feat: surface task execution progress across Host Agent and Cloud

Host Agent now persists step-level execution detail locally (via a real
TaskMetadataStore/Timeline wired into TaskRunner) and reports a bounded
in-progress snapshot piggybacked on lease renewal. Cloud persists that
snapshot per active assignment and exposes it through the existing task
list/detail query path; Cloud Console renders it as a live badge. Host
Agent's local console gains authenticated, read-only task list and
detail/timeline pages (same-origin, server-rendered) with inlined
screenshots.

Also fixes a pre-existing gap in the shared Timeline: the actual
per-step LLM prompt is now recorded instead of the task goal, benefiting
both Runtime and Host Agent consoles. When a host uses the cloud planner
transport, each decide call's prompt and resulting tool decision are
durably logged in a new planner_decision_log table (with bounded
retention) and browsable from Cloud Console; direct-transport hosts
explicitly surface a "not reported" state.

Includes Alembic migrations 0008 (progress columns on scheduled_tasks)
and 0009 (planner_decision_log), bounded Host-Agent-local retention,
dual-backend repository parity, and Vitest + pytest coverage. Task 6.5
(manual end-to-end device verification) remains.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

runtime/tool_calling_client.py

@@ -25,6 +25,11 @@ class ToolCallDecision:
     tool_name: str
     arguments: dict[str, Any]
     usage: ToolCallUsage | None = None
+    # The actual prompts sent to the LLM for this call. Populated by the
+    # built-in Anthropic/OpenAI clients; empty for clients (e.g.
+    # CloudProxyToolCallingClient) that don't surface them.
+    system_prompt: str = ""
+    user_prompt: str = ""
 
 
 class ToolCallingClient(Protocol):
@@ -72,7 +77,11 @@ class AnthropicToolCallingClient:
                 tools,
                 timeout=timeout,
             )
-            return _decision_from_anthropic_response(response)
+            return _decision_from_anthropic_response(
+                response,
+                system_prompt=system_prompt,
+                user_prompt=user_prompt,
+            )
         except ToolCallUnavailable:
             raise
         except Exception as exc:
@@ -164,7 +173,11 @@ class OpenAIToolCallingClient:
                 tools,
                 timeout=timeout,
             )
-            return _decision_from_openai_response(response)
+            return _decision_from_openai_response(
+                response,
+                system_prompt=system_prompt,
+                user_prompt=user_prompt,
+            )
         except ToolCallUnavailable:
             raise
         except Exception as exc:
@@ -250,7 +263,12 @@ def _anthropic_tool(spec: ToolSpec) -> dict[str, Any]:
     }
 
 
-def _decision_from_anthropic_response(response: Any) -> ToolCallDecision:
+def _decision_from_anthropic_response(
+    response: Any,
+    *,
+    system_prompt: str = "",
+    user_prompt: str = "",
+) -> ToolCallDecision:
     content = _value(response, "content")
     if not isinstance(content, list):
         raise ValueError("anthropic tool-call response missing content list")
@@ -264,6 +282,8 @@ def _decision_from_anthropic_response(response: Any) -> ToolCallDecision:
                 tool_name=name,
                 arguments=arguments,
                 usage=_anthropic_usage(response),
+                system_prompt=system_prompt,
+                user_prompt=user_prompt,
             )
     raise ValueError("anthropic response did not include a tool_use block")
 
@@ -295,7 +315,12 @@ def _openai_tool(spec: ToolSpec) -> dict[str, Any]:
     }
 
 
-def _decision_from_openai_response(response: Any) -> ToolCallDecision:
+def _decision_from_openai_response(
+    response: Any,
+    *,
+    system_prompt: str = "",
+    user_prompt: str = "",
+) -> ToolCallDecision:
     choices = _value(response, "choices")
     if not isinstance(choices, list) or not choices:
         raise ValueError("openai tool-call response missing choices")
@@ -312,6 +337,8 @@ def _decision_from_openai_response(response: Any) -> ToolCallDecision:
         tool_name=name,
         arguments=arguments,
         usage=_openai_usage(response),
+        system_prompt=system_prompt,
+        user_prompt=user_prompt,
     )