fix(coding-agent): fixed context usage tracking to keep status and selector totals in sync

- Added context snapshot metadata to AssistantMessage for prompt and non-message token history.
- Anchored context usage calculations on assistant snapshots and computed percent numerically.
- Updated status-line, /context, selector, and interactive mode flows to share session usage totals.
- Extended status-line cache fingerprinting and invalidation for assistant usage and prompt/tool/skill changes.

packages/coding-agent/src/cli/bench-cli.ts

@@ -17,7 +17,12 @@ import { formatDuration, getProjectDir } from "@oh-my-pi/pi-utils";
 import chalk from "chalk";
 import type { ApiKeyResolverModel } from "../config/api-key-resolver";
 import { type CanonicalModelQueryOptions, ModelRegistry } from "../config/model-registry";
-import { formatModelSelectorValue, formatModelString, getModelMatchPreferences, resolveCliModel } from "../config/model-resolver";
+import {
+	formatModelSelectorValue,
+	formatModelString,
+	getModelMatchPreferences,
+	resolveCliModel,
+} from "../config/model-resolver";
 import { Settings } from "../config/settings";
 import benchPrompt from "../prompts/bench.md" with { type: "text" };
 import { discoverAuthStorage } from "../sdk";