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

359 lines
14 KiB
TypeScript
Raw Normal View History

fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact'
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
import { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError } from '@deepseek-ai/dsh-llm'
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm'
import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm'
import { defineTool } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
2026-07-14 02:32:35 +08:00
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
import * as Invariants from '@deepseek-ai/dsh-invariants'
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
import * as LlmRetry from '@deepseek-ai/dsh-llm-retry'
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
import { SessionId, type SurfaceEvent } from '@deepseek-ai/dsh-session'
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
/**
* CBR-001 regression through the real loop. A replacement checkpoint has a high
* log seq at the surface head and carries no tool pair, so both adjacent cuts
* must be safe and re-compacting that checkpoint alone must succeed. This pins
* surface-position semantics rather than raw-log scanning.
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
*/
class ReproCompactService extends BasicCompactService {
2026-07-14 21:57:52 +08:00
override async summarize(): Promise<{ summary: ContentBlock[]; provider: string; model: string }> {
return {
summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }],
provider: 'mock',
model: 'stub',
}
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
}
}
/** Each call emits one tool-call until exhausted, then a final text answer. */
class StepwiseToolAdapter extends LlmAdapter {
calls = 0
constructor(private toolSteps: number) {
super()
}
async * stream(_options: GenerateOptions): AsyncIterable<StreamChunk> {
const n = this.calls
this.calls += 1
if (n < this.toolSteps) {
const id = CallId(`c${n}`)
const args = `{"i":${n}}`
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'block-end', index: 0, block: { type: 'text', text: `step ${n}` } }
yield { type: 'block-start', index: 1, blockType: 'tool-call' }
yield { type: 'block-end', index: 1, block: { type: 'tool-call', id, name: 'work', arguments: args } }
yield { type: 'finish', reason: { kind: 'tool-calls' } }
return
}
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'block-end', index: 0, block: { type: 'text', text: 'all done' } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
}
/** First conversation request overflows, then the rebuilt retry succeeds. */
class OverflowRecoveryAdapter extends LlmAdapter {
readonly conversationRequests: GenerateOptions[] = []
readonly summaryRequests: GenerateOptions[] = []
constructor(
private readonly delivery: 'thrown' | 'in-band',
private readonly transientAfterOverflow = false,
) {
super()
}
override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
if (options.system?.includes('You are a compaction engine')) {
this.summaryRequests.push(options)
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'block-end', index: 0, block: { type: 'text', text: 'RECOVERY CHECKPOINT' } }
yield { type: 'finish', reason: { kind: 'stop' } }
return
}
this.conversationRequests.push(options)
if (this.conversationRequests.length === 1) {
if (this.delivery === 'thrown') {
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
throw new LlmError('request too large for model context', CONTEXT_WINDOW_EXCEEDED_CODE)
}
yield {
type: 'finish',
reason: {
kind: 'error',
failure: {
message: 'request too large for model context',
code: CONTEXT_WINDOW_EXCEEDED_CODE,
},
},
}
return
}
if (this.transientAfterOverflow && this.conversationRequests.length === 2) {
throw new LlmError('temporary provider outage', 'SERVER')
}
yield { type: 'block-start', index: 0, blockType: 'text' }
yield { type: 'block-end', index: 0, block: { type: 'text', text: 'recovered' } }
yield { type: 'finish', reason: { kind: 'stop' } }
}
}
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> {
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(Invariants)
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(TokenMeterService, { contextWindow: 400 })
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
ctx.llm.registerAdapter(['mock'], new StepwiseToolAdapter(toolSteps))
ctx.tools.register(defineTool({
name: 'work',
description: 'does work',
parameters: { i: { type: 'number' } },
async execute() {
return [{ type: 'text', text: 'work result' }]
},
}))
// Small window so several tool steps cross the threshold and compaction
// fires within the runaway turn after enough history can shrink.
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
const compact = new ReproCompactService(ctx, {
auto: true,
thresholdRatio: 0.5,
retainTokens: 50,
summarizationModel: '',
maxTokens: 8192,
compactionRetries: 1,
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
})
return { ctx, compact }
}
2026-07-14 02:32:35 +08:00
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'idle') {
dispose()
resolve()
}
})
})
}
function seedOverflowHistory(agent: Agent): void {
for (let turn = 1; turn <= 2; turn += 1) {
const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY'
agent.session.append('turn/start', {
turn,
trigger: { kind: 'message', source: { kind: 'user' } },
})
agent.session.append('user/message', {
content: [{ type: 'text', text: `${sentinel} ${'old context '.repeat(200)}` }],
source: { kind: 'user' },
}, { surfaceOp: 'append' })
agent.session.append('step/start', { turn, step: 1 })
agent.session.append('assistant/message', {
provenance: { provider: 'mock', model: 'mock' },
turn,
step: 1,
content: [{ type: 'text', text: `historical response ${turn} ${'detail '.repeat(200)}` }],
}, { surfaceOp: 'append' })
agent.session.append('step/end', { turn, step: 1 })
agent.session.append('turn/end', { turn, reason: { kind: 'completed' } })
}
}
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () => {
it('uses the model actually routed by agent/request for post-step pressure', async () => {
const { ctx } = await harness(8)
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
try {
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
const agent = ctx.agentLoop.create(SessionId('routed-pressure'), {
provider: 'unconfigured-agent-fallback',
model: 'unconfigured-agent-fallback',
})
agent.send([{ type: 'text', text: 'do a routed multi-step task' }])
await waitForIdle(ctx, agent)
expect(agent.session.requestHeader()?.config.model).toBe('mock')
expect(agent.session.events.some(event => event.type === 'compact/summary')).toBe(true)
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'completed' } },
})
} finally {
await ctx.fiber.dispose()
}
})
it('runs automatic pressure after the current tool result and before step/end', async () => {
const { ctx } = await harness(8)
try {
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
const agent = ctx.agentLoop.create(SessionId('post-step-order'), { provider: 'mock', model: 'mock' })
agent.send([{ type: 'text', text: 'do tool work' }])
await waitForIdle(ctx, agent)
const events = [...agent.session.events]
const compactStart = events.find(event => event.type === 'compact/start')
expect(compactStart).toBeDefined()
const precedingResult = events.findLast(event =>
event.type === 'tool/result' && event.seq < compactStart!.seq,
)
if (precedingResult?.type !== 'tool/result') throw new Error('expected a durable tool result before compaction')
const stepEnd = events.find(event =>
event.type === 'step/end'
&& event.data.step === precedingResult.data.step
&& event.seq > compactStart!.seq,
)
expect(precedingResult.seq).toBeLessThan(compactStart!.seq)
expect(compactStart!.seq).toBeLessThan(stepEnd!.seq)
} finally {
await ctx.fiber.dispose()
}
})
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
it('the head checkpoint the loop lands is a balanced cut on both sides', async () => {
const { ctx } = await harness(8)
try {
Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id # Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00
const agent = ctx.agentLoop.create(SessionId('repro'), { provider: 'mock', model: 'mock' })
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
agent.send([{ type: 'text', text: 'do a long multi-step task' }])
await waitForIdle(ctx, agent)
const events = [...agent.session.events]
// A compaction ran: at least one checkpoint landed on the surface.
const checkpoints = events.filter(
(e): e is SurfaceEvent =>
e.type === 'user/message'
&& typeof (e as SurfaceEvent).surfaceOp === 'object',
)
expect(checkpoints.length).toBeGreaterThan(0)
// High log position does not make a text-only checkpoint mid-step; both
// its start and end cuts are balanced in surface order.
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
const nodes = agent.session.surface.nodes
for (const cp of checkpoints) {
const index = nodes.indexOf(cp.seq)
if (index === -1) continue // shadowed by a later checkpoint — no longer an edge.
expect(toolPairingBalancedBefore(agent.session, cp.seq),
`checkpoint seq ${cp.seq} must be a balanced region START`).toBe(true)
expect(toolPairingBalancedAfter(agent.session, cp.seq),
`checkpoint seq ${cp.seq} must be a balanced region END`).toBe(true)
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
}
} finally {
await ctx.fiber.dispose()
}
})
})
describe('context-overflow recovery across the real loop and compact-basic', () => {
it.each(['thrown', 'in-band'] as const)(
'force-compacts a %s overflow between failed and retry steps',
async (delivery) => {
const ctx = new Context()
const adapter = new OverflowRecoveryAdapter(delivery)
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(Invariants)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(TokenMeterService, { contextWindow: 128 })
ctx.llm.registerAdapter(['mock'], adapter)
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, provider: 'mock', model: 'mock' }))
await ctx.plugin(BasicCompactService, {
thresholdRatio: 1,
retainTokens: 100,
maxTokens: 64,
compactionRetries: 0,
maxOverflowRetries: 1,
})
try {
Merge latest origin/master into compact-post-step-overflow-recovery # Conflicts: # docs/agent-lifecycle.md # docs/architecture.md # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/event-producer-consumer.md # docs/rfc/INDEX.md # docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md # docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md # docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md # docs/rfc/implemented/feature/2026-07-07-session-prefix.md # packages/compact/compact-basic/README.md # packages/compact/compact-basic/src/config.ts # packages/compact/compact-basic/src/index.ts # packages/compact/compact-basic/src/summarizer.ts # packages/compact/compact-basic/tests/compact-basic.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/compact/compact/README.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/llm/llm-deepseek/src/adapter.ts # packages/llm/llm-pi-ai/README.md # packages/llm/llm-pi-ai/src/stream.ts # packages/llm/llm-pi-ai/tests/convert.spec.ts # packages/llm/llm/README.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
const agent = ctx.agentLoop.create(SessionId(`overflow-${delivery}`), {
provider: 'unconfigured-agent-fallback',
model: 'unconfigured-agent-fallback',
})
seedOverflowHistory(agent)
agent.send([{ type: 'text', text: 'continue from history' }])
await agent.whenIdle()
expect(adapter.conversationRequests).toHaveLength(2)
expect(adapter.summaryRequests).toHaveLength(1)
expect(JSON.stringify(adapter.conversationRequests[0]!.messages)).toContain('OLD HISTORY SENTINEL')
const retry = JSON.stringify(adapter.conversationRequests[1]!.messages)
expect(retry).toContain('RECOVERY CHECKPOINT')
expect(retry).not.toContain('OLD HISTORY SENTINEL')
const events = [...agent.session.events]
const failedEnd = events.find(event =>
event.type === 'step/end' && event.data.turn === 3 && event.data.step === 1,
)!
const retryStart = events.find(event =>
event.type === 'step/start' && event.data.turn === 3 && event.data.step === 2,
)!
const compaction = events.filter(event =>
event.type === 'compact/start'
|| event.type === 'compact/summary'
|| event.type === 'compact/end',
)
expect(compaction.map(event => event.type)).toEqual([
'compact/start',
'compact/summary',
'compact/end',
])
expect(compaction.every(event => event.seq > failedEnd.seq && event.seq < retryStart.seq)).toBe(true)
expect(events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'completed' } },
})
} finally {
await ctx.fiber.dispose()
}
},
)
it('keeps context-overflow and transient retry budgets independent in one sequence', async () => {
const ctx = new Context()
const adapter = new OverflowRecoveryAdapter('thrown', true)
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(Invariants)
await ctx.plugin(LlmRetry, {
maxTransientRetries: 1,
initialDelayMs: 1,
maxDelayMs: 1,
jitterRatio: 0,
})
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(TokenMeterService, { contextWindow: 128 })
ctx.llm.registerAdapter(['mock'], adapter)
await ctx.plugin(BasicCompactService, {
thresholdRatio: 1,
retainTokens: 100,
maxTokens: 64,
compactionRetries: 0,
maxOverflowRetries: 1,
})
try {
const agent = ctx.agentLoop.create(SessionId('alternating-recovery'), { provider: 'mock', model: 'mock' })
seedOverflowHistory(agent)
agent.send([{ type: 'text', text: 'continue from history' }])
await agent.whenIdle()
expect(adapter.conversationRequests).toHaveLength(3)
expect(adapter.summaryRequests).toHaveLength(1)
expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data))
.toEqual([expect.objectContaining({ step: 2, retry: 1, failure: { message: 'temporary provider outage', code: 'SERVER' } })])
expect(agent.session.events.filter(event => event.type === 'step/start').slice(-3).map(event => event.data.step))
.toEqual([1, 2, 3])
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'completed' } },
})
} finally {
await ctx.fiber.dispose()
}
})
})