refactor(token-meter): make context occupancy durable projection state

Replace the transient `session/model-request` mux frame with ordinary durable
session state. Occupancy now rides two last-wins projection fields instead of a
non-replayable frame that needed removal tombstones and cross-stream fencing.

The frame was the only non-replayable class on the mux stream. Because host and
mux are independent SSE streams with no cross-stream order, a request emitted
before a removal could arrive after `host/session-removed`, and a legitimate
request for a new lifecycle reusing the same id could be fenced by a late
removal. Fixing that needed a lifecycle generation on every frame; the frame
itself was the problem.

Removed: the `session/model-request` frame and schema, the `agent/model-request`
core event, the ApiProxy measurement point, the client-side telemetry map and
removal tombstone, and the synthetic `cancelled` open error used to signal
reconnect through the error channel.

Added: `request/context`, a log-only session event recording the
registration-bound capacity of the route a request resolved to, appended beside
`request/header` from the lookup that already prepared the call and skipped when
the route is unchanged. Capacity stays out of `EpochHeader` because it is
adapter metadata about a route, not an input the request was built from, so it
must not join request reconstruction or header equality.

The `contextPressure` projection pairs the newest provider-reported prompt size
with the newest recorded capacity. The two are deliberately not one atomic
request observation: switching models can pair a fresh capacity with the prior
route's pressure until the next request reports usage. The figure is a
user-facing reference, and this matches how the TUI status line has always
computed occupancy.

packages/llm/token-meter/src/projection.ts

@@ -1,5 +1,5 @@
 /**
- * Pure client-safe token-usage projection vocabulary.
+ * Pure client-safe token-projection vocabulary.
  *
  * @module @deepseek-ai/dsh-token-meter/projection
  */
@@ -17,9 +17,34 @@ export interface TokenUsageProjection {
   cacheWriteTokens: number
 }
 
+/**
+ * Approximate context occupancy for a status display.
+ *
+ * The two fields are deliberately NOT one atomic request observation:
+ * `pressureTokens` is the newest provider-reported prompt size in the log,
+ * `contextWindow` the newest recorded route capacity. Switching models can
+ * therefore pair a fresh capacity with the previous route's pressure until the
+ * next request reports usage. This is an intentional trade — the value is a
+ * user-facing reference, not a billing or gating input — and it matches how
+ * the TUI status line has always computed occupancy. See the token-meter
+ * README for the full rationale.
+ */
+export interface ContextPressureProjection {
+  /**
+   * Provider-reported prompt size of the most recent request: uncached input
+   * plus cache reads and writes. Response output is excluded, so this does not
+   * grow as the current turn streams.
+   */
+  pressureTokens: number
+  /** Newest recorded route capacity; absent when no adapter advertised one. */
+  contextWindow?: number
+}
+
 declare module '@deepseek-ai/dsh-session-projection/types' {
   interface SessionProjectionMap {
     /** Provider-reported usage accumulated across the complete durable log. */
     tokenUsage: TokenUsageProjection
+    /** Newest request pressure paired with the newest known route capacity. */
+    contextPressure: ContextPressureProjection
   }
 }