Skip to content

Agent Zero AI framework

Own Responses-API state advancement in hist_add_ai_response

linkliti4634070e95a8
diff --git a/AGENTS.md b/AGENTS.md
index 4b0545add..9a790fff9 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -15,6 +15,7 @@
## Root Ownership
- `agent.py` owns `Agent`, `AgentContext`, and loop data.
+- `Agent.hist_add_ai_response` owns Responses-API state advancement: it calls `_remember_llm_result_state` internally and requires an `LLMResult` (empty for non-LLM turns like greetings or intervention progress). Callers must not invoke `_remember_llm_result_state` manually.
- `initialize.py` owns framework initialization.
- `models.py` owns model-provider configuration and LiteLLM integration.
- `run_ui.py` is the WebUI entry point.
diff --git a/agent.py b/agent.py
index fa5308c88..e4f00ed6b 100644
--- a/agent.py
+++ b/agent.py
@@ -532,7 +532,6 @@ class Agent:
id=log_item.id if log_item else "",
llm_result=llm_result,
)
- self._remember_llm_result_state(llm_result, assistant_message)
tools_result = await self.process_llm_result_tools(llm_result)
if tools_result: # final response of message loop available
return tools_result # break the execution if the task is done
@@ -771,16 +770,18 @@ class Agent:
@extension.extensible
def hist_add_ai_response(
- self, message: str, id: str = "", llm_result: LLMResult | None = None
+ self, message: str, llm_result: LLMResult, id: str = ""
):
self.loop_data.last_response = message
content = self.parse_prompt("fw.ai_response.md", message=message)
- return self.hist_add_message(
+ msg = self.hist_add_message(
True,
content=content,
id=id,
metadata=metadata_from_llm_result(llm_result),
)
+ self._remember_llm_result_state(llm_result, msg)
+ return msg
@extension.extensible
def hist_add_warning(self, message: history.MessageContent, id: str = ""):
@@ -1098,7 +1099,7 @@ class Agent:
self.hist_add_tool_result(last_tool.name, tool_progress)
last_tool.set_progress(None)
if progress.strip():
- self.hist_add_ai_response(progress)
+ self.hist_add_ai_response(progress, llm_result=LLMResult())
# append the intervention message
self.hist_add_user_message(msg, intervention=True)
raise InterventionException(msg)
diff --git a/extensions/python/agent_init/AGENTS.md b/extensions/python/agent_init/AGENTS.md
index c8c64d17b..7bf26fd03 100644
--- a/extensions/python/agent_init/AGENTS.md
+++ b/extensions/python/agent_init/AGENTS.md
@@ -14,6 +14,7 @@
- Preserve ordering between initial message creation and profile settings loading.
- Keep a placeholder user turn (`fw.initial_user_message.md`) ahead of the AI greeting (`fw.initial_message.md`) so `output_langchain` never pops the greeting as a leading `AIMessage`; do not remove either prompt without replacing the turn-order guarantee.
- Minify the initial AI message JSON before storage; preserve raw text as the displayed greeting when JSON parsing fails.
+- `_10_initial_message.py` passes an empty `LLMResult()` to `hist_add_ai_response` so the Responses-API state seam runs uniformly; the empty result carries no `response_id`, so state advancement is a no-op for the greeting turn.
## Work Guidance
diff --git a/extensions/python/agent_init/_10_initial_message.py b/extensions/python/agent_init/_10_initial_message.py
index a017db2dc..5d1a2bcec 100644
--- a/extensions/python/agent_init/_10_initial_message.py
+++ b/extensions/python/agent_init/_10_initial_message.py
@@ -1,6 +1,7 @@
import json
from agent import LoopData, UserMessage
from helpers.extension import Extension
+from helpers.llm_result import LLMResult
class InitialMessage(Extension):
@@ -40,7 +41,7 @@ class InitialMessage(Extension):
self.agent.loop_data = LoopData(user_message=None)
# Add the message to history as an AI response
- msg = self.agent.hist_add_ai_response(initial_message)
+ msg = self.agent.hist_add_ai_response(initial_message, llm_result=LLMResult())
# Add to log (green bubble) for immediate UI display
self.agent.context.log.log(
diff --git a/extensions/python/message_loop_result/AGENTS.md b/extensions/python/message_loop_result/AGENTS.md
index f87835d35..f88bbef8e 100644
--- a/extensions/python/message_loop_result/AGENTS.md
+++ b/extensions/python/message_loop_result/AGENTS.md
@@ -9,7 +9,7 @@
- Extensions receive mutable `result_data` with `llm_result` and may set `skip_default_processing` after fully handling the turn.
- `_20_empty_response.py` retries fully empty turns (no response and no reasoning): count them toward the unusable-response limit without adding a warning to model history, and use `fw.msg_empty_response.md` for agent-prefixed UI warning text only.
- `_20_empty_response.py` retries reasoning-only turns: add an agent-facing `fw.msg_reasoning_only.md` history warning with a separate `fw.msg_reasoning_only_response.md` user notice, and count them through the stop-unusable-response-loop extension.
-- `_30_repeat_response.py` retries response content that exactly matches `loop_data.last_response`, regardless of reasoning, using `fw.msg_repeat.md` for history and `fw.msg_repeat_response.md` for the agent-prefixed UI warning text.
+- `_30_repeat_response.py` retries response content that exactly matches `loop_data.last_response`, regardless of reasoning, using `fw.msg_repeat.md` for history and `fw.msg_repeat_response.md` for the agent-prefixed UI warning text. State advancement is owned by `hist_add_ai_response`; do not call `_remember_llm_result_state` manually.
## Local Contracts
diff --git a/extensions/python/message_loop_result/_30_repeat_response.py b/extensions/python/message_loop_result/_30_repeat_response.py
index 45457ff82..4b4e09ba7 100644
--- a/extensions/python/message_loop_result/_30_repeat_response.py
+++ b/extensions/python/message_loop_result/_30_repeat_response.py
@@ -27,7 +27,6 @@ class RepeatResponse(Extension):
id=log_item.id if log_item else "",
llm_result=llm_result,
)
- self.agent._remember_llm_result_state(llm_result, assistant_message)
warning_message = self.agent.hist_add_warning(message=warning)
PrintStyle(font_color="orange", padding=True).print(warning)
self.agent.context.log.log(
diff --git a/plugins/_context_doctor/AGENTS.md b/plugins/_context_doctor/AGENTS.md
index b55a331b8..d2624c457 100644
--- a/plugins/_context_doctor/AGENTS.md
+++ b/plugins/_context_doctor/AGENTS.md
@@ -19,6 +19,7 @@
- Nonempty non-tool output becomes `{"thoughts":[raw]}`; XML-like output becomes `{}` only when suppression is enabled.
- Blank-line-separated thoughts expand into separate entries after repair when the split strategy is enabled (default on).
- A raw-text fallback conversion must emit a `fw.msg_thoughts_fallback.md` history warning and a separate `fw.msg_thoughts_fallback_response.md` user notice, refresh the generating log and response item with the transformed thoughts JSON, and set `skip_default_processing` so the retry advances the unusable-response counter.
+- The fallback passes the repaired `llm_result` to `hist_add_ai_response`, which owns Responses-API state advancement (`_remember_llm_result_state`); do not call the state method directly. The fallback turn's `response_id` is recorded so the next turn's `previous_response_id` chain stays intact.
- The fallback warning is counted by the core stop-unusable-response loop alongside `fw.msg_misformat.md`, `fw.msg_repeat.md`, `fw.msg_empty_response.md`, and `fw.msg_reasoning_only.md`.
- Log kvps retain streamed `reasoning` and `thoughts`, then add transformed output; `update_log` controls only View Details content.
- A repaired `response` tool call refreshes the response log item when streaming did not create it.