feat(llm): add replay token metering (PR2 round 1)

examples/coding-agent/cordis.yml

@@ -45,17 +45,14 @@
       Verify your work by running the code or tests. Keep answers brief and
       factual.
 
-# Summarize an older range when derived history approaches the context window.
-# This leaf consumes `ctx.llm` and the app's `agent/pre-step` seam.
+# Replay-aware request pressure for the bundled DeepSeek model profiles.
+- id: token-meter
+  name: '@deepseek-ai/dsh-token-meter'
+
+# Summarize an older range when measured history approaches the context window.
+# Built-in model policies provide the ordinary threshold and retained-tail defaults.
 - id: compact-basic
   name: '@deepseek-ai/dsh-compact-basic'
-  config:
-    contextWindow: 128000
-    thresholdRatio: 0.8
-    retainTokens: 20480
-    summarizationModel: ''
-    maxTokens: 8192
-    compactionRetries: 1
 
 # Expose fresh-child `spawn` and completed-prefix `fork` through independent
 # in-process backends. Each tool instance needs a distinct `toolName`; the registry