Merge newest origin/master into token-meter-service

packages/llm/token-meter/README.md

@@ -19,7 +19,7 @@ The estimator intentionally uses one fixed heuristic: four characters per token
 
 `measure()` synchronizes once and returns one detached, deeply immutable snapshot. `totalTokens` is request-and-response pressure, while `surfaceTokens` is the surface-only heuristic total and equals the sum of `nodes[].tokens`. A `requestHeader` override affects pressure fields only; the surface fields still describe the current session. Every call clones the positional nodes, so measurement is O(surface).
 
-The fold tracks request headers and deltas, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope and its total is no lower than that call's full heuristic anchor; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements.
+The fold tracks full request-header snapshots, step boundaries, surface appends and replacements, successful assistant messages, provider usage, and assistant-chunk provenance. Provider usage is reused only when the latest successful call's canonical request envelope matches the measured envelope and its total is no lower than that call's full heuristic anchor; a later success replaces the earlier anchor. Otherwise the complete current envelope and surface are estimated. Surface changes remain signed relative to a matching anchor, including negative deltas after shrinking replacements.
 
 Usage accounting sums disjoint input, cache-read, cache-write, and output buckets; reasoning is not added again. Every successful call records an assistant anchor, including content-less calls. An explicit empty provenance list means a known empty provider stream, while absent legacy provenance conservatively treats the durable assistant output as provider output.
 

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

@@ -9,7 +9,7 @@ import z from 'schemastery'
 import { BlockAssembler, deepFreeze } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, Message, TokenUsage } from '@deepseek-ai/dsh-llm'
 import type { EpochHeader, Session, SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session'
-import { applyHeaderDelta, canonicalHeader, headerEquals, isSurfaceEvent } from '@deepseek-ai/dsh-session'
+import { canonicalHeader, headerEquals, isSurfaceEvent } from '@deepseek-ai/dsh-session'
 import type {
   TokenMeasurement,
   TokenMeasurementBaseline,
@@ -220,12 +220,6 @@ export class TokenMeterService extends Service {
       case 'request/header':
         nextHeader = canonicalHeader(event.data.header)
         break
-      case 'request/header-delta':
-        if (state.header === undefined) {
-          throw new Error(`token meter: request/header-delta at seq ${event.seq} has no preceding header`)
-        }
-        nextHeader = applyHeaderDelta(state.header, event.data)
-        break
       case 'step/start':
         if (state.stepStart !== undefined) {
           throw new Error(

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

@@ -375,10 +375,13 @@ describe('replay anchors and surface folds', () => {
     }).baseline.kind).toBe('estimated')
   })
 
-  it('folds valid header deltas into the effective envelope', () => {
-    const session = new Session(SessionId('header-delta'))
+  it('folds the latest full header snapshot into the effective envelope', () => {
+    const session = new Session(SessionId('header-snapshot'))
     appendHeader(session, header('deepseek-v4-flash'))
-    session.append('request/header-delta', { config: { provider: 'mock', model: 'deepseek-v4-pro' } })
+    session.append('request/header', {
+      header: header('deepseek-v4-pro'),
+      reason: 'change',
+    })
     const result = meter().measure(session)
     expect(result.baseline.kind).toBe('estimated')
     expect(result.logRevision).toBe(2)
@@ -401,7 +404,7 @@ describe('replay anchors and surface folds', () => {
     expect(before.surfaceDeltaTokens).toBeGreaterThan(0)
     expectSurfaceTotal(before)
 
-    const first = seeded.surface.nodes[0]!.seq
+    const first = seeded.surface.nodes[0]!
     seeded.append('user/message', {
       content: [{ type: 'text', text: 'replacement' }],
       source: { kind: 'plugin', plugin: 'test' },
@@ -440,12 +443,6 @@ describe('malformed replay and listener lifecycle', () => {
     expect(() => service.measure(session)).toThrow(pattern)
   }
 
-  it('rejects a header delta before any snapshot transactionally', () => {
-    const session = new Session(SessionId('bad-delta'))
-    session.append('request/header-delta', { config: { provider: 'mock', model: 'deepseek-v4-flash' } })
-    expectRepeatedFailure(meter(), session, /no preceding header/)
-  })
-
   it('rejects an assistant without its step boundary transactionally', () => {
     const session = new Session(SessionId('bad-step'))
     appendHeader(session, header('deepseek-v4-flash'))