mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
feat: add ResponsesApiTransport + wire all Codex transport paths
Add ResponsesApiTransport wrapping codex_responses_adapter.py behind the ProviderTransport ABC. Auto-registered via _discover_transports(). Wire ALL Codex transport methods to production paths in run_agent.py: - build_kwargs: main _build_api_kwargs codex branch (50 lines extracted) - normalize_response: main loop + flush + summary + retry (4 sites) - convert_tools: memory flush tool override - convert_messages: called internally via build_kwargs - validate_response: response validation gate - preflight_kwargs: request sanitization (2 sites) Remove 7 dead legacy wrappers from AIAgent (_responses_tools, _chat_messages_to_responses_input, _normalize_codex_response, _preflight_codex_api_kwargs, _preflight_codex_input_items, _extract_responses_message_text, _extract_responses_reasoning_text). Keep 3 ID manipulation methods still used by _build_assistant_message. Update 18 test call sites across 3 test files to call adapter functions directly instead of through deleted AIAgent wrappers. 24 new tests. 343 codex/responses/transport tests pass (0 failures). PR 4 of the provider transport refactor.
This commit is contained in:
kshitijk4poor
Teknium
parent
09dd5eb6a5
commit
c832ebd67c
7 changed files with 589 additions and 169 deletions
240
run_agent.py
240
run_agent.py
|
|
@ -4308,10 +4308,6 @@ class AIAgent:
|
|||
if self._memory_store:
|
||||
self._memory_store.load_from_disk()
|
||||
|
||||
def _responses_tools(self, tools: Optional[List[Dict[str, Any]]] = None) -> Optional[List[Dict[str, Any]]]:
|
||||
"""Convert chat-completions tool schemas to Responses function-tool schemas."""
|
||||
return _codex_responses_tools(tools if tools is not None else self.tools)
|
||||
|
||||
@staticmethod
|
||||
def _deterministic_call_id(fn_name: str, arguments: str, index: int = 0) -> str:
|
||||
"""Generate a deterministic call_id from tool call content.
|
||||
|
|
@ -4335,33 +4331,6 @@ class AIAgent:
|
|||
"""Build a valid Responses `function_call.id` (must start with `fc_`)."""
|
||||
return _codex_derive_responses_function_call_id(call_id, response_item_id)
|
||||
|
||||
def _chat_messages_to_responses_input(self, messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
|
||||
"""Convert internal chat-style messages to Responses input items."""
|
||||
return _codex_chat_messages_to_responses_input(messages)
|
||||
|
||||
def _preflight_codex_input_items(self, raw_items: Any) -> List[Dict[str, Any]]:
|
||||
return _codex_preflight_codex_input_items(raw_items)
|
||||
|
||||
def _preflight_codex_api_kwargs(
|
||||
self,
|
||||
api_kwargs: Any,
|
||||
*,
|
||||
allow_stream: bool = False,
|
||||
) -> Dict[str, Any]:
|
||||
return _codex_preflight_codex_api_kwargs(api_kwargs, allow_stream=allow_stream)
|
||||
|
||||
def _extract_responses_message_text(self, item: Any) -> str:
|
||||
"""Extract assistant text from a Responses message output item."""
|
||||
return _codex_extract_responses_message_text(item)
|
||||
|
||||
def _extract_responses_reasoning_text(self, item: Any) -> str:
|
||||
"""Extract a compact reasoning text from a Responses reasoning item."""
|
||||
return _codex_extract_responses_reasoning_text(item)
|
||||
|
||||
def _normalize_codex_response(self, response: Any) -> tuple[Any, str]:
|
||||
"""Normalize a Responses API object to an assistant_message-like object."""
|
||||
return _codex_normalize_codex_response(response)
|
||||
|
||||
def _thread_identity(self) -> str:
|
||||
thread = threading.current_thread()
|
||||
return f"{thread.name}:{thread.ident}"
|
||||
|
|
@ -4854,7 +4823,7 @@ class AIAgent:
|
|||
active_client = client or self._ensure_primary_openai_client(reason="codex_create_stream_fallback")
|
||||
fallback_kwargs = dict(api_kwargs)
|
||||
fallback_kwargs["stream"] = True
|
||||
fallback_kwargs = self._preflight_codex_api_kwargs(fallback_kwargs, allow_stream=True)
|
||||
fallback_kwargs = self._get_codex_transport().preflight_kwargs(fallback_kwargs, allow_stream=True)
|
||||
stream_or_response = active_client.responses.create(**fallback_kwargs)
|
||||
|
||||
# Compatibility shim for mocks or providers that still return a concrete response.
|
||||
|
|
@ -6596,6 +6565,15 @@ class AIAgent:
|
|||
self._anthropic_transport = t
|
||||
return t
|
||||
|
||||
def _get_codex_transport(self):
|
||||
"""Return the cached ResponsesApiTransport instance (lazy singleton)."""
|
||||
t = getattr(self, "_codex_transport", None)
|
||||
if t is None:
|
||||
from agent.transports import get_transport
|
||||
t = get_transport("codex_responses")
|
||||
self._codex_transport = t
|
||||
return t
|
||||
|
||||
def _prepare_anthropic_messages_for_api(self, api_messages: list) -> list:
|
||||
if not any(
|
||||
isinstance(msg, dict) and self._content_has_image_parts(msg.get("content"))
|
||||
|
|
@ -6752,14 +6730,7 @@ class AIAgent:
|
|||
}
|
||||
|
||||
if self.api_mode == "codex_responses":
|
||||
instructions = ""
|
||||
payload_messages = api_messages
|
||||
if api_messages and api_messages[0].get("role") == "system":
|
||||
instructions = str(api_messages[0].get("content") or "").strip()
|
||||
payload_messages = api_messages[1:]
|
||||
if not instructions:
|
||||
instructions = DEFAULT_AGENT_IDENTITY
|
||||
|
||||
_ct = self._get_codex_transport()
|
||||
is_github_responses = (
|
||||
base_url_host_matches(self.base_url, "models.github.ai")
|
||||
or base_url_host_matches(self.base_url, "api.githubcopilot.com")
|
||||
|
|
@ -6771,64 +6742,20 @@ class AIAgent:
|
|||
and "/backend-api/codex" in self._base_url_lower
|
||||
)
|
||||
)
|
||||
|
||||
# Resolve reasoning effort: config > default (medium)
|
||||
reasoning_effort = "medium"
|
||||
reasoning_enabled = True
|
||||
if self.reasoning_config and isinstance(self.reasoning_config, dict):
|
||||
if self.reasoning_config.get("enabled") is False:
|
||||
reasoning_enabled = False
|
||||
elif self.reasoning_config.get("effort"):
|
||||
reasoning_effort = self.reasoning_config["effort"]
|
||||
|
||||
# Clamp effort levels not supported by the Responses API model.
|
||||
# GPT-5.4 supports none/low/medium/high/xhigh but not "minimal".
|
||||
# "minimal" is valid on OpenRouter and GPT-5 but fails on 5.2/5.4.
|
||||
_effort_clamp = {"minimal": "low"}
|
||||
reasoning_effort = _effort_clamp.get(reasoning_effort, reasoning_effort)
|
||||
|
||||
kwargs = {
|
||||
"model": self.model,
|
||||
"instructions": instructions,
|
||||
"input": self._chat_messages_to_responses_input(payload_messages),
|
||||
"tools": self._responses_tools(),
|
||||
"tool_choice": "auto",
|
||||
"parallel_tool_calls": True,
|
||||
"store": False,
|
||||
}
|
||||
|
||||
if not is_github_responses:
|
||||
kwargs["prompt_cache_key"] = self.session_id
|
||||
|
||||
is_xai_responses = self.provider == "xai" or self._base_url_hostname == "api.x.ai"
|
||||
|
||||
if reasoning_enabled and is_xai_responses:
|
||||
# xAI reasons automatically — no effort param, just include encrypted content
|
||||
kwargs["include"] = ["reasoning.encrypted_content"]
|
||||
elif reasoning_enabled:
|
||||
if is_github_responses:
|
||||
# Copilot's Responses route advertises reasoning-effort support,
|
||||
# but not OpenAI-specific prompt cache or encrypted reasoning
|
||||
# fields. Keep the payload to the documented subset.
|
||||
github_reasoning = self._github_models_reasoning_extra_body()
|
||||
if github_reasoning is not None:
|
||||
kwargs["reasoning"] = github_reasoning
|
||||
else:
|
||||
kwargs["reasoning"] = {"effort": reasoning_effort, "summary": "auto"}
|
||||
kwargs["include"] = ["reasoning.encrypted_content"]
|
||||
elif not is_github_responses and not is_xai_responses:
|
||||
kwargs["include"] = []
|
||||
|
||||
if self.request_overrides:
|
||||
kwargs.update(self.request_overrides)
|
||||
|
||||
if self.max_tokens is not None and not is_codex_backend:
|
||||
kwargs["max_output_tokens"] = self.max_tokens
|
||||
|
||||
if is_xai_responses and getattr(self, "session_id", None):
|
||||
kwargs["extra_headers"] = {"x-grok-conv-id": self.session_id}
|
||||
|
||||
return kwargs
|
||||
return _ct.build_kwargs(
|
||||
model=self.model,
|
||||
messages=api_messages,
|
||||
tools=self.tools,
|
||||
reasoning_config=self.reasoning_config,
|
||||
session_id=getattr(self, "session_id", None),
|
||||
max_tokens=self.max_tokens,
|
||||
request_overrides=self.request_overrides,
|
||||
is_github_responses=is_github_responses,
|
||||
is_codex_backend=is_codex_backend,
|
||||
is_xai_responses=is_xai_responses,
|
||||
github_reasoning_extra=self._github_models_reasoning_extra_body() if is_github_responses else None,
|
||||
)
|
||||
|
||||
sanitized_messages = api_messages
|
||||
needs_sanitization = False
|
||||
|
|
@ -7438,7 +7365,7 @@ class AIAgent:
|
|||
if not _aux_available and self.api_mode == "codex_responses":
|
||||
# No auxiliary client -- use the Codex Responses path directly
|
||||
codex_kwargs = self._build_api_kwargs(api_messages)
|
||||
codex_kwargs["tools"] = self._responses_tools([memory_tool_def])
|
||||
codex_kwargs["tools"] = self._get_codex_transport().convert_tools([memory_tool_def])
|
||||
if _flush_temperature is not None:
|
||||
codex_kwargs["temperature"] = _flush_temperature
|
||||
else:
|
||||
|
|
@ -7473,9 +7400,15 @@ class AIAgent:
|
|||
# Extract tool calls from the response, handling all API formats
|
||||
tool_calls = []
|
||||
if self.api_mode == "codex_responses" and not _aux_available:
|
||||
assistant_msg, _ = self._normalize_codex_response(response)
|
||||
if assistant_msg and assistant_msg.tool_calls:
|
||||
tool_calls = assistant_msg.tool_calls
|
||||
_ct_flush = self._get_codex_transport()
|
||||
_cnr_flush = _ct_flush.normalize_response(response)
|
||||
if _cnr_flush and _cnr_flush.tool_calls:
|
||||
tool_calls = [
|
||||
SimpleNamespace(
|
||||
id=tc.id, type="function",
|
||||
function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
|
||||
) for tc in _cnr_flush.tool_calls
|
||||
]
|
||||
elif self.api_mode == "anthropic_messages" and not _aux_available:
|
||||
_tfn = self._get_anthropic_transport()
|
||||
_flush_nr = _tfn.normalize_response(response, strip_tool_prefix=self._is_anthropic_oauth)
|
||||
|
|
@ -8519,8 +8452,9 @@ class AIAgent:
|
|||
codex_kwargs = self._build_api_kwargs(api_messages)
|
||||
codex_kwargs.pop("tools", None)
|
||||
summary_response = self._run_codex_stream(codex_kwargs)
|
||||
assistant_message, _ = self._normalize_codex_response(summary_response)
|
||||
final_response = (assistant_message.content or "").strip() if assistant_message else ""
|
||||
_ct_sum = self._get_codex_transport()
|
||||
_cnr_sum = _ct_sum.normalize_response(summary_response)
|
||||
final_response = (_cnr_sum.content or "").strip()
|
||||
else:
|
||||
summary_kwargs = {
|
||||
"model": self.model,
|
||||
|
|
@ -8577,8 +8511,9 @@ class AIAgent:
|
|||
codex_kwargs = self._build_api_kwargs(api_messages)
|
||||
codex_kwargs.pop("tools", None)
|
||||
retry_response = self._run_codex_stream(codex_kwargs)
|
||||
retry_msg, _ = self._normalize_codex_response(retry_response)
|
||||
final_response = (retry_msg.content or "").strip() if retry_msg else ""
|
||||
_ct_retry = self._get_codex_transport()
|
||||
_cnr_retry = _ct_retry.normalize_response(retry_response)
|
||||
final_response = (_cnr_retry.content or "").strip()
|
||||
elif self.api_mode == "anthropic_messages":
|
||||
_tretry = self._get_anthropic_transport()
|
||||
_ant_kw2 = _tretry.build_kwargs(model=self.model, messages=api_messages, tools=None,
|
||||
|
|
@ -9340,7 +9275,7 @@ class AIAgent:
|
|||
if self._force_ascii_payload:
|
||||
_sanitize_structure_non_ascii(api_kwargs)
|
||||
if self.api_mode == "codex_responses":
|
||||
api_kwargs = self._preflight_codex_api_kwargs(api_kwargs, allow_stream=False)
|
||||
api_kwargs = self._get_codex_transport().preflight_kwargs(api_kwargs, allow_stream=False)
|
||||
|
||||
try:
|
||||
from hermes_cli.plugins import invoke_hook as _invoke_hook
|
||||
|
|
@ -9428,38 +9363,34 @@ class AIAgent:
|
|||
response_invalid = False
|
||||
error_details = []
|
||||
if self.api_mode == "codex_responses":
|
||||
output_items = getattr(response, "output", None) if response is not None else None
|
||||
if response is None:
|
||||
response_invalid = True
|
||||
error_details.append("response is None")
|
||||
elif not isinstance(output_items, list):
|
||||
response_invalid = True
|
||||
error_details.append("response.output is not a list")
|
||||
elif not output_items:
|
||||
# Stream backfill may have failed, but
|
||||
# _normalize_codex_response can still recover
|
||||
# from response.output_text. Only mark invalid
|
||||
# when that fallback is also absent.
|
||||
_out_text = getattr(response, "output_text", None)
|
||||
_out_text_stripped = _out_text.strip() if isinstance(_out_text, str) else ""
|
||||
if _out_text_stripped:
|
||||
logger.debug(
|
||||
"Codex response.output is empty but output_text is present "
|
||||
"(%d chars); deferring to normalization.",
|
||||
len(_out_text_stripped),
|
||||
)
|
||||
else:
|
||||
_resp_status = getattr(response, "status", None)
|
||||
_resp_incomplete = getattr(response, "incomplete_details", None)
|
||||
logger.warning(
|
||||
"Codex response.output is empty after stream backfill "
|
||||
"(status=%s, incomplete_details=%s, model=%s). %s",
|
||||
_resp_status, _resp_incomplete,
|
||||
getattr(response, "model", None),
|
||||
f"api_mode={self.api_mode} provider={self.provider}",
|
||||
)
|
||||
_ct_v = self._get_codex_transport()
|
||||
if not _ct_v.validate_response(response):
|
||||
if response is None:
|
||||
response_invalid = True
|
||||
error_details.append("response.output is empty")
|
||||
error_details.append("response is None")
|
||||
else:
|
||||
# output_text fallback: stream backfill may have failed
|
||||
# but normalize can still recover from output_text
|
||||
_out_text = getattr(response, "output_text", None)
|
||||
_out_text_stripped = _out_text.strip() if isinstance(_out_text, str) else ""
|
||||
if _out_text_stripped:
|
||||
logger.debug(
|
||||
"Codex response.output is empty but output_text is present "
|
||||
"(%d chars); deferring to normalization.",
|
||||
len(_out_text_stripped),
|
||||
)
|
||||
else:
|
||||
_resp_status = getattr(response, "status", None)
|
||||
_resp_incomplete = getattr(response, "incomplete_details", None)
|
||||
logger.warning(
|
||||
"Codex response.output is empty after stream backfill "
|
||||
"(status=%s, incomplete_details=%s, model=%s). %s",
|
||||
_resp_status, _resp_incomplete,
|
||||
getattr(response, "model", None),
|
||||
f"api_mode={self.api_mode} provider={self.provider}",
|
||||
)
|
||||
response_invalid = True
|
||||
error_details.append("response.output is empty")
|
||||
elif self.api_mode == "anthropic_messages":
|
||||
_tv = self._get_anthropic_transport()
|
||||
if not _tv.validate_response(response):
|
||||
|
|
@ -10885,7 +10816,40 @@ class AIAgent:
|
|||
|
||||
try:
|
||||
if self.api_mode == "codex_responses":
|
||||
assistant_message, finish_reason = self._normalize_codex_response(response)
|
||||
_ct = self._get_codex_transport()
|
||||
_cnr = _ct.normalize_response(response)
|
||||
# Back-compat shim: downstream expects SimpleNamespace with
|
||||
# codex-specific fields (.codex_reasoning_items, .reasoning_details,
|
||||
# and .call_id/.response_item_id on tool calls).
|
||||
_tc_list = None
|
||||
if _cnr.tool_calls:
|
||||
_tc_list = []
|
||||
for tc in _cnr.tool_calls:
|
||||
_tc_ns = SimpleNamespace(
|
||||
id=tc.id, type="function",
|
||||
function=SimpleNamespace(name=tc.name, arguments=tc.arguments),
|
||||
)
|
||||
if tc.provider_data:
|
||||
if tc.provider_data.get("call_id"):
|
||||
_tc_ns.call_id = tc.provider_data["call_id"]
|
||||
if tc.provider_data.get("response_item_id"):
|
||||
_tc_ns.response_item_id = tc.provider_data["response_item_id"]
|
||||
_tc_list.append(_tc_ns)
|
||||
assistant_message = SimpleNamespace(
|
||||
content=_cnr.content,
|
||||
tool_calls=_tc_list or None,
|
||||
reasoning=_cnr.reasoning,
|
||||
reasoning_content=None,
|
||||
codex_reasoning_items=(
|
||||
_cnr.provider_data.get("codex_reasoning_items")
|
||||
if _cnr.provider_data else None
|
||||
),
|
||||
reasoning_details=(
|
||||
_cnr.provider_data.get("reasoning_details")
|
||||
if _cnr.provider_data else None
|
||||
),
|
||||
)
|
||||
finish_reason = _cnr.finish_reason
|
||||
elif self.api_mode == "anthropic_messages":
|
||||
_transport = self._get_anthropic_transport()
|
||||
_nr = _transport.normalize_response(
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue