Merge latest origin/master into token-meter-service

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

@@ -18,6 +18,7 @@ const DEFAULT_RETAIN_RATIO = 0.16
 const BASIC_COMPACT_CONFIG_KEYS: ReadonlySet<string> = new Set([
   'thresholdRatio',
   'retainTokens',
+  'summarizationProvider',
   'summarizationModel',
   'maxTokens',
   'compactionRetries',
@@ -30,7 +31,7 @@ function validateConfigKeys(config: BasicCompactConfig): void {
     if (!BASIC_COMPACT_CONFIG_KEYS.has(key)) {
       throw new Error(
         `BasicCompactConfig: unknown key "${key}" `
-        + '(allowed: thresholdRatio, retainTokens, summarizationModel, maxTokens, compactionRetries, auto)',
+        + '(allowed: thresholdRatio, retainTokens, summarizationProvider, summarizationModel, maxTokens, compactionRetries, auto)',
       )
     }
   }
@@ -53,6 +54,7 @@ export function resolveConfig(
   const resolved: ResolvedConfig = {
     thresholdRatio,
     retainTokens,
+    summarizationProvider: config.summarizationProvider ?? '',
     summarizationModel: config.summarizationModel ?? '',
     maxTokens: config.maxTokens ?? 8192,
     compactionRetries: config.compactionRetries ?? 1,
@@ -69,9 +71,17 @@ export function resolveConfig(
   }
   assertPositiveInteger('maxTokens', resolved.maxTokens)
   assertNonNegativeInteger('compactionRetries', resolved.compactionRetries)
+  if (typeof resolved.summarizationProvider !== 'string') {
+    throw new Error('BasicCompactConfig: summarizationProvider must be a string')
+  }
   if (typeof resolved.summarizationModel !== 'string') {
     throw new Error('BasicCompactConfig: summarizationModel must be a string')
   }
+  if ((resolved.summarizationProvider.length === 0) !== (resolved.summarizationModel.length === 0)) {
+    throw new Error(
+      'BasicCompactConfig: summarizationProvider and summarizationModel must both be set or both be empty',
+    )
+  }
   if (typeof resolved.auto !== 'boolean') {
     throw new Error('BasicCompactConfig: auto must be a boolean')
   }

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

@@ -27,9 +27,15 @@ export type {
   ResolvedConfig,
 } from './types.ts'
 
-/** Resolve the latest actual routed model, then the agent's configured fallback. */
-function effectiveModel(agent: Agent): string | undefined {
-  return agent.session.requestHeader()?.config.model ?? agent.options.model
+/** Resolve the latest actual routed provider/model, then the complete agent fallback pair. */
+function effectiveTarget(agent: Agent): { provider: string; model: string } | undefined {
+  const latest = agent.session.requestHeader()?.config
+  if (latest !== undefined) return { provider: latest.provider, model: latest.model }
+  const { provider, model } = agent.options
+  if (provider === undefined || provider.length === 0 || model === undefined || model.length === 0) {
+    return undefined
+  }
+  return { provider, model }
 }
 
 /**
@@ -38,14 +44,14 @@ function effectiveModel(agent: Agent): string | undefined {
  * later request middleware has not run yet.
  */
 function provisionalHeader(
-  model: string,
+  target: { provider: string; model: string },
   session: Session,
   fullSystemPrompt: string,
   sessionPrefix: readonly Message[],
 ): EpochHeader {
   const latest = session.requestHeader()
   return canonicalHeader({
-    config: latest === undefined ? { model } : { ...latest.config, model },
+    config: latest === undefined ? target : { ...latest.config, ...target },
     ...fullSystemPrompt.length === 0 ? {} : { system: fullSystemPrompt },
     ...latest?.tools === undefined ? {} : { tools: latest.tools },
     ...sessionPrefix.length === 0 ? {} : { messagePrefix: [...sessionPrefix] },
@@ -66,6 +72,7 @@ export class BasicCompactService extends CompactService {
   static Config: z<BasicCompactConfig> = z.object({
     thresholdRatio: z.number().default(0.8),
     retainTokens: z.number().step(1),
+    summarizationProvider: z.string().default(''),
     summarizationModel: z.string().default(''),
     maxTokens: z.number().step(1).min(1).default(8192),
     compactionRetries: z.number().step(1).min(0).default(1),
@@ -93,7 +100,7 @@ export class BasicCompactService extends CompactService {
     text: string,
     agent: Agent,
     signal?: AbortSignal,
-  ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> {
+  ): Promise<{ summary: ContentBlock[]; provider: string; model: string; maxTokens?: number }> {
     return summarizeWithLlm(this.ctx, this.config, text, agent, signal)
   }
 
@@ -101,7 +108,7 @@ 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 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 agent - agent whose session and provisional provider/model are measured.
    * @param fullSystemPrompt - current assembled system prompt override.
    * @param sessionPrefix - current request-only prefix override.
    * @param signal - live step cancellation signal forwarded to summarization.
@@ -113,10 +120,10 @@ export class BasicCompactService extends CompactService {
     sessionPrefix: readonly Message[],
     signal: AbortSignal,
   ): Promise<CompactionResult | null> {
-    const model = effectiveModel(agent)
-    if (model === undefined || model.length === 0) return null
+    const target = effectiveTarget(agent)
+    if (target === undefined) return null
     const meter = this.ctx.tokenMeter
-    const requestHeader = provisionalHeader(model, agent.session, fullSystemPrompt, sessionPrefix)
+    const requestHeader = provisionalHeader(target, agent.session, fullSystemPrompt, sessionPrefix)
     const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio)
     let measurement = meter.measure(agent.session, requestHeader)
     if (measurement.totalTokens < threshold) return null

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

@@ -123,7 +123,7 @@ export async function compactSurfaceRegion(
     }
     const shadowedTokenCount = selected.reduce((total, node) => total + node.tokens, 0)
     const text = renderTranscript(session.events, shadowedSeqs)
-    const { summary, model, maxTokens } = await dependencies.summarize(text, agent, signal)
+    const { summary, provider, model, maxTokens } = await dependencies.summarize(text, agent, signal)
 
     const currentMeasurement = dependencies.meter.measure(session)
     if (currentMeasurement.logRevision !== lockedMeasurement.logRevision) {
@@ -145,6 +145,7 @@ export async function compactSurfaceRegion(
       shadowedRange: { start, end },
       shadowedSeqs,
       shadowedTokenCount,
+      provider,
       model,
       ...maxTokens === undefined ? {} : { maxTokens },
     })

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

@@ -58,6 +58,7 @@ const CHECKPOINT_PREAMBLE =
 /** Safe summary content plus the exact auxiliary call envelope recorded in provenance. */
 export interface SummaryResult {
   summary: ContentBlock[]
+  provider: string
   model: string
   maxTokens?: number
 }
@@ -78,17 +79,27 @@ export async function summarizeWithLlm(
   agent: Agent,
   signal?: AbortSignal,
 ): Promise<SummaryResult> {
-  const latestModel = agent.session.requestHeader()?.config.model
-  const model = config.summarizationModel || latestModel || agent.options.model || ''
-  if (model.length === 0) {
+  const latest = agent.session.requestHeader()?.config
+  const configured = config.summarizationProvider.length === 0
+    ? undefined
+    : { provider: config.summarizationProvider, model: config.summarizationModel }
+  const agentTarget = agent.options.provider !== undefined
+    && agent.options.provider.length > 0
+    && agent.options.model !== undefined
+    && agent.options.model.length > 0
+    ? { provider: agent.options.provider, model: agent.options.model }
+    : undefined
+  const target = configured ?? latest ?? agentTarget
+  if (target === undefined) {
     throw new Error(
-      'no model available for summarization: set BasicCompactConfig.summarizationModel, route one request, or set AgentOptions.model',
+      'no provider/model available for summarization: set both BasicCompactConfig summarization fields, route one request, or set both AgentOptions fields',
     )
   }
 
   const assembler = new BlockAssembler()
   const options: GenerateOptions = {
-    model,
+    provider: target.provider,
+    model: target.model,
     messages: [{
       role: 'user',
       content: [{ type: 'text', text: `Summarize this conversation history:\n\n${text}\n\nSummary:` }],
@@ -106,7 +117,12 @@ export async function summarizeWithLlm(
   if (!summary.some(block => block.text.trim().length > 0)) {
     throw new Error('summarization produced no text summary content')
   }
-  return { summary, model, maxTokens: config.maxTokens }
+  return {
+    summary,
+    provider: target.provider,
+    model: target.model,
+    maxTokens: config.maxTokens,
+  }
 }
 
 /**

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

@@ -10,7 +10,9 @@ export interface BasicCompactConfig {
   thresholdRatio?: number
   /** Recent surface tokens retained verbatim. Defaults to `floor(contextWindow * 0.16)`. */
   retainTokens?: number
-  /** Summary model; `''` resolves the latest routed model, then `AgentOptions.model`. Defaults to `''`. */
+  /** Summary provider; `''` resolves the latest routed pair, then the agent pair. Defaults to `''`. */
+  summarizationProvider?: string
+  /** Summary model; `''` resolves the latest routed pair, then the agent pair. Defaults to `''`. */
   summarizationModel?: string
   /** Provider generation cap for summarization. Defaults to `8192`. */
   maxTokens?: number
@@ -24,6 +26,7 @@ export interface BasicCompactConfig {
 export interface ResolvedConfig {
   readonly thresholdRatio: number
   readonly retainTokens: number
+  readonly summarizationProvider: string
   readonly summarizationModel: string
   readonly maxTokens: number
   readonly compactionRetries: number