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

examples/coding-agent/composition.md

@@ -23,6 +23,8 @@ flowchart LR
   bundle_agent_core --> spine_sessions["ctx.sessions"]
   bundle_agent_core --> spine_tools["ctx.tools + tool-bash"]
   bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"]
+  plugin_coding_token_meter["token-meter<br/>@deepseek-ai/dsh-token-meter"]
+  cfg --> plugin_coding_token_meter
   plugin_coding_compact_basic["compact-basic<br/>@deepseek-ai/dsh-compact-basic"]
   cfg --> plugin_coding_compact_basic
   plugin_coding_subagent["subagent<br/>@deepseek-ai/dsh-subagent"]
@@ -55,6 +57,7 @@ flowchart LR
 | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
 | `bash` | `@deepseek-ai/dsh-bash-local` |
 | `stdio-agent` | `@deepseek-ai/dsh-stdio-agent` |
+| `token-meter` | `@deepseek-ai/dsh-token-meter` |
 | `compact-basic` | `@deepseek-ai/dsh-compact-basic` |
 | `subagent` | `@deepseek-ai/dsh-subagent` |
 | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` |

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

examples/coding-agent/tests/compaction.e2e.ts

@@ -33,10 +33,15 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
     // Reasoning tokens require a larger generation cap than the retained checkpoint.
     ctx = await codingHarness(workdir, {
       persona: SYSTEM_PROMPT,
+      tokenMeter: {
+        models: {
+          'deepseek-v4-flash': { contextWindow: 2000 },
+        },
+      },
       compact: {
-        contextWindow: 2000,
-        thresholdRatio: 0.5,
-        retainTokens: 400,
+        models: {
+          'deepseek-v4-flash': { thresholdRatio: 0.5, retainTokens: 400 },
+        },
         summarizationModel: '',
         maxTokens: 1024,
         compactionRetries: 1,

examples/coding-agent/tests/harness.ts

@@ -10,6 +10,8 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
+import TokenMeterService from '@deepseek-ai/dsh-token-meter'
+import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
 import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
@@ -46,6 +48,8 @@ export interface CodingHarnessOptions {
    * compaction plugin (the default suites run without it).
    */
   compact?: BasicCompactConfig
+  /** Optional meter profiles loaded before compact-basic. */
+  tokenMeter?: TokenMeterConfig
 }
 
 export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
@@ -60,9 +64,12 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
   await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
   await ctx.plugin(ToolBash)
   await ctx.plugin(ToolTodo)
-  // Compaction is opt-in: only the compaction e2e loads it, with a lowered
-  // contextWindow/retainTokens so a short real session crosses the threshold.
-  if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact)
+  // Compaction is opt-in: only the compaction e2e loads the reusable meter and
+  // backend, with a lowered profile window so a short real session crosses the threshold.
+  if (options.compact !== undefined) {
+    await ctx.plugin(TokenMeterService, options.tokenMeter)
+    await ctx.plugin(BasicCompactService, options.compact)
+  }
   // Durable JSONL persistence is opt-in: only the resume e2e needs it, and the
   // other suites stay file-free. Loaded last so a resume's deferred
   // `ctx.inject(['sessionPersistence'])` resolves once this is present.