feat(middleware): add adaptive execution intercepts

Signed-off-by: Bryan Bednarski <bbednarski@nvidia.com>
This commit is contained in:
Bryan Bednarski
2026-06-03 11:22:06 -07:00
parent b4b9a93848
commit 2e0c9083db
14 changed files with 2013 additions and 149 deletions
+41 -1
View File
@@ -1225,6 +1225,28 @@ def run_conversation(
_sanitize_structure_non_ascii(api_kwargs)
if agent.api_mode == "codex_responses":
api_kwargs = agent._get_transport().preflight_kwargs(api_kwargs, allow_stream=False)
try:
from hermes_cli.middleware import apply_llm_request_middleware
_llm_request_mw = apply_llm_request_middleware(
api_kwargs,
task_id=effective_task_id,
turn_id=turn_id,
api_request_id=api_request_id,
session_id=agent.session_id or "",
platform=agent.platform or "",
model=agent.model,
provider=agent.provider,
base_url=agent.base_url,
api_mode=agent.api_mode,
api_call_count=api_call_count,
)
api_kwargs = _llm_request_mw.payload
_original_api_kwargs = _llm_request_mw.original_payload
_llm_middleware_trace = _llm_request_mw.trace
except Exception:
_original_api_kwargs = dict(api_kwargs)
_llm_middleware_trace = []
try:
from hermes_cli.plugins import (
@@ -1277,6 +1299,7 @@ def run_conversation(
request_char_count=total_chars,
max_tokens=agent.max_tokens,
started_at=api_start_time,
middleware_trace=list(_llm_middleware_trace),
request=_request_payload,
)
except Exception:
@@ -1335,7 +1358,24 @@ def run_conversation(
)
return agent._interruptible_api_call(next_api_kwargs)
response = _perform_api_call(api_kwargs)
from hermes_cli.middleware import run_llm_execution_middleware
response = run_llm_execution_middleware(
api_kwargs,
_perform_api_call,
original_request=_original_api_kwargs,
task_id=effective_task_id,
turn_id=turn_id,
api_request_id=api_request_id,
session_id=agent.session_id or "",
platform=agent.platform or "",
model=agent.model,
provider=agent.provider,
base_url=agent.base_url,
api_mode=agent.api_mode,
api_call_count=api_call_count,
middleware_trace=list(_llm_middleware_trace),
)
api_duration = time.time() - api_start_time