fix: 速度胶囊每轮只显示一次 + 技能调用按 run 合并统计

速度胶囊：原本每条 AI 消息都渲染，agentic 多轮 LLM 调用会出现多个胶囊。改为只在每轮 turn-final 消息（下一条 human 之前的最后一条 AI 消息）显示。

技能统计：tool_call_metrics 改为按 (run_id, skill_name) upsert 合并——同一 run 内同一技能的多次调用/重试合并为一行；任一成功即记成功，全部失败则记一行 error 并累积所有报错信息；非技能调用不受影响。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

offline-backend-20260512/backend/CLAUDE.md

@@ -173,7 +173,7 @@ Lead-agent middlewares are assembled in strict append order across `packages/har
 16. **SubagentLimitMiddleware** - Truncates excess `task` tool calls from model response to enforce `MAX_CONCURRENT_SUBAGENTS` limit (optional, if `subagent_enabled`)
 17. **LoopDetectionMiddleware** - Detects repeated tool-call loops; hard-stop responses clear both structured `tool_calls` and raw provider tool-call metadata before forcing a final text answer
 18. **ClarificationMiddleware** - Intercepts `ask_clarification` tool calls, interrupts via `Command(goto=END)` (must be last)
-8a. **ToolMetricsMiddleware** - Appended immediately after `ToolErrorHandlingMiddleware` in `_build_runtime_middlewares`, so it sits *deepest* in the `wrap_tool_call` chain. Records one `tool_call_metrics` row per tool/skill/MCP invocation — timing duration and bucketing failures into a coarse `error_category` (rate_limited / ip_blocked / auth_error / timeout / network_error / not_found / empty_result / tool_error). It catches both raised exceptions (before #8 converts them) and *self-handled* errors returned as error `ToolMessage`s (search tools that swallow HTTP 429/403). It also captures the targeted Agent Skill into `tool_call_metrics.skill_name`: the lead agent invokes a skill by `read_file`-ing its `/mnt/skills/<category>/<name>/SKILL.md` path (per the `<skill_system>` prompt block — there is no dedicated "use skill" tool), so `skill_name` is recovered by scanning every tool call's string arguments for the `skills/{public,custom}/{name}/` path shape (`_SKILL_PATH_RE`), plus the explicit `name` argument of `skill_view`/`skill_manage`/`skill_archive`. `skill_view`-specific success detection handles its swallowed failures (`Skill 'x' not found.` returned as a plain string rather than raised). Regression coverage: `tests/test_tool_metrics_middleware.py`. Writes are best-effort fire-and-forget. Surfaced by the admin `GET /api/admin/tool-metrics` router (which has a `kind=skill` filter and a per-skill `/summary` breakdown).
+8a. **ToolMetricsMiddleware** - Appended immediately after `ToolErrorHandlingMiddleware` in `_build_runtime_middlewares`, so it sits *deepest* in the `wrap_tool_call` chain. Records one `tool_call_metrics` row per tool/skill/MCP invocation — timing duration and bucketing failures into a coarse `error_category` (rate_limited / ip_blocked / auth_error / timeout / network_error / not_found / empty_result / tool_error). It catches both raised exceptions (before #8 converts them) and *self-handled* errors returned as error `ToolMessage`s (search tools that swallow HTTP 429/403). It also captures the targeted Agent Skill into `tool_call_metrics.skill_name`: the lead agent invokes a skill by `read_file`-ing its `/mnt/skills/<category>/<name>/SKILL.md` path (per the `<skill_system>` prompt block — there is no dedicated "use skill" tool), so `skill_name` is recovered by scanning every tool call's string arguments for the `skills/{public,custom}/{name}/` path shape (`_SKILL_PATH_RE`), plus the explicit `name` argument of `skill_view`/`skill_manage`/`skill_archive`. `skill_view`-specific success detection handles its swallowed failures (`Skill 'x' not found.` returned as a plain string rather than raised). Regression coverage: `tests/test_tool_metrics_middleware.py`. Writes are best-effort fire-and-forget. **Per-run skill merging**: `SqlToolMetricsStore.record` upserts skill rows by `(run_id, skill_name)` instead of inserting one row per call — a skill touched by several tool calls / retries inside one run collapses to a single row. Any success in the run wins (a skill that failed then finally succeeded is recorded as one `success`); a skill that only ever failed yields one `error` row whose `error_message` accumulates every attempt's message; durations are summed. Non-skill tool calls, and skill calls with no `run_id`, keep one row each. The read→merge→write is guarded by a per-event-loop `asyncio.Lock`. Surfaced by the admin `GET /api/admin/tool-metrics` router (which has a `kind=skill` filter and a per-skill `/summary` breakdown).
 9. **PromptPrefixMiddleware** - Injects the admin-configured prompt prefix into the model request only. The prefix is tagged onto the first human message's `additional_kwargs['prompt_prefix']` by the Gateway (`app.gateway.services`) and prepended to content here at call time, so the persisted/displayed message stays prefix-free
 10. **SummarizationMiddleware** - Context reduction when approaching token limits (optional, if enabled)
 11. **TodoListMiddleware** - Task tracking with `write_todos` tool (optional, if plan_mode)