Agent Zero AI framework
Tighten context doctor usable-response detection
linkliti093b9106ef09
diff --git a/plugins/_context_doctor/AGENTS.md b/plugins/_context_doctor/AGENTS.mdindex 9dd0de858..3f4f59cee 100644--- a/plugins/_context_doctor/AGENTS.md+++ b/plugins/_context_doctor/AGENTS.md@@ -18,7 +18,7 @@- Repaired and fallback JSON is always minified.- 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). This rewrites model-authored thoughts for every repaired turn by design, not only the raw-text fallback branch.-- `looks_like_tool_call` returns True when the transformed output is a dict containing at least one A0 key (thoughts/headline/tool_name/tool_args). Empty dicts or dicts without any A0 key fall through to the raw-text fallback branch.+- `looks_like_tool_call` returns True only when the transformed output is a dict containing at least one A0 key (thoughts/headline/tool_name/tool_args) with a usable non-empty value: non-empty list of non-empty strings for `thoughts`, non-empty string for `headline`/`tool_name`, non-empty dict for `tool_args`. Empty dicts, missing keys, or keys with empty/blank values fall through to the raw-text fallback branch.- 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`.diff --git a/plugins/_context_doctor/extensions/python/message_loop_result/_10_context_doctor.py b/plugins/_context_doctor/extensions/python/message_loop_result/_10_context_doctor.pyindex 5fa677521..2b788438f 100644--- a/plugins/_context_doctor/extensions/python/message_loop_result/_10_context_doctor.py+++ b/plugins/_context_doctor/extensions/python/message_loop_result/_10_context_doctor.py@@ -24,7 +24,7 @@ class ContextDoctor(Extension):# Extract LLM responsellm_result = result_data.get("llm_result")response = getattr(llm_result, "response", None)- if not isinstance(response, str) or not response:+ if not isinstance(response, str) or not response.strip():return# Repair response before default processingdiff --git a/plugins/_context_doctor/helpers/context_doctor.py b/plugins/_context_doctor/helpers/context_doctor.pyindex 52e24df75..fd0f28b91 100644--- a/plugins/_context_doctor/helpers/context_doctor.py+++ b/plugins/_context_doctor/helpers/context_doctor.py@@ -136,7 +136,7 @@ def transform_response(def looks_like_tool_call(response: str, transformed: str) -> bool:- """Return True if transformed output is a valid A0 response JSON."""+ """Return True if transformed output is a JSON with usable A0 content."""if not response:return Falsetry:@@ -145,7 +145,25 @@ def looks_like_tool_call(response: str, transformed: str) -> bool:return Falseif not isinstance(parsed, dict) or not parsed:return False- return any(k in parsed for k in ("thoughts", "headline", "tool_name", "tool_args"))++ for key in ("thoughts", "headline", "tool_name", "tool_args"):+ if key not in parsed:+ continue+ value = parsed[key]+ if key == "thoughts":+ if (+ isinstance(value, list)+ and value+ and all(isinstance(item, str) and item.strip() for item in value)+ ):+ return True+ elif key in ("headline", "tool_name"):+ if isinstance(value, str) and value.strip():+ return True+ elif key == "tool_args":+ if isinstance(value, dict) and value:+ return True+ return Falsedef update_log_item(diff --git a/plugins/_context_doctor/tests/test_context_doctor.py b/plugins/_context_doctor/tests/test_context_doctor.pyindex 584563bf5..93ea78e0a 100644--- a/plugins/_context_doctor/tests/test_context_doctor.py+++ b/plugins/_context_doctor/tests/test_context_doctor.py@@ -138,6 +138,30 @@ def test_looks_like_tool_call_rejects_non_a0_dict():assert not looks_like_tool_call('{"foo":"bar"}', '{"foo":"bar"}')+def test_looks_like_tool_call_rejects_empty_thoughts_list():+ assert not looks_like_tool_call('{"thoughts":[]}', '{"thoughts":[]}')+++def test_looks_like_tool_call_rejects_blank_thoughts_entries():+ assert not looks_like_tool_call('{"thoughts":[""," "]}', '{"thoughts":[""," "]}')+++def test_looks_like_tool_call_rejects_empty_headline():+ assert not looks_like_tool_call('{"headline":""}', '{"headline":""}')+++def test_looks_like_tool_call_rejects_empty_tool_name():+ assert not looks_like_tool_call('{"tool_name":""}', '{"tool_name":""}')+++def test_looks_like_tool_call_rejects_empty_tool_args():+ assert not looks_like_tool_call('{"tool_args":{}}', '{"tool_args":{}}')+++def test_looks_like_tool_call_rejects_wrong_thoughts_type():+ assert not looks_like_tool_call('{"thoughts":"x"}', '{"thoughts":"x"}')++def test_extension_replaces_result_refreshes_log_and_response_item(monkeypatch):monkeypatch.setattr("plugins._context_doctor.extensions.python.message_loop_result._10_context_doctor.get_plugin_config",