feat(ai): durcissement phase F (#79) - rate limit, redaction, OpenAPI/MCP, E2E

backend/agent/loop.py

@@ -17,6 +17,7 @@ from __future__ import annotations
 
 import json
 import logging
+import os
 from collections.abc import Callable
 from dataclasses import dataclass, field
 from typing import Any
@@ -35,11 +36,14 @@ logger = logging.getLogger("obsigate.agent.loop")
 DEFAULT_MAX_ITERATIONS = 10
 # Cap the size of a tool result fed back to the model (chars).
 MAX_TOOL_RESULT_CHARS = 100_000
+# Quota: maximum tool calls executed per agent run (``BOOKSLM_MAX_TOOL_CALLS``).
+DEFAULT_MAX_TOOL_CALLS = int(os.environ.get("BOOKSLM_MAX_TOOL_CALLS", "25"))
 
 # Stopping reasons
 STOP_DONE = "done"
 STOP_MAX_ITERATIONS = "max_iterations"
 STOP_CONFIRMATION_REQUIRED = "confirmation_required"
+STOP_QUOTA_EXCEEDED = "quota_exceeded"
 
 
 @dataclass
@@ -158,6 +162,7 @@ async def run_agent(
     llm: Callable[..., Any] | None = None,
     tools: list[dict[str, Any]] | None = None,
     max_iterations: int = DEFAULT_MAX_ITERATIONS,
+    max_tool_calls: int | None = None,
     on_tool_call: Callable[[ToolCallRecord], None] | None = None,
     resume_messages: list[dict[str, Any]] | None = None,
     confirm_pending: dict[str, Any] | None = None,
@@ -173,6 +178,8 @@ async def run_agent(
         tools: Tool schemas to expose. ``None`` exposes all in-app tools;
             pass ``[]`` to disable tool calling (plain chat).
         max_iterations: Hard cap on LLM round-trips.
+        max_tool_calls: Hard cap on the total number of executed tool calls
+            (quota, defaults to ``BOOKSLM_MAX_TOOL_CALLS``).
         on_tool_call: Optional callback invoked after each executed tool call.
         resume_messages: Conversation snapshot from a paused run (returned with
             a ``confirmation`` event). When set, the loop resumes from it.
@@ -187,11 +194,20 @@ async def run_agent(
     llm = llm or provider_llm
     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
 
     convo = [dict(m) for m in (resume_messages if resume_messages is not None else messages)]
     executed: list[ToolCallRecord] = []
 
     if confirm_pending:
+        if quota is not None and len(executed) >= quota:
+            return AgentResult(
+                content="",
+                messages=convo,
+                tool_calls=executed,
+                iterations=0,
+                stopped=STOP_QUOTA_EXCEEDED,
+            )
         _execute_confirmed(ctx, confirm_pending, convo, executed, on_tool_call)
 
     for iteration in range(1, max_iterations + 1):
@@ -209,6 +225,15 @@ async def run_agent(
         convo.append(_assistant_tool_message(response.content, response.tool_calls))
 
         for call in response.tool_calls:
+            if quota is not None and len(executed) >= quota:
+                logger.warning(f"Agent reached the tool-call quota ({quota})")
+                return AgentResult(
+                    content=response.content or "",
+                    messages=convo,
+                    tool_calls=executed,
+                    iterations=iteration,
+                    stopped=STOP_QUOTA_EXCEEDED,
+                )
             try:
                 result = call_tool(call.name, ctx, call.arguments)
                 payload = result.data