refactor(token-meter): simplify singleton service (round 1)

packages/compact/compact-basic/src/automatic.ts

@@ -7,10 +7,6 @@
 import type { Context } from 'cordis'
 import type { CompactionResult } from '@deepseek-ai/dsh-compact'
 import type { Message } from '@deepseek-ai/dsh-llm'
-import {
-  TOKEN_METER_MODEL_UNCONFIGURED,
-  TokenMeterError,
-} from '@deepseek-ai/dsh-token-meter'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 
 interface AutomaticCompactor {
@@ -49,10 +45,6 @@ export function registerAutomaticCompaction(
         )
       }
     } catch (error: unknown) {
-      // A named routed model without a meter profile is configuration failure,
-      // not an optional operational compaction miss.
-      if (error instanceof TokenMeterError
-        && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error
       const message = error instanceof Error ? error.message : String(error)
       ctx.logger.warn(`compaction failed: ${message}; proceeding with full history`)
     }

packages/compact/compact-basic/src/config.ts

@@ -1,63 +1,49 @@
 /**
- * Runtime defaulting and per-model policy validation for compact-basic.
+ * Runtime defaulting and policy validation for compact-basic.
  *
  * @module @deepseek-ai/dsh-compact-basic/config
  */
 
 import { deepFreeze } from '@deepseek-ai/dsh-llm'
-import type { ModelTokenMeter, TokenMeterService } from '@deepseek-ai/dsh-token-meter'
-import type {
-  BasicCompactConfig,
-  ModelCompactConfig,
-  ResolvedConfig,
-  ResolvedModelCompactConfig,
-} from './types.ts'
+import type { TokenMeterService } from '@deepseek-ai/dsh-token-meter'
+import type { BasicCompactConfig, ResolvedConfig } from './types.ts'
 
-/** Default request-pressure fraction for every metered model. */
+/** Default request-pressure fraction of the token meter's context window. */
 const DEFAULT_THRESHOLD_RATIO = 0.8
 
-/** Default verbatim-tail fraction of a model's context window. */
+/** Default verbatim-tail fraction of the token meter's context window. */
 const DEFAULT_RETAIN_RATIO = 0.16
 
 /**
- * Resolve common defaults and validate every named model override.
+ * Resolve defaults and validate the service-wide compaction policy.
  * @param config - raw compact-basic configuration.
- * @param tokenMeter - owning meter service used to reject unknown override names.
- * @returns a detached deeply immutable top-level configuration.
+ * @param tokenMeter - token meter supplying the context capacity.
+ * @returns a detached deeply immutable configuration.
  */
 export function resolveConfig(
   config: BasicCompactConfig = {},
   tokenMeter: TokenMeterService,
 ): ResolvedConfig {
-  const configuredModels: unknown = config.models
-  const models = configuredModels === undefined ? {} : configuredModels
-  if (typeof models !== 'object' || models === null || Array.isArray(models)) {
-    throw new Error('BasicCompactConfig: models must be an object')
-  }
-
-  const detachedModels: Record<string, ModelCompactConfig> = {}
-  for (const [model, override] of Object.entries(models as Record<string, unknown>)) {
-    if (typeof override !== 'object' || override === null || Array.isArray(override)) {
-      throw new Error(`BasicCompactConfig: models.${model} must be an object`)
-    }
-    const meter = tokenMeter.resolve(model)
-    detachedModels[model] = { ...override as ModelCompactConfig }
-    resolveModelConfig({
-      models: detachedModels,
-      summarizationModel: '',
-      maxTokens: 8192,
-      compactionRetries: 1,
-      auto: true,
-    }, meter)
-  }
-
+  const thresholdRatio = config.thresholdRatio ?? DEFAULT_THRESHOLD_RATIO
+  const retainTokens = config.retainTokens
+    ?? Math.floor(tokenMeter.contextWindow * DEFAULT_RETAIN_RATIO)
   const resolved: ResolvedConfig = {
-    models: detachedModels,
+    thresholdRatio,
+    retainTokens,
     summarizationModel: config.summarizationModel ?? '',
     maxTokens: config.maxTokens ?? 8192,
     compactionRetries: config.compactionRetries ?? 1,
     auto: config.auto ?? true,
   }
+
+  assertRatio('thresholdRatio', resolved.thresholdRatio)
+  assertNonNegativeInteger('retainTokens', resolved.retainTokens)
+  const thresholdTokens = Math.floor(tokenMeter.contextWindow * resolved.thresholdRatio)
+  if (resolved.retainTokens >= thresholdTokens) {
+    throw new Error(
+      `BasicCompactConfig: retainTokens (${resolved.retainTokens}) must be less than threshold tokens ${thresholdTokens}`,
+    )
+  }
   assertPositiveInteger('maxTokens', resolved.maxTokens)
   assertNonNegativeInteger('compactionRetries', resolved.compactionRetries)
   if (typeof resolved.summarizationModel !== 'string') {
@@ -66,36 +52,7 @@ export function resolveConfig(
   if (typeof resolved.auto !== 'boolean') {
     throw new Error('BasicCompactConfig: auto must be a boolean')
   }
-  return deepFreeze(structuredClone(resolved))
-}
-
-/**
- * Resolve one effective model's default policy plus optional field overrides.
- * @param config - validated compact-basic configuration.
- * @param meter - effective model's token-meter handle and context capacity.
- * @returns a detached immutable model policy.
- */
-export function resolveModelConfig(
-  config: ResolvedConfig,
-  meter: ModelTokenMeter,
-): ResolvedModelCompactConfig {
-  const override = config.models[meter.model]
-  const thresholdRatio = override?.thresholdRatio ?? DEFAULT_THRESHOLD_RATIO
-  const retainTokens = override?.retainTokens ?? Math.floor(meter.contextWindow * DEFAULT_RETAIN_RATIO)
-  assertRatio(`models.${meter.model}.thresholdRatio`, thresholdRatio)
-  assertNonNegativeInteger(`models.${meter.model}.retainTokens`, retainTokens)
-  const thresholdTokens = Math.floor(meter.contextWindow * thresholdRatio)
-  if (retainTokens >= thresholdTokens) {
-    throw new Error(
-      `BasicCompactConfig: models.${meter.model}.retainTokens (${retainTokens}) must be less than threshold tokens ${thresholdTokens}`,
-    )
-  }
-  return deepFreeze({
-    model: meter.model,
-    contextWindow: meter.contextWindow,
-    thresholdRatio,
-    retainTokens,
-  })
+  return deepFreeze(resolved)
 }
 
 function assertPositiveInteger(name: string, value: number): void {

packages/compact/compact-basic/src/index.ts

@@ -11,24 +11,20 @@ import type { CompactionResult } from '@deepseek-ai/dsh-compact'
 import { canonicalHeader } from '@deepseek-ai/dsh-session'
 import type { EpochHeader, Session } from '@deepseek-ai/dsh-session'
 import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm'
-import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { registerAutomaticCompaction } from './automatic.ts'
-import { resolveConfig, resolveModelConfig } from './config.ts'
+import { resolveConfig } from './config.ts'
 import { compactSurfaceRegion, selectCompactableRange } from './region.ts'
 import { summarizeWithLlm } from './summarizer.ts'
 import type {
   BasicCompactConfig,
   ResolvedConfig,
-  ResolvedModelCompactConfig,
 } from './types.ts'
 
-export { resolveConfig, resolveModelConfig } from './config.ts'
+export { resolveConfig } from './config.ts'
 export type {
   BasicCompactConfig,
-  ModelCompactConfig,
   ResolvedConfig,
-  ResolvedModelCompactConfig,
 } from './types.ts'
 
 /** Resolve the latest actual routed model, then the agent's configured fallback. */
@@ -61,28 +57,24 @@ function provisionalHeader(
  * retention, provenance, and summary-convergence pricing.
  *
  * `summarize()` is the sole subclass customization hook; the replay and durable
- * mutation strategy stays fixed so every pricing decision uses one effective
- * conversation-model meter.
+ * mutation strategy stays fixed so every pricing decision uses the singleton
+ * token meter.
  */
 export class BasicCompactService extends CompactService {
   static inject = ['llm', 'tokenMeter']
 
   static Config: z<BasicCompactConfig> = z.object({
-    models: z.dict(z.object({
-      thresholdRatio: z.number(),
-      retainTokens: z.number().step(1),
-    })),
+    thresholdRatio: z.number().default(0.8),
+    retainTokens: z.number().step(1),
     summarizationModel: z.string().default(''),
     maxTokens: z.number().step(1).min(1).default(8192),
     compactionRetries: z.number().step(1).min(0).default(1),
     auto: z.boolean().default(true),
   })
 
-  /** Resolved and validated common configuration plus named partial overrides. */
+  /** Resolved and validated compaction configuration. */
   readonly config: ResolvedConfig
 
-  private readonly modelConfigs = new Map<string, ResolvedModelCompactConfig>()
-
   constructor(ctx: Context, config: BasicCompactConfig = {}) {
     super(ctx)
     this.config = resolveConfig(config, ctx.tokenMeter)
@@ -107,9 +99,8 @@ export class BasicCompactService extends CompactService {
 
   /**
    * Check replayed pressure for the provisional pre-step envelope and compact
-   * a tool-balanced head until it falls below the effective model threshold.
-   * A genuinely model-less router-first step skips this provisional check;
-   * naming an unconfigured model throws the token meter's typed error.
+   * a tool-balanced head until it falls below the service-wide threshold.
+   * A genuinely model-less router-first step skips this provisional check.
    * @param agent - agent whose session and provisional model are measured.
    * @param fullSystemPrompt - current assembled system prompt override.
    * @param sessionPrefix - current request-only prefix override.
@@ -124,10 +115,9 @@ export class BasicCompactService extends CompactService {
   ): Promise<CompactionResult | null> {
     const model = effectiveModel(agent)
     if (model === undefined || model.length === 0) return null
-    const meter = this.ctx.tokenMeter.resolve(model)
-    const policy = this._modelConfig(meter)
+    const meter = this.ctx.tokenMeter
     const requestHeader = provisionalHeader(model, agent.session, fullSystemPrompt, sessionPrefix)
-    const threshold = Math.floor(policy.contextWindow * policy.thresholdRatio)
+    const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio)
     let measurement = meter.measure(agent.session, requestHeader)
     if (measurement.totalTokens < threshold) return null
 
@@ -139,7 +129,7 @@ export class BasicCompactService extends CompactService {
           `compaction: pressure revision ${measurement.logRevision} does not match surface revision ${surface.logRevision}`,
         )
       }
-      const range = selectCompactableRange(agent.session, surface, policy.retainTokens)
+      const range = selectCompactableRange(agent.session, surface, this.config.retainTokens)
       if (range === null) {
         /* v8 ignore else -- concrete replacement preserves a compactable checkpoint; subclass hooks cannot mutate it. */
         if (result === null) return null
@@ -159,12 +149,12 @@ export class BasicCompactService extends CompactService {
 
   /**
    * Compact one inclusive positional surface range using the effective
-   * conversation model for all retention and shrink pricing. Reject an agent
-   * that does not own the exact target before any resolution or mutation.
+   * token meter for all retention and shrink pricing. Reject an agent that does
+   * not own the exact target before any mutation.
    * @param session - session whose surface is mutated; must equal `agent.session`.
    * @param start - inclusive first surface-node seq.
    * @param end - inclusive last surface-node seq.
-   * @param agent - owner of the target session, used by the summarizer and model resolver.
+   * @param agent - owner of the target session, used by the summarizer.
    * @param signal - optional summarization cancellation signal.
    * @returns the successful durable compaction result.
    */
@@ -178,27 +168,11 @@ export class BasicCompactService extends CompactService {
     if (session !== agent.session) {
       throw new Error('compactRegion: agent.session must be the exact target session')
     }
-    const model = effectiveModel(agent)
-    if (model === undefined || model.length === 0) {
-      throw new Error('compactRegion: no routed or configured conversation model is available for token pricing')
-    }
-    const meter = this.ctx.tokenMeter.resolve(model)
-    this._modelConfig(meter)
     return compactSurfaceRegion({
-      meter,
+      meter: this.ctx.tokenMeter,
       summarize: (text, owner, abort) => this.summarize(text, owner, abort),
     }, session, start, end, agent, signal)
   }
-
-  /** Resolve and memoize one lazy default/override model policy. */
-  private _modelConfig(meter: ModelTokenMeter): ResolvedModelCompactConfig {
-    let modelConfig = this.modelConfigs.get(meter.model)
-    if (modelConfig === undefined) {
-      modelConfig = resolveModelConfig(this.config, meter)
-      this.modelConfigs.set(meter.model, modelConfig)
-    }
-    return modelConfig
-  }
 }
 
 export default BasicCompactService

packages/compact/compact-basic/src/region.ts

@@ -10,14 +10,14 @@ import {
   toolPairingBalancedBefore,
 } from '@deepseek-ai/dsh-compact'
 import type { CompactionResult } from '@deepseek-ai/dsh-compact'
-import type { ModelTokenMeter, TokenSurfaceMeasurement } from '@deepseek-ai/dsh-token-meter'
+import type { TokenMeterService, TokenSurfaceMeasurement } from '@deepseek-ai/dsh-token-meter'
 import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { frameSummary } from './summarizer.ts'
 import type { SummaryResult } from './summarizer.ts'
 
 interface RegionDependencies {
-  readonly meter: ModelTokenMeter
+  readonly meter: TokenMeterService
   summarize(text: string, agent: Agent, signal?: AbortSignal): Promise<SummaryResult>
 }
 

packages/compact/compact-basic/src/types.ts

@@ -4,18 +4,12 @@
  * @module @deepseek-ai/dsh-compact-basic/types
  */
 
-/** Optional pressure and retention policy for one metered model. */
-export interface ModelCompactConfig {
-  /** Compact at this fraction of the model's configured context window. Defaults to `0.8`. */
+/** Basic compaction configuration; every common field has a deployment default. */
+export interface BasicCompactConfig {
+  /** Compact at this fraction of the token meter's context window. Defaults to `0.8`. */
   thresholdRatio?: number
   /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */
   retainTokens?: number
-}
-
-/** Basic compaction configuration; every common field has a deployment default. */
-export interface BasicCompactConfig {
-  /** Field-wise pressure/retention overrides keyed by configured token-meter model name. */
-  models?: Record<string, ModelCompactConfig>
   /** Summary model; `''` resolves the latest routed model, then `AgentOptions.model`. Defaults to `''`. */
   summarizationModel?: string
   /** Provider generation cap for summarization. Defaults to `8192`. */
@@ -26,19 +20,12 @@ export interface BasicCompactConfig {
   auto?: boolean
 }
 
-/** Validated top-level defaults plus detached per-model partial overrides. */
+/** Validated and detached compaction configuration. */
 export interface ResolvedConfig {
-  readonly models: Readonly<Record<string, Readonly<ModelCompactConfig>>>
+  readonly thresholdRatio: number
+  readonly retainTokens: number
   readonly summarizationModel: string
   readonly maxTokens: number
   readonly compactionRetries: number
   readonly auto: boolean
 }
-
-/** Fully resolved pressure/retention policy for one effective model. */
-export interface ResolvedModelCompactConfig {
-  readonly model: string
-  readonly contextWindow: number
-  readonly thresholdRatio: number
-  readonly retainTokens: number
-}