not None:
try:
@@ -2380,6 +2378,15 @@ def _get_task_timeout(task: str, default: float = _DEFAULT_AUX_TIMEOUT) -> float
return default
def _get_task_extra_body(task: str) -> Dict[str, Any]:
"""Read auxiliary.<task>.extra_body and return a shallow copy when valid."""
task_config = _get_auxiliary_task_config(task)
raw = task_config.get("extra_body")
if isinstance(raw, dict):
return dict(raw)
return {}
# ---------------------------------------------------------------------------
# Anthropic-compatible endpoint detection + image block conversion
# ---------------------------------------------------------------------------
@@ -2580,6 +2587,8 @@ def call_llm(
"""
resolved_provider, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
task, provider, model, base_url, api_key)
effective_extra_body = _get_task_extra_body(task)
effective_extra_body.update(extra_body or {})
if task == "vision":
effective_provider, client, final_model = resolve_vision_provider_client(
@@ -2654,7 +2663,7 @@ def call_llm(
kwargs = _build_call_kwargs(
resolved_provider, final_model, messages,
temperature=temperature, max_tokens=max_tokens,
tools=tools, timeout=effective_timeout, extra_body=extra_body,
tools=tools, timeout=effective_timeout, extra_body=effective_extra_body,
base_url=_base_info or resolved_base_url)
# Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
@@ -2709,7 +2718,7 @@ def call_llm(
fb_label, fb_model, messages,
temperature=temperature, max_tokens=max_tokens,
tools=tools, timeout=effective_timeout,
extra_body=extra_body,
extra_body=effective_extra_body,
base_url=str(getattr(fb_client, "base_url", "") or ""))
return _validate_llm_response(
fb_client.chat.completions.create(**fb_kwargs), task)
@@ -2792,6 +2801,8 @@ async def async_call_llm(
"""
resolved_provider, resolved_model, resolved_base_url, resolved_api_key, resolved_api_mode = _resolve_task_provider_model(
task, provider, model, base_url, api_key)
effective_extra_body = _get_task_extra_body(task)
effective_extra_body.update(extra_body or {})
if task == "vision":
effective_provider, client, final_model = resolve_vision_provider_client(
@@ -2852,7 +2863,7 @@ async def async_call_llm(
kwargs = _build_call_kwargs(
resolved_provider, final_model, messages,
temperature=temperature, max_tokens=max_tokens,
tools=tools, timeout=effective_timeout, extra_body=extra_body,
tools=tools, timeout=effective_timeout, extra_body=effective_extra_body,
base_url=_client_base or resolved_base_url)
# Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
@@ -2891,7 +2902,7 @@ async def async_call_llm(
fb_label, fb_model, messages,
temperature=temperature, max_tokens=max_tokens,
tools=tools, timeout=effective_timeout,
extra_body=extra_body,
extra_body=effective_extra_body,
base_url=str(getattr(fb_client, "base_url", "") or ""))
# Convert sync fallback client to async
async_fb, async_fb_model = _to_async_client(fb_client, fb_model or "")