fix(showcase): ms-agent-python D6 residuals (toolCallId strip, fixtures, hitl pages, multimodal)

Port the replay-safe toolCallId stripping middleware from the ms-agent-dotnet
sibling route.ts so HITL/interrupt demos match toolCallId-keyed aimock
fixtures across the 2nd-turn request. The strip walks every inbound message
(role=tool, role=assistant.toolCalls[].id, toolCallId, tool_call_id) before
the AG-UI HttpAgent forwards them onto the FastAPI backend, and the outbound
event stream rewrites toolCallId on TOOL_CALL_* events to embed the
deterministic per-run suffix so the next turn's fixture matcher still
keys on the original (suffix-stripped) id.

Wraps the human_in_the_loop, interrupt-adapted, hitl-in-app, and
hitl-in-chat agents with the new replay-safe middleware. Adds gen-ui-agent
set_steps state-snapshot synthesis, readonly-state-agent-context system
message injection, and shared-state-read-write preference-as-system
injection — all ported verbatim from the dotnet sibling so the per-agent
shaping behavior is identical across the MAF runtimes.

chat-slots.json: add the turnIndex:1 "Give me a fun fact" fixture mirrored
from langgraph-python/chat-slots.json so the chat-slots.spec.ts second-
turn assertion ("second assistant turn is also wrapped in the custom
slot") gets a deterministic reply instead of falling through to headless-
simple's fun-fact fixture or the live proxy.

hitl-in-app and hitl-in-chat demo pages were already mirrored from LGP
(only a minor consumerAgentId addition on the in-app suggestions module).
No frontend page changes needed.

The B2 header-forwarding conveyance in src/agents/_header_forwarding.py
is untouched and verified intact (httpx hook + Starlette HTTP middleware
plus ContextVar bridge).

Multimodal diagnosis: the 5-test multimodal.spec.ts timeout is NOT a
routing/wiring gap. The agent_server.py mounts /multimodal FIRST (before
the catch-all "/"), the dedicated Next.js route /api/copilotkit-multimodal
registers the HttpAgent under "multimodal-demo", and the page wires
runtimeUrl + agent correctly. The multimodal fixture's userMessage
"describe the sample image" is the same stale phrasing LGP uses (which
passes at 185/0/2 — the test asserts a /image/i regex on the assistant
transcript, so fallthrough to the proxy still satisfies it). The
remaining suspects are (a) agent_framework_ag_ui's AG-UI -> AF adapter
mishandling inbound `binary` content parts, (b) the dual chat_client
init pattern (multimodal_chat_client built after the global httpx hook
is installed — the hook is idempotent so this should be safe), or
(c) >30s real-OpenAI vision latency under D6 record-replay. Capture
agent_server stderr during a single multimodal run to confirm.

Author: jpr5

showcase/aimock/d6/ms-agent-python/chat-slots.json

@@ -15,6 +15,17 @@
       "response": {
         "content": "Confirmed — the chat-slots demo is rendering through the custom slot wrappers. The CustomAssistantMessage component should be visible as a tinted card with a 'slot' badge in the corner."
       }
+    },
+    {
+      "_comment": "chat-slots e2e (chat-slots.spec.ts:90 'second assistant turn is also wrapped in the custom slot') — turn 2 prompt after the 'Say hello in one short sentence' first turn. Without this fixture aimock has no match for turn 2 and the second assistant slot never mounts. turnIndex:1 is REQUIRED to avoid stealing headless-simple's turn-0 fun-fact prompt (which resolves to a different deterministic reply in headless-simple.json).",
+      "match": {
+        "userMessage": "Give me a fun fact",
+        "turnIndex": 1,
+        "context": "ms-agent-python"
+      },
+      "response": {
+        "content": "Sure — sea otters hold hands while they sleep so they don't drift apart on the current."
+      }
     }
   ]
-}
+}