Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification

# Conflicts: # .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md # .agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml # .agents/notes/implemented/feature/2026-07-06-sandbox.md # .agents/notes/implemented/feature/2026-07-06-sandbox.zh.md # .agents/notes/implemented/feature/2026-07-27-tmux-location-context.i18n.yaml # .agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml # .agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml # .agents/notes/implemented/simplification/2026-07-30-private-agent-send.i18n.yaml # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/compaction.i18n.yaml # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/llm-streaming.md # docs/core-data-structures/llm-streaming.zh.md # docs/core-data-structures/session.i18n.yaml # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/acp-agent/tests/snapshots/bash-spill/session.jsonl # examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/cancel/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl # examples/acp-agent/tests/snapshots/error-finish/session.jsonl # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/fs-edit/session.jsonl # examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl # examples/acp-agent/tests/snapshots/fs-read/session.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl # examples/acp-agent/tests/snapshots/fs-write/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl # examples/acp-agent/tests/snapshots/multi-turn/session.jsonl # examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/pty-tools/session.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl # examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl # examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl # examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/acp-agent/tests/snapshots/todo-write/session.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl # examples/acp-agent/tests/snapshots/web-fetch/session.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl # examples/headless-agent/tests/semantic-checkpoint-snapshots/tool-outcome-unknown/session.expected.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/pty-tools/session.jsonl # examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl # packages/client/runtime/README.i18n.yaml # packages/client/runtime/src/client/sessions/request-inspection.ts # packages/compact/compact-basic/README.i18n.yaml # packages/compact/compact-basic/README.md # packages/compact/compact-basic/README.zh.md # packages/compact/compact-basic/src/index.ts # packages/context/time-context/tests/time-context.spec.ts # packages/context/tmux-context/README.i18n.yaml # packages/context/tmux-context/tests/tmux-context.spec.ts # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/README.md # packages/core/agent-loop/README.zh.md # packages/core/agent-loop/src/agent.ts # packages/core/agent/README.i18n.yaml # packages/core/agent/README.md # packages/core/agent/README.zh.md # packages/core/agent/src/types.ts # packages/core/session/README.i18n.yaml # packages/core/session/README.md # packages/core/session/README.zh.md # packages/fs/tool-str-replace-editor/tests/tools.spec.ts # packages/goal/command-goal/tests/command-goal.spec.ts # packages/goal/goal/tests/goal.spec.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/tests/api-proxy-workspace.spec.ts # packages/llm/llm/README.i18n.yaml # packages/llm/llm/README.md # packages/llm/llm/README.zh.md # packages/llm/llm/src/index.ts # packages/pty/pty-local/tests/index.spec.ts # packages/pty/pty-local/tests/local.spec.ts # packages/pty/pty/tests/service.spec.ts # packages/pty/tool-bash-persistent/tests/loader-composition.spec.ts # packages/pty/tool-bash-persistent/tests/tools.spec.ts # packages/pty/tool-pty/tests/loader-composition.spec.ts # packages/pty/tool-pty/tests/tools.spec.ts # packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts # packages/skill/tool-skill/tests/tool-skill.spec.ts # packages/tasks/tasks-local/tests/tasks.spec.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/tests/tui.spec.ts # packages/ui/user-approval/src/index.ts # packages/ui/user-approval/tests/approval.spec.ts
2026-07-31 22:16:40 +08:00
parent afedf18ccf 9a3bdd599c
commit e0988abc74
1010 changed files with 105572 additions and 5504 deletions
@@ -0,0 +1,333 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import { createMessage, createUserMessage } from '@deepseek-ai/dsh-llm'
+import type { TokenUsage } from '@deepseek-ai/dsh-llm'
+import SessionStore from '@deepseek-ai/dsh-session'
+import type { Session } from '@deepseek-ai/dsh-session'
+import SessionProjectionRegistry from '@deepseek-ai/dsh-session-projection'
+import TokenMeterService from '@deepseek-ai/dsh-token-meter'
+import type { ContextPressureProjection, TokenUsageProjection } from '@deepseek-ai/dsh-token-meter/client'
+
+const ZERO: TokenUsageProjection = {
+  uncachedInputTokens: 0,
+  outputTokens: 0,
+  cacheReadTokens: 0,
+  cacheWriteTokens: 0,
+}
+
+async function harness(): Promise<{
+  ctx: Context
+  session: Session
+  meterFiber: Awaited<ReturnType<Context['plugin']>>
+}> {
+  const ctx = new Context()
+  await ctx.plugin(SessionStore)
+  await ctx.plugin(SessionProjectionRegistry)
+  const meterFiber = await ctx.plugin(TokenMeterService)
+  return { ctx, session: ctx.sessions.create(), meterFiber }
+}
+
+function startStep(session: Session, turn: number, step: number): void {
+  session.append('step/start', { turn, step })
+}
+
+function usageChunk(
+  session: Session,
+  usage: TokenUsage,
+  turn: number,
+  step: number,
+): number {
+  return session.append('assistant/chunk', {
+    turn,
+    step,
+    chunk: { type: 'usage', usage },
+  }).seq
+}
+
+function finalUsage(
+  session: Session,
+  usage: TokenUsage,
+  turn: number,
+  step: number,
+  sourceSeqs: number[],
+): void {
+  session.append('assistant/message', {
+    turn,
+    step,
+    message: createMessage({
+      role: 'assistant',
+      content: [],
+      source: { kind: 'model', provider: 'mock', model: 'mock' },
+    }),
+    usage,
+  }, { surfaceOp: 'append', sourceEventSeqs: sourceSeqs })
+  session.append('step/end', { turn, step })
+}
+
+const projected = (ctx: Context, session: Session): TokenUsageProjection => {
+  const value = ctx.sessionProjections.snapshot(session).values.tokenUsage
+  if (value === undefined) throw new Error('tokenUsage projection is not registered')
+  return value
+}
+
+describe('tokenUsage session projection', () => {
+  it('serves zero buckets for an empty log', async () => {
+    const { ctx, session } = await harness()
+    expect(projected(ctx, session)).toEqual(ZERO)
+  })
+
+  it('does not count a usage chunk and identical final usage twice', async () => {
+    const { ctx, session } = await harness()
+    const changes: unknown[] = []
+    ctx.sessionProjections.onChanged((_session, key, value) => {
+      if (key === 'tokenUsage') changes.push(value)
+    })
+    const usage = {
+      inputTokens: 10,
+      outputTokens: 4,
+      cacheReadTokens: 7,
+      cacheWriteTokens: 2,
+      reasoningTokens: 3,
+    }
+    startStep(session, 1, 1)
+    const source = usageChunk(session, usage, 1, 1)
+    finalUsage(session, usage, 1, 1, [source])
+
+    expect(projected(ctx, session)).toEqual({
+      uncachedInputTokens: 10,
+      outputTokens: 4,
+      cacheReadTokens: 7,
+      cacheWriteTokens: 2,
+    })
+    expect(changes).toHaveLength(1)
+  })
+
+  it('replaces an earlier same-step chunk sample with the final usage', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    const source = usageChunk(session, {
+      inputTokens: 10,
+      outputTokens: 2,
+      cacheReadTokens: 3,
+    }, 1, 1)
+    finalUsage(session, {
+      inputTokens: 14,
+      outputTokens: 5,
+      cacheReadTokens: 8,
+      cacheWriteTokens: 1,
+    }, 1, 1, [source])
+
+    expect(projected(ctx, session)).toEqual({
+      uncachedInputTokens: 14,
+      outputTokens: 5,
+      cacheReadTokens: 8,
+      cacheWriteTokens: 1,
+    })
+  })
+
+  it('accumulates disjoint buckets across steps without adding reasoning twice', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    const first = usageChunk(session, {
+      inputTokens: 10,
+      outputTokens: 6,
+      reasoningTokens: 5,
+      cacheReadTokens: 2,
+    }, 1, 1)
+    finalUsage(session, {
+      inputTokens: 10,
+      outputTokens: 6,
+      reasoningTokens: 5,
+      cacheReadTokens: 2,
+    }, 1, 1, [first])
+    startStep(session, 1, 2)
+    const second = usageChunk(session, {
+      inputTokens: 20,
+      outputTokens: 9,
+      reasoningTokens: 7,
+      cacheWriteTokens: 4,
+    }, 1, 2)
+    finalUsage(session, {
+      inputTokens: 20,
+      outputTokens: 9,
+      reasoningTokens: 7,
+      cacheWriteTokens: 4,
+    }, 1, 2, [second])
+
+    expect(projected(ctx, session)).toEqual({
+      uncachedInputTokens: 30,
+      outputTokens: 15,
+      cacheReadTokens: 2,
+      cacheWriteTokens: 4,
+    })
+  })
+
+  it('retains a usage chunk when the request produces no final assistant message', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    usageChunk(session, { inputTokens: 9, outputTokens: 1 }, 1, 1)
+    session.append('step/end', { turn: 1, step: 1 })
+    expect(projected(ctx, session)).toEqual({
+      uncachedInputTokens: 9,
+      outputTokens: 1,
+      cacheReadTokens: 0,
+      cacheWriteTokens: 0,
+    })
+  })
+
+  it('does not erase historical billing when the visible surface is replaced', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    const source = usageChunk(session, { inputTokens: 12, outputTokens: 3 }, 1, 1)
+    finalUsage(session, { inputTokens: 12, outputTokens: 3 }, 1, 1, [source])
+    const before = session.append('user/message', createUserMessage({
+      content: [{ type: 'text', text: 'before compaction' }],
+      source: { kind: 'user' },
+    }), { surfaceOp: 'append' })
+    session.append('user/message', createUserMessage({
+      content: [{ type: 'text', text: 'compacted' }],
+      source: { kind: 'plugin', plugin: 'test' },
+    }), {
+      surfaceOp: { op: 'replace', start: before.seq, end: before.seq },
+      sourceEventSeqs: [before.seq],
+    })
+
+    expect(projected(ctx, session)).toEqual({
+      uncachedInputTokens: 12,
+      outputTokens: 3,
+      cacheReadTokens: 0,
+      cacheWriteTokens: 0,
+    })
+  })
+
+  it('unregisters with the token-meter fiber and restores from a JSON checkpoint', async () => {
+    const { ctx, session, meterFiber } = await harness()
+    startStep(session, 1, 1)
+    usageChunk(session, { inputTokens: 8, outputTokens: 2, cacheReadTokens: 5 }, 1, 1)
+    const checkpoint = JSON.parse(JSON.stringify(
+      ctx.sessionProjections.checkpoint(session),
+    )) as ReturnType<typeof ctx.sessionProjections.checkpoint>
+
+    await meterFiber.dispose()
+    expect(ctx.sessionProjections.snapshot(session).values).not.toHaveProperty('tokenUsage')
+
+    await ctx.plugin(TokenMeterService)
+    expect(ctx.sessionProjections.viewCheckpoint(checkpoint).tokenUsage).toEqual({
+      uncachedInputTokens: 8,
+      outputTokens: 2,
+      cacheReadTokens: 5,
+      cacheWriteTokens: 0,
+    })
+  })
+})
+
+const pressure = (ctx: Context, session: Session): ContextPressureProjection => {
+  const value = ctx.sessionProjections.snapshot(session).values.contextPressure
+  if (value === undefined) throw new Error('contextPressure projection is not registered')
+  return value
+}
+
+function recordContext(session: Session, model: string, contextWindow?: number): void {
+  session.append('request/context', {
+    provider: 'mock',
+    model,
+    ...contextWindow === undefined ? {} : { contextWindow },
+  })
+}
+
+describe('contextPressure session projection', () => {
+  it('serves no pressure or capacity for an empty log', async () => {
+    const { ctx, session } = await harness()
+    expect(pressure(ctx, session)).toEqual({})
+  })
+
+  it('does not synthesize zero pressure before a provider usage sample', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    recordContext(session, 'small', 64_000)
+    expect(pressure(ctx, session)).toEqual({ contextWindow: 64_000 })
+  })
+
+  it('sums prompt-side buckets and excludes response output', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    usageChunk(session, {
+      inputTokens: 100,
+      outputTokens: 4_000,
+      cacheReadTokens: 20,
+      cacheWriteTokens: 5,
+    }, 1, 1)
+    // Output is deliberately absent: occupancy describes the prompt that was
+    // sent, so it holds still while the response streams.
+    expect(pressure(ctx, session).pressureTokens).toBe(125)
+  })
+
+  it('replaces pressure with the newest request rather than accumulating', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    const first = usageChunk(session, { inputTokens: 100, outputTokens: 10 }, 1, 1)
+    finalUsage(session, { inputTokens: 100, outputTokens: 10 }, 1, 1, [first])
+    startStep(session, 2, 1)
+    usageChunk(session, { inputTokens: 250, outputTokens: 10 }, 2, 1)
+    expect(pressure(ctx, session).pressureTokens).toBe(250)
+  })
+
+  it('carries the newest recorded capacity and replaces it on a model switch', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    recordContext(session, 'small', 64_000)
+    usageChunk(session, { inputTokens: 100, outputTokens: 10 }, 1, 1)
+    expect(pressure(ctx, session)).toEqual({ pressureTokens: 100, contextWindow: 64_000 })
+    recordContext(session, 'large', 256_000)
+    expect(pressure(ctx, session)).toEqual({ pressureTokens: 100, contextWindow: 256_000 })
+  })
+
+  it('removes an older capacity when the newest route advertises none', async () => {
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    recordContext(session, 'small', 64_000)
+    usageChunk(session, { inputTokens: 100, outputTokens: 10 }, 1, 1)
+    recordContext(session, 'unknown')
+    expect(pressure(ctx, session)).toEqual({ pressureTokens: 100 })
+  })
+
+  it('pushes no change for unrelated events or a restated capacity', async () => {
+    // The registry gates its change feed on Object.is, so a unit that rebuilt
+    // state for an event it does not care about would push phantom updates.
+    const { ctx, session } = await harness()
+    startStep(session, 1, 1)
+    recordContext(session, 'small', 64_000)
+    usageChunk(session, { inputTokens: 100, outputTokens: 10 }, 1, 1)
+    const changed: string[] = []
+    ctx.sessionProjections.onChanged((_session, key) => { changed.push(key) })
+
+    session.append('todo/write', { todos: [] })
+    expect(changed).not.toContain('contextPressure')
+    // A repeated capacity record for the same window is also a no-op.
+    recordContext(session, 'small', 64_000)
+    expect(changed).not.toContain('contextPressure')
+    // A real capacity change still reports.
+    recordContext(session, 'large', 256_000)
+    expect(changed).toContain('contextPressure')
+  })
+
+  it('restores from a JSON checkpoint and unregisters with the token-meter fiber', async () => {
+    const { ctx, session, meterFiber } = await harness()
+    startStep(session, 1, 1)
+    recordContext(session, 'small', 64_000)
+    usageChunk(session, { inputTokens: 42, outputTokens: 2 }, 1, 1)
+    const checkpoint = JSON.parse(JSON.stringify(
+      ctx.sessionProjections.checkpoint(session),
+    )) as ReturnType<typeof ctx.sessionProjections.checkpoint>
+    expect(checkpoint.contextPressure?.ver).toBe(2)
+
+    await meterFiber.dispose()
+    expect(ctx.sessionProjections.snapshot(session).values).not.toHaveProperty('contextPressure')
+
+    await ctx.plugin(TokenMeterService)
+    expect(ctx.sessionProjections.viewCheckpoint(checkpoint).contextPressure).toEqual({
+      pressureTokens: 42,
+      contextWindow: 64_000,
+    })
+  })
+})