feat(assistant): #91 steps humains en direct + outils web_search/fetch_url (labels backend, SSE step, garde SSRF)

backend/agent/loop.py

@@ -30,6 +30,7 @@ from backend.tools.api import (
     call_tool,
     get_tool_schemas,
 )
+from backend.tools.labels import thought_step_label, tool_step_label
 
 logger = logging.getLogger("obsigate.agent.loop")
 
@@ -54,6 +55,9 @@ class ToolCallRecord:
     arguments: dict[str, Any]
     ok: bool
     result: Any
+    # Human-readable « step » label for the Notion-style UI
+    # ({key, params} — see backend.tools.labels).
+    step: dict[str, Any] = field(default_factory=dict)
 
 
 @dataclass
@@ -63,6 +67,9 @@ class AgentResult:
     content: str = ""
     messages: list[dict[str, Any]] = field(default_factory=list)
     tool_calls: list[ToolCallRecord] = field(default_factory=list)
+    # Ordered Notion-style step descriptors ({key, params}); tool steps and
+    # intermediate reasoning notes interleaved by execution order.
+    steps: list[dict[str, Any]] = field(default_factory=list)
     iterations: int = 0
     stopped: str = STOP_DONE
     pending: dict[str, Any] | None = None
@@ -142,7 +149,10 @@ def _execute_confirmed(
         payload = e.to_dict()
         ok = False
 
-    record = ToolCallRecord(name=name, arguments=arguments, ok=ok, result=payload)
+    record = ToolCallRecord(
+        name=name, arguments=arguments, ok=ok, result=payload,
+        step=tool_step_label(name, arguments),
+    )
     executed.append(record)
     if on_tool_call is not None:
         on_tool_call(record)
@@ -164,6 +174,7 @@ async def run_agent(
     max_iterations: int = DEFAULT_MAX_ITERATIONS,
     max_tool_calls: int | None = None,
     on_tool_call: Callable[[ToolCallRecord], None] | None = None,
+    on_thought: Callable[[dict[str, Any]], None] | None = None,
     resume_messages: list[dict[str, Any]] | None = None,
     confirm_pending: dict[str, Any] | None = None,
 ) -> AgentResult:
@@ -195,6 +206,15 @@ async def run_agent(
     if tools is None:
         tools = get_tool_schemas(scope=ToolScope.IN_APP)
     quota = DEFAULT_MAX_TOOL_CALLS if max_tool_calls is None else max_tool_calls
+    steps: list[dict[str, Any]] = []
+
+    def _emit_note(text: str) -> None:
+        """Record an intermediate reasoning note as a visible step."""
+        note = thought_step_label(text)
+        if note["params"]["value"]:
+            steps.append(note)
+            if on_thought is not None:
+                on_thought(note)
 
     convo = [dict(m) for m in (resume_messages if resume_messages is not None else messages)]
     executed: list[ToolCallRecord] = []
@@ -205,6 +225,7 @@ async def run_agent(
                 content="",
                 messages=convo,
                 tool_calls=executed,
+                steps=steps,
                 iterations=0,
                 stopped=STOP_QUOTA_EXCEEDED,
             )
@@ -218,10 +239,13 @@ async def run_agent(
                 content=response.content or "",
                 messages=convo,
                 tool_calls=executed,
+                steps=steps,
                 iterations=iteration,
                 stopped=STOP_DONE,
             )
 
+        # Intermediate reasoning shown alongside tool calls → a "thought" step.
+        _emit_note(response.content or "")
         convo.append(_assistant_tool_message(response.content, response.tool_calls))
 
         for call in response.tool_calls:
@@ -231,6 +255,7 @@ async def run_agent(
                     content=response.content or "",
                     messages=convo,
                     tool_calls=executed,
+                    steps=steps,
                     iterations=iteration,
                     stopped=STOP_QUOTA_EXCEEDED,
                 )
@@ -247,6 +272,7 @@ async def run_agent(
                     content=response.content or "",
                     messages=convo,
                     tool_calls=executed,
+                    steps=steps,
                     iterations=iteration,
                     stopped=STOP_CONFIRMATION_REQUIRED,
                     pending=pending,
@@ -255,8 +281,12 @@ async def run_agent(
                 payload = e.to_dict()
                 ok = False
 
-            record = ToolCallRecord(name=call.name, arguments=call.arguments, ok=ok, result=payload)
+            record = ToolCallRecord(
+                name=call.name, arguments=call.arguments, ok=ok, result=payload,
+                step=tool_step_label(call.name, call.arguments),
+            )
             executed.append(record)
+            steps.append(record.step)
             if on_tool_call is not None:
                 on_tool_call(record)
 
@@ -272,6 +302,7 @@ async def run_agent(
         content="",
         messages=convo,
         tool_calls=executed,
+        steps=steps,
         iterations=max_iterations,
         stopped=STOP_MAX_ITERATIONS,
     )