Resolve compaction policy per routed model

packages/llm/token-meter/README.md

@@ -4,11 +4,7 @@ Replay-aware token measurement through the singleton `ctx.tokenMeter` service. I
 
 ## Configuration
 
-| Key | Default | Contract |
-|---|---:|---|
-| `contextWindow` | `128000` | Positive integer service-wide context capacity. |
-
-The estimator intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. `contextWindow` is the only deployment setting. Direct construction validates it; Loader mounts first apply the package's Schemastery shape validation. Unrecognized top-level keys are rejected.
+The estimator has no settings. It intentionally uses one fixed heuristic: four characters per token plus structural overhead for roles, blocks, and request-envelope fields. Any key is rejected, including the obsolete global `contextWindow`; model capacity belongs to the adapter that owns an exact provider/model route and is available through `ctx.llm.resolveModelContext()`.
 
 ## Measurement contract
 
@@ -30,13 +26,7 @@ Usage accounting sums disjoint input, cache-read, cache-write, and output bucket
 - name: '@deepseek-ai/dsh-compact-basic'
 ```
 
-Both plugins have usable defaults. A deployment with a different capacity configures the meter once:
-
-```yaml
-- name: '@deepseek-ai/dsh-token-meter'
-  config:
-    contextWindow: 32768
-```
+Both plugins have usable defaults. The meter remains independent of model routing and optional compaction. A deployment configures capacity on its LLM adapter and compaction policy on `dsh-compact-basic`.
 
 ## Model Experience
 

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

@@ -19,12 +19,6 @@ import type {
 
 export type * from './types.ts'
 
-/** Default service-wide provider context capacity. */
-const DEFAULT_CONTEXT_WINDOW = 128_000
-
-/** Complete public configuration key set. */
-const TOKEN_METER_CONFIG_KEYS: ReadonlySet<string> = new Set(['contextWindow'])
-
 /** Fixed text-density estimate used until exact tokenization is needed. */
 const CHARS_PER_TOKEN = 4
 
@@ -74,28 +68,10 @@ function optionalHeaderEquals(
 /** Reject stale or misspelled keys before defaults can hide them. */
 function validateConfigKeys(config: TokenMeterConfig): void {
   for (const key of Object.keys(config)) {
-    if (!TOKEN_METER_CONFIG_KEYS.has(key)) {
-      throw new Error(
-        `TokenMeterConfig: unknown key "${key}" (allowed: contextWindow)`,
-      )
-    }
+    throw new Error(`TokenMeterConfig: unknown key "${key}" (no settings are supported)`)
   }
 }
 
-/** Resolve and validate the one service-wide context capacity. */
-function resolveContextWindow(config: TokenMeterConfig): number {
-  validateConfigKeys(config)
-  const contextWindow = config.contextWindow === undefined
-    ? DEFAULT_CONTEXT_WINDOW
-    : config.contextWindow
-  if (!Number.isInteger(contextWindow) || contextWindow <= 0) {
-    throw new Error(
-      `TokenMeterConfig: contextWindow (${contextWindow}) must be a positive integer`,
-    )
-  }
-  return contextWindow
-}
-
 declare module 'cordis' {
   interface Context {
     tokenMeter: TokenMeterService
@@ -104,18 +80,13 @@ declare module 'cordis' {
 
 /** Replay owner for one service-wide estimator and isolated per-session folds. */
 export class TokenMeterService extends Service {
-  static Config: z<TokenMeterConfig> = z.object({
-    contextWindow: z.number().step(1).min(1).default(DEFAULT_CONTEXT_WINDOW),
-  })
-
-  /** Provider context-window capacity used by pressure consumers. */
-  readonly contextWindow: number
+  static Config: z<TokenMeterConfig> = z.object({})
 
   private readonly states = new WeakMap<Session, ReplayState>()
 
   constructor(ctx: Context, config: TokenMeterConfig = {}) {
     super(ctx, 'tokenMeter')
-    this.contextWindow = resolveContextWindow(config)
+    validateConfigKeys(config)
 
     // Readers catch up independently, while eager observation bounds ordinary
     // read latency without creating state for sessions no consumer has read.

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

@@ -6,11 +6,8 @@
 
 import type { TokenUsage } from '@deepseek-ai/dsh-llm'
 
-/** Token-meter plugin configuration. */
-export interface TokenMeterConfig {
-  /** Service-wide context-window capacity in tokens. Defaults to `128000`. */
-  contextWindow?: number
-}
+/** Token-meter plugin configuration; the fixed estimator has no settings. */
+export type TokenMeterConfig = object
 
 /** The baseline from which a signed surface delta produces current pressure. */
 export type TokenMeasurementBaseline =

packages/llm/token-meter/tests/token-meter.spec.ts

@@ -87,29 +87,13 @@ function expectSurfaceTotal(measurement: TokenMeasurement): void {
 }
 
 describe('TokenMeterService configuration and registration', () => {
-  it('provides one zero-config context window', () => {
-    const service = meter()
-    expect(service.contextWindow).toBe(128_000)
-  })
-
-  it('accepts one service-wide context-window override', () => {
-    expect(meter({ contextWindow: 32_000 }).contextWindow).toBe(32_000)
-  })
-
-  it.each(['models', 'contextWidow'])('rejects unknown top-level config key %s', (key) => {
-    expect(() => meter({ [key]: {} }))
-      .toThrow(`TokenMeterConfig: unknown key "${key}"`)
-  })
-
-  it.each([
-    { contextWindow: 0 },
-    { contextWindow: -1 },
-    { contextWindow: 1.5 },
-    { contextWindow: Number.NaN },
-    { contextWindow: null },
-  ] as unknown as TokenMeterConfig[])('rejects invalid context capacity %#', (config) => {
-    expect(() => meter(config)).toThrow(/contextWindow .* positive integer/)
-  })
+  it.each(['models', 'contextWindow', 'contextWidow'])(
+    'rejects stale or unknown top-level config key %s',
+    (key) => {
+      expect(() => meter({ [key]: {} }))
+        .toThrow(`TokenMeterConfig: unknown key "${key}"`)
+    },
+  )
 
   it('registers and unregisters ctx.tokenMeter with its plugin fiber', async () => {
     const ctx = new Context()
@@ -123,7 +107,7 @@ describe('TokenMeterService configuration and registration', () => {
 
 describe('TokenMeterService pricing', () => {
   it('prices every built-in content shape and merge-extended blocks with one fixed heuristic', () => {
-    const service = meter({ contextWindow: 100 })
+    const service = meter()
     const blocks: ContentBlock[] = [
       { type: 'text', text: 'abcd' },
       { type: 'reasoning', text: 'ab' },
@@ -331,7 +315,7 @@ describe('replay anchors and surface folds', () => {
   })
 
   it('keeps only the latest successful request anchor across model switches', () => {
-    const service = meter({ contextWindow: 1_000 })
+    const service = meter()
     const session = new Session(SessionId('switch'))
     const alphaHeader = header('alpha', { system: 'same envelope' })
     appendSuccessfulCall(session, alphaHeader, { usage: USAGE, providerText: 'alpha' })