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

packages/compact/compact-basic/README.md

@@ -8,7 +8,7 @@ This is the implementation tier of the compaction capability — see the [interf
 
 This backend owns the compaction policy:
 
-- **Measurement** — the effective conversation model's `ModelTokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config.
+- **Measurement** — the singleton `ctx.tokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config.
 - **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope.
 - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold.
 - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call.
@@ -16,16 +16,16 @@ This backend owns the compaction policy:
 - **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation.
 - **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged.
 
-`summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on the conversation model's meter. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`.
+`summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on `ctx.tokenMeter`. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`.
 
 ## Config (`BasicCompactConfig`)
 
-Every common setting is optional. Every model known to `ctx.tokenMeter` receives the default compact policy lazily; named overrides merge only the fields supplied and must name a configured meter profile.
+Every setting is optional. The pressure and retention policy applies to the token meter's single context window.
 
 | Key | Required | Meaning |
 |---|---|---|
-| `models.<model>.thresholdRatio` | no (default `0.8`) | Compact at `floor(contextWindow × ratio)`. |
-| `models.<model>.retainTokens` | no (default `floor(contextWindow × 0.16)`) | Recent surface budget kept verbatim; must be below the threshold. |
+| `thresholdRatio` | no (default `0.8`) | Compact at `floor(contextWindow × ratio)`. |
+| `retainTokens` | no (default `floor(contextWindow × 0.16)`) | Recent surface budget kept verbatim; must be below the threshold. |
 | `summarizationModel` | no (default `''`) | Empty resolves the latest logged routed model, then `AgentOptions.model`. |
 | `maxTokens` | no (default `8192`) | Provider generation cap for the summarization call; may include reasoning tokens. |
 | `compactionRetries` | no (default `1`) | Extra attempts after the first when pressure remains above threshold. |
@@ -116,7 +116,7 @@ Rules:
 ## Known Limitations and Deferred Work
 
 - **Pre-step sees a provisional request envelope** — the current prompt and prefix are exact, but routing and tool changes made later in `agent/request` are not logged yet. A router-only agent with no provisional model skips that check.
-- **Meter accuracy follows the selected profile** — missing provider usage falls back to the token meter's configured character density and structural overhead.
+- **Meter accuracy follows the fixed heuristic** — missing reusable provider usage falls back to character count plus structural overhead rather than exact tokenization.
 - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting.
 - **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds.
 - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)).

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
-}

packages/compact/compact-basic/tests/compact-basic.spec.ts

@@ -1,31 +1,21 @@
 import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
-import BasicCompactService, {
-  resolveConfig,
-  resolveModelConfig,
-} from '@deepseek-ai/dsh-compact-basic'
+import BasicCompactService, { resolveConfig } from '@deepseek-ai/dsh-compact-basic'
 import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
 import { selectCompactableRange } from '@deepseek-ai/dsh-compact-basic/src/region.ts'
 import type { CompactionResult } from '@deepseek-ai/dsh-compact'
 import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm'
 import { Session, SessionId } from '@deepseek-ai/dsh-session'
-import TokenMeterService, {
-  TOKEN_METER_MODEL_UNCONFIGURED,
-  TokenMeterError,
-} from '@deepseek-ai/dsh-token-meter'
+import TokenMeterService from '@deepseek-ai/dsh-token-meter'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 
 const SIGNAL = new AbortController().signal
 const MODEL = 'test-model'
 
-function createContext(
-  models: Record<string, { contextWindow?: number; charsPerToken?: number }> = {
-    [MODEL]: { contextWindow: 100, charsPerToken: 1_000 },
-  },
-): Context {
+function createContext(contextWindow = 1_000): Context {
   const ctx = new Context()
-  void new TokenMeterService(ctx, { models })
+  void new TokenMeterService(ctx, { contextWindow })
   return ctx
 }
 
@@ -34,7 +24,7 @@ function agent(session: Session, model?: string): Agent {
 }
 
 /** Closed two-message turns followed by one open turn for durable compaction events. */
-function conversation(turns = 4, text = 'fixture'): Session {
+function conversation(turns = 4, text = 'fixture '.repeat(40).trim()): Session {
   const session = new Session(SessionId(`conversation-${turns}`))
   for (let turn = 1; turn <= turns; turn += 1) {
     session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } })
@@ -128,83 +118,64 @@ async function compactIfNeeded(
 }
 
 describe('compact configuration and defaults', () => {
-  it('uses low-friction common and per-profile defaults', () => {
-    const ctx = createContext({
-      [MODEL]: { contextWindow: 100, charsPerToken: 1_000 },
-      large: { contextWindow: 1_000, charsPerToken: 4 },
-    })
+  it('uses low-friction service-wide defaults', () => {
+    const ctx = createContext()
     const resolved = resolveConfig({}, ctx.tokenMeter)
 
     expect(resolved).toEqual({
-      models: {},
+      thresholdRatio: 0.8,
+      retainTokens: 160,
       summarizationModel: '',
       maxTokens: 8192,
       compactionRetries: 1,
       auto: true,
     })
-    expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve(MODEL))).toEqual({
-      model: MODEL,
-      contextWindow: 100,
-      thresholdRatio: 0.8,
-      retainTokens: 16,
-    })
-    expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve('large')).retainTokens).toBe(160)
     expect(Object.isFrozen(resolved)).toBe(true)
   })
 
-  it('merges threshold and retention overrides field-wise', () => {
+  it('resolves threshold and retention overrides independently', () => {
     const ctx = createContext()
     const thresholdOnly = resolveConfig({
-      models: { [MODEL]: { thresholdRatio: 0.5 } },
-    }, ctx.tokenMeter)
-    expect(resolveModelConfig(thresholdOnly, ctx.tokenMeter.resolve(MODEL))).toMatchObject({
       thresholdRatio: 0.5,
-      retainTokens: 16,
+    }, ctx.tokenMeter)
+    expect(thresholdOnly).toMatchObject({
+      thresholdRatio: 0.5,
+      retainTokens: 160,
     })
 
     const retentionOnly = resolveConfig({
-      models: { [MODEL]: { retainTokens: 7 } },
+      retainTokens: 70,
     }, ctx.tokenMeter)
-    expect(resolveModelConfig(retentionOnly, ctx.tokenMeter.resolve(MODEL))).toMatchObject({
+    expect(retentionOnly).toMatchObject({
       thresholdRatio: 0.8,
-      retainTokens: 7,
+      retainTokens: 70,
     })
   })
 
-  it('validates common values and model policy invariants', () => {
+  it('validates common values and pressure-policy invariants', () => {
     const ctx = createContext()
     const bad = [
       [{ maxTokens: 0 }, /maxTokens/],
       [{ compactionRetries: -1 }, /compactionRetries/],
       [{ auto: 'yes' }, /auto must be a boolean/],
       [{ summarizationModel: 1 }, /summarizationModel must be a string/],
-      [{ models: null }, /models must be an object/],
-      [{ models: { [MODEL]: null } }, /must be an object/],
-      [{ models: { [MODEL]: { thresholdRatio: 0 } } }, /number in \(0, 1\]/],
-      [{ models: { [MODEL]: { thresholdRatio: 1.1 } } }, /number in \(0, 1\]/],
-      [{ models: { [MODEL]: { retainTokens: -1 } } }, /non-negative integer/],
-      [{ models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 50 } } }, /less than threshold/],
+      [{ thresholdRatio: 0 }, /number in \(0, 1\]/],
+      [{ thresholdRatio: 1.1 }, /number in \(0, 1\]/],
+      [{ retainTokens: -1 }, /non-negative integer/],
+      [{ thresholdRatio: 0.5, retainTokens: 500 }, /less than threshold/],
     ] as Array<[unknown, RegExp]>
 
     for (const [config, pattern] of bad) {
       expect(() => resolveConfig(config as BasicCompactConfig, ctx.tokenMeter)).toThrow(pattern)
     }
   })
-
-  it('rejects an override for an unknown meter profile with the exact typed error', () => {
-    const ctx = createContext()
-    expect(() => resolveConfig({ models: { missing: { retainTokens: 1 } } }, ctx.tokenMeter))
-      .toThrow(expect.objectContaining({
-        code: TOKEN_METER_MODEL_UNCONFIGURED,
-        model: 'missing',
-      }))
-  })
 })
 
 describe('pressure measurement and retention', () => {
   const compactConfig: BasicCompactConfig = {
     auto: false,
-    models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } },
+    thresholdRatio: 0.5,
+    retainTokens: 180,
   }
 
   it('skips the provisional check only when no routed or fallback model exists', async () => {
@@ -214,10 +185,10 @@ describe('pressure measurement and retention', () => {
     expect(compact.calls).toHaveLength(0)
   })
 
-  it('throws for a named unconfigured model instead of swallowing it', async () => {
+  it('meters any routed model without profile resolution', async () => {
     const compact = service(compactConfig)
-    await expect(compactIfNeeded(compact, conversation(), 'missing'))
-      .rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing' })
+    await expect(compactIfNeeded(compact, conversation(), 'unlisted-model'))
+      .resolves.not.toBeNull()
   })
 
   it('does nothing below threshold and compacts a priced head above threshold', async () => {
@@ -234,38 +205,39 @@ describe('pressure measurement and retention', () => {
   it('counts the current prompt and request prefix without putting either on the surface', async () => {
     const compact = service({
       auto: false,
-      models: { [MODEL]: { thresholdRatio: 0.7, retainTokens: 9 } },
+      thresholdRatio: 0.7,
+      retainTokens: 50,
     })
-    const session = conversation(2, 'x'.repeat(2_000))
+    const session = conversation(2, 'x'.repeat(200))
     expect(await compactIfNeeded(compact, session)).toBeNull()
 
     const prefix: Message[] = [{
       role: 'user',
-      content: [{ type: 'text', text: 'p'.repeat(10_000) }],
+      content: [{ type: 'text', text: 'p'.repeat(1_000) }],
     }]
-    const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(5_000), prefix)
+    const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(1_000), prefix)
     expect(result).not.toBeNull()
     expect(prefix).toHaveLength(1)
     expect(session.events.some(event => event.type === 'context/message')).toBe(false)
   })
 
-  it('uses the latest logged routed model instead of AgentOptions.model', async () => {
-    const ctx = createContext({
-      actual: { contextWindow: 100, charsPerToken: 1_000 },
-      fallback: { contextWindow: 10_000, charsPerToken: 1_000 },
-    })
+  it('uses the latest logged routed model in the provisional request envelope', async () => {
+    const ctx = createContext()
     const compact = service({
       auto: false,
-      models: { actual: { thresholdRatio: 0.5, retainTokens: 18 } },
+      thresholdRatio: 0.5,
+      retainTokens: 180,
     }, ctx)
     const session = conversation(4)
     session.append('request/header', {
       header: { config: { model: 'actual' } },
       reason: 'initial',
     })
+    const measure = vi.spyOn(ctx.tokenMeter, 'measure')
 
     const result = await compactIfNeeded(compact, session, 'fallback')
     expect(result).not.toBeNull()
+    expect(measure.mock.calls[0]?.[1]?.config.model).toBe('actual')
   })
 
   it('declines when envelope pressure is high but the surface has no compactable range', async () => {
@@ -279,7 +251,7 @@ describe('pressure measurement and retention', () => {
 
   it('detects scalar/surface revision disagreement', async () => {
     const ctx = createContext()
-    const meter = ctx.tokenMeter.resolve(MODEL)
+    const meter = ctx.tokenMeter
     const original = meter.measureSurface.bind(meter)
     vi.spyOn(meter, 'measureSurface').mockImplementation((session) => {
       const measurement = original(session)
@@ -294,7 +266,8 @@ describe('pressure measurement and retention', () => {
     const compact = service({
       auto: false,
       compactionRetries: 0,
-      models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } },
+      thresholdRatio: 0.3,
+      retainTokens: 180,
     })
     compact.summary = Array.from({ length: 7 }, (_, index) => ({
       type: 'text',
@@ -308,8 +281,9 @@ describe('pressure measurement and retention', () => {
   it('rounds a retention cut head-ward to preserve tool-call/result pairing', async () => {
     const compact = service({
       auto: false,
-      models: { [MODEL]: { thresholdRatio: 0.8, retainTokens: 8 } },
-    })
+      thresholdRatio: 0.8,
+      retainTokens: 80,
+    }, createContext(4_000))
     const session = toolConversation()
     const result = await compactIfNeeded(compact, session)
     expect(result).not.toBeNull()
@@ -327,7 +301,7 @@ describe('pressure measurement and retention', () => {
   it('rejects a priced surface that is not the current positional surface', () => {
     const ctx = createContext()
     const session = conversation(2)
-    const priced = ctx.tokenMeter.resolve(MODEL).measureSurface(session)
+    const priced = ctx.tokenMeter.measureSurface(session)
     expect(() => selectCompactableRange(session, {
       ...priced,
       nodes: priced.nodes.slice(1),
@@ -355,7 +329,7 @@ describe('pressure measurement and retention', () => {
     }, { surfaceOp: 'append' })
     session.append('step/end', { turn: 1, step: 1 })
 
-    const priced = ctx.tokenMeter.resolve(MODEL).measureSurface(session)
+    const priced = ctx.tokenMeter.measureSurface(session)
     expect(selectCompactableRange(session, priced, 1)).toBeNull()
   })
 })
@@ -497,7 +471,7 @@ describe('compaction region transaction', () => {
 
   it('rejects a meter snapshot that changed before summarization began', async () => {
     const ctx = createContext()
-    const meter = ctx.tokenMeter.resolve(MODEL)
+    const meter = ctx.tokenMeter
     const original = meter.measureSurface.bind(meter)
     vi.spyOn(meter, 'measureSurface').mockImplementationOnce((session) => {
       const measurement = original(session)
@@ -569,7 +543,7 @@ describe('compaction region transaction', () => {
 
   it('rejects a non-shrinking framed summary under the conversation meter', async () => {
     const compact = service()
-    compact.summary = Array.from({ length: 20 }, (_, index) => ({
+    compact.summary = Array.from({ length: 100 }, (_, index) => ({
       type: 'text',
       text: `verbose ${index}`,
     }))
@@ -585,7 +559,7 @@ describe('compaction region transaction', () => {
     expect(session.events.some(event => event.type === 'compact/summary')).toBe(false)
   })
 
-  it('requires a conversation model for pricing', async () => {
+  it('lets a model-independent custom summarizer compact without a conversation model', async () => {
     const compact = service()
     const session = conversation(1)
     const nodes = session.surface.nodes
@@ -594,7 +568,7 @@ describe('compaction region transaction', () => {
       nodes[0]!.seq,
       nodes[1]!.seq,
       agent(session),
-    )).rejects.toThrow(/no routed or configured conversation model/)
+    )).resolves.toMatchObject({ shadowedSeqs: [nodes[0]!.seq, nodes[1]!.seq] })
   })
 })
 
@@ -632,7 +606,7 @@ async function summarizerHarness(
 ): Promise<{ ctx: Context; adapter: ScriptedAdapter; compact: BasicCompactService }> {
   const ctx = new Context()
   await ctx.plugin(LlmService)
-  void new TokenMeterService(ctx, { models: { [model]: { contextWindow: 100 } } })
+  void new TokenMeterService(ctx, { contextWindow: 1_000 })
   const adapter = new ScriptedAdapter(blocks, finish)
   ctx.llm.registerAdapter([model], adapter)
   const compact = new BasicCompactService(ctx, config)
@@ -724,7 +698,8 @@ describe('automatic listener and loader composition', () => {
   it('compacts above threshold and remains idle below it', async () => {
     const ctx = createContext()
     const compact = new TestCompactService(ctx, {
-      models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } },
+      thresholdRatio: 0.5,
+      retainTokens: 180,
     })
     const pressured = conversation(4)
     await preStep(ctx, agent(pressured, MODEL))
@@ -741,7 +716,8 @@ describe('automatic listener and loader composition', () => {
     const warnings: string[] = []
     ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn
     const compact = new TestCompactService(ctx, {
-      models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } },
+      thresholdRatio: 0.5,
+      retainTokens: 180,
     })
     compact.error = 'temporary failure'
     const session = conversation(4)
@@ -751,20 +727,12 @@ describe('automatic listener and loader composition', () => {
     expect(session.events.some(event => event.type === 'compact/summary')).toBe(false)
   })
 
-  it('propagates a named unknown-model configuration failure', async () => {
-    const ctx = createContext()
-    void new TestCompactService(ctx)
-    await expect(preStep(ctx, agent(conversation(4), 'missing'))).rejects.toMatchObject({
-      code: TOKEN_METER_MODEL_UNCONFIGURED,
-      model: 'missing',
-    })
-  })
-
   it('auto:false installs no listener', async () => {
     const ctx = createContext()
     void new TestCompactService(ctx, {
       auto: false,
-      models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } },
+      thresholdRatio: 0.5,
+      retainTokens: 180,
     })
     const session = conversation(4)
     await preStep(ctx, agent(session, MODEL))
@@ -777,7 +745,7 @@ describe('automatic listener and loader composition', () => {
     const meterFiber = await ctx.plugin(TokenMeterService)
     const compactFiber = await ctx.plugin(BasicCompactService, { auto: false })
 
-    expect(ctx.tokenMeter.resolve('deepseek-v4-flash').contextWindow).toBe(128_000)
+    expect(ctx.tokenMeter.contextWindow).toBe(128_000)
     expect(ctx.get('compact')).toBeInstanceOf(BasicCompactService)
     await compactFiber.dispose()
     expect(ctx.get('compact')).toBeUndefined()
@@ -788,11 +756,10 @@ describe('automatic listener and loader composition', () => {
   it('removes its automatic listener with the plugin fiber', async () => {
     const ctx = new Context()
     await ctx.plugin(LlmService)
-    await ctx.plugin(TokenMeterService, {
-      models: { [MODEL]: { contextWindow: 100, charsPerToken: 1_000 } },
-    })
+    await ctx.plugin(TokenMeterService, { contextWindow: 1_000 })
     const fiber = await ctx.plugin(TestCompactService, {
-      models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } },
+      thresholdRatio: 0.5,
+      retainTokens: 180,
     })
     await fiber.dispose()
 
@@ -801,17 +768,3 @@ describe('automatic listener and loader composition', () => {
     expect(session.events.some(event => event.type === 'compact/start')).toBe(false)
   })
 })
-
-describe('typed unknown-model boundary', () => {
-  it('uses TokenMeterError identity rather than message matching', () => {
-    const ctx = createContext()
-    let thrown: unknown
-    try {
-      ctx.tokenMeter.resolve('missing')
-    } catch (error: unknown) {
-      thrown = error
-    }
-    expect(thrown).toBeInstanceOf(TokenMeterError)
-    expect(thrown).toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED })
-  })
-})

packages/compact/compact-basic/tests/compact-loop-repro.spec.ts

@@ -62,9 +62,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr
   await ctx.plugin(ToolRegistry)
   await ctx.plugin(AgentRegistry)
   await ctx.plugin(AgentLoop, { agents: [] })
-  await ctx.plugin(TokenMeterService, {
-    models: { mock: { contextWindow: 64, charsPerToken: 1_000 } },
-  })
+  await ctx.plugin(TokenMeterService, { contextWindow: 400 })
   ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps))
   ctx.tools.register(defineTool({
     name: 'work',
@@ -74,11 +72,12 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr
       return [{ type: 'text', text: 'work result' }]
     },
   }))
-  // Tiny window so a couple of tool steps cross the threshold and compaction
-  // fires within the runaway turn.
+  // Small window so several tool steps cross the threshold and compaction
+  // fires within the runaway turn after enough history can shrink.
   const compact = new ReproCompactService(ctx, {
     auto: true,
-    models: { mock: { thresholdRatio: 0.5, retainTokens: 20 } },
+    thresholdRatio: 0.5,
+    retainTokens: 50,
     summarizationModel: '',
     maxTokens: 8192,
     compactionRetries: 1,

packages/compact/compact-basic/tests/loader-composition.spec.ts

@@ -57,10 +57,7 @@ describe('real Loader composition', () => {
       .filter(entry => entry.fiber === undefined && !entry.disabled)
       .map(entry => entry.options.name)
     expect(unloaded).toEqual([])
-    expect(context.tokenMeter.resolve('deepseek-v4-flash')).toMatchObject({
-      contextWindow: 128_000,
-      charsPerToken: 4,
-    })
+    expect(context.tokenMeter.contextWindow).toBe(128_000)
     expect(context.get('compact')).toBeInstanceOf(BasicCompactService)
   })
 })