Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

refactor(web): project usage and snapshot request context

Browse Source
This commit is contained in:
Hypatia May
2026-07-29 15:27:59 +08:00
parent e37cb23336
commit bf618dabf9
78 changed files with 748 additions and 934 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/client/connection/src/client/api.ts
+1 -1
View File
@@ -12,7 +12,7 @@ export type {
WorkspaceApi, WorkspaceId, WorkspaceView,
CommandsApi, CommandDescriptor, SkillsApi, SkillEntry,
ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning,
ModelReasoningEffort, ModelTarget, SessionMetrics, SessionModels, SessionProjectionsBlock,
ModelReasoningEffort, ModelRequestTelemetry, ModelTarget, SessionModels, SessionProjectionsBlock,
GoalsApi, GoalRef,
} from '@deepseek-ai/dsh-host-apiproxy/api'
export type { ToolCallView, ToolResultView } from '@deepseek-ai/dsh-tools/presentation'
packages/client/connection/src/client/fixture.ts
+115 -2
View File
@@ -15,6 +15,7 @@ import type {
AssistantMessage,
ContentBlock,
MessageSource,
TokenUsage,
ToolResultMessage,
UserMessage,
} from '@deepseek-ai/dsh-llm'
@@ -103,6 +104,16 @@ function sid(id: string): SessionId {
return id as SessionId
}
/** Deterministic provider billing attached to fixture assistant messages. */
function fixtureUsage(turn: number, step: number): TokenUsage {
return {
inputTokens: 20 + turn % 5,
outputTokens: 8 + step,
cacheReadTokens: turn === 0 ? 0 : 80,
cacheWriteTokens: turn % 10 === 0 ? 4 : 0,
}
}
/** fx-alpha history script: 60 turns (~130+ messages -> 3 pages at PAGE_MESSAGES=50),
* mixing reasoning blocks / tool call+result / steering / context. */
function buildAlphaLog(): SessionEvent[] {
@@ -110,7 +121,17 @@ function buildAlphaLog(): SessionEvent[] {
let time = Date.now() - 3_600_000
const push = (e: Record<string, unknown>): number => {
const seq = events.length
events.push({ seq, time: (time += 800), ...e })
const data = e['data'] as Record<string, unknown> | undefined
const authored = e['type'] === 'assistant/message' && data !== undefined
? {
...e,
data: {
...data,
usage: fixtureUsage(data['turn'] as number, data['step'] as number),
},
}
: e
events.push({ seq, time: (time += 800), ...authored })
return seq
}
for (let turn = 0; turn < 60; turn++) {
@@ -369,6 +390,60 @@ function permissionSelectOf(
}
}
interface FixtureTokenUsageProjection {
uncachedInputTokens: number
outputTokens: number
cacheReadTokens: number
cacheWriteTokens: number
}
/** Fixture parallel of token-meter's last-sample-replacing usage projection. */
function tokenUsageOf(log: readonly SessionEvent[]): FixtureTokenUsageProjection {
const totals: FixtureTokenUsageProjection = {
uncachedInputTokens: 0,
outputTokens: 0,
cacheReadTokens: 0,
cacheWriteTokens: 0,
}
let last: {
turn: number
step: number
buckets: FixtureTokenUsageProjection
} | null = null
for (const event of log) {
const item = event as unknown as {
type: string
data: {
turn?: number
step?: number
usage?: TokenUsage
chunk?: { type?: string; usage?: TokenUsage }
}
}
const usage = item.type === 'assistant/chunk' && item.data.chunk?.type === 'usage'
? item.data.chunk.usage
: item.type === 'assistant/message'
? item.data.usage
: undefined
if (usage === undefined || item.data.turn === undefined || item.data.step === undefined) continue
const buckets: FixtureTokenUsageProjection = {
uncachedInputTokens: usage.inputTokens,
outputTokens: usage.outputTokens,
cacheReadTokens: usage.cacheReadTokens ?? 0,
cacheWriteTokens: usage.cacheWriteTokens ?? 0,
}
const previous = last?.turn === item.data.turn && last.step === item.data.step
? last.buckets
: undefined
totals.uncachedInputTokens += buckets.uncachedInputTokens - (previous?.uncachedInputTokens ?? 0)
totals.outputTokens += buckets.outputTokens - (previous?.outputTokens ?? 0)
totals.cacheReadTokens += buckets.cacheReadTokens - (previous?.cacheReadTokens ?? 0)
totals.cacheWriteTokens += buckets.cacheWriteTokens - (previous?.cacheWriteTokens ?? 0)
last = { turn: item.data.turn, step: item.data.step, buckets }
}
return totals
}
function projectionValuesOf(log: readonly SessionEvent[]): Record<string, unknown> {
const values: Record<string, unknown> = {}
const titleEvent = log.findLast(item => (item as { type: string }).type === 'session/title')
@@ -383,12 +458,28 @@ function projectionValuesOf(log: readonly SessionEvent[]): Record<string, unknow
values['plan'] = planViewOf(log)
// Always present (GoalService unit composed): null before create / after clear.
values['goal'] = backscanGoal(log)
// Always present (token-meter composed): full-log provider billing.
values['tokenUsage'] = tokenUsageOf(log)
return values
}
/** Host push-frame parallel: emit one session/projection frame per key the given event advanced. */
function projectionFramesOf(id: SessionId, log: readonly SessionEvent[], event: SessionEvent): Extract<MuxFrame, { type: 'session/projection' }>[] {
const type = (event as { type: string }).type
if (
(type === 'assistant/chunk'
&& (event as unknown as { data: { chunk?: { type?: string } } }).data.chunk?.type === 'usage')
|| (type === 'assistant/message'
&& (event as unknown as { data: { usage?: TokenUsage } }).data.usage !== undefined)
) {
return [{
type: 'session/projection',
sessionId: id,
key: 'tokenUsage',
value: tokenUsageOf(log),
seq: event.seq,
}]
}
if (type === 'session/title') {
const values = projectionValuesOf(log)
/* v8 ignore next -- the advancing title event is in the log, so the key is present. */
@@ -853,7 +944,16 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
replays.delete(id)
const done = pieces.slice(0, i).join('')
append(id, { type: 'assistant/chunk', data: { turn, step, chunk: { type: 'block-end', index: 0, block: { type: 'text', text: done } } } })
append(id, { type: 'assistant/message', surfaceOp: 'append', data: { turn, step, message: assistantMessage(text(aborted ? `${done}（已中断）` : done)) } })
append(id, {
type: 'assistant/message',
surfaceOp: 'append',
data: {
turn,
step,
message: assistantMessage(text(aborted ? `${done}（已中断）` : done)),
usage: fixtureUsage(turn, step),
},
})
append(id, { type: 'step/end', data: { turn, step } })
append(id, { type: 'turn/end', data: { turn, reason: { kind: aborted ? 'cancelled' : 'completed' } } })
setRunning(id, false)
@@ -1036,6 +1136,19 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
append(id, { type: 'plan/mode', data: { active: plan.wanted } })
}
append(id, { type: 'user/message', surfaceOp: 'append', data: userMessage(content) })
const target = modelTargets.get(id) ?? { provider: 'deepseek', model: 'deepseek-v4-flash' }
const usage = tokenUsageOf(logOf(id))
emitMux({
type: 'session/model-request',
sessionId: id,
turn,
step: 0,
provider: target.provider,
model: target.model,
contextTokens: usage.uncachedInputTokens + usage.outputTokens
+ usage.cacheReadTokens + usage.cacheWriteTokens,
contextWindow: 128_000,
})
startReply(
id,
turn,
packages/client/connection/src/client/index.ts
+1 -1
View File
@@ -17,7 +17,7 @@ export type {
ToolCallView, ToolResultView, WorkspaceApi, WorkspaceId, WorkspaceView,
CommandsApi, CommandDescriptor, SkillsApi, SkillEntry,
ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning,
ModelReasoningEffort, ModelTarget, SessionMetrics, SessionModels, SessionProjectionsBlock,
ModelReasoningEffort, ModelRequestTelemetry, ModelTarget, SessionModels, SessionProjectionsBlock,
RpcRequest, RpcResponse, RpcResult, RpcError, RpcErrorCode,
ClientRequest, ServerResponse, ServerRequest, ClientResponse, RpcMessage, RpcReceipt,
IApiClient, SessionId, SessionEvent, ContentBlock, StreamChunk,