feat(agents): enforce one librarian timeout budget

- add LIBRARIAN_TIMEOUT config (default 180s) and enforce it with
  asyncio.wait_for inside delegate_to_librarian, covering the live
  paths (steward direct delegation and SSE streaming) that had no cap
- timeouts fail honestly: success=False with a curated butler sentence,
  detail in logs
- set an explicit timeout on TatlockOllamaProvider's AsyncOpenAI client
  from OLLAMA_TIMEOUT instead of the SDK default (~600s per LLM call)
- remove the contradictory unused 60s default from
  AgentRequest.timeout_seconds; coordination falls back to the
  configured budget

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/agents/protocol.py

@@ -6,7 +6,7 @@ Defines standardized request/response formats for communication between:
 - Tatlock (coordination) → Expert agents (Librarian, Developer, etc.)
 """
 from enum import Enum
-from typing import Any, Optional
+from typing import Any
 
 from pydantic import BaseModel, Field
 
@@ -53,13 +53,16 @@ class AgentRequest(BaseModel):
         default="default",
         description="User identifier for multi-tenant operations"
     )
-    max_tokens: Optional[int] = Field(
+    max_tokens: int | None = Field(
         default=None,
         description="Optional token limit for response"
     )
-    timeout_seconds: Optional[int] = Field(
-        default=60,
-        description="Maximum time for task completion"
+    timeout_seconds: int | None = Field(
+        default=None,
+        description=(
+            "Maximum time for task completion; None uses the configured "
+            "expert budget (LIBRARIAN_TIMEOUT)"
+        )
     )
 
 
@@ -103,7 +106,7 @@ class AgentResponse(BaseModel):
         default_factory=list,
         description="Sources or references used"
     )
-    error_message: Optional[str] = Field(
+    error_message: str | None = Field(
         default=None,
         description="Error details if success=False"
     )