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
This commit is contained in:
_Kerman
@@ -258,7 +258,7 @@ describe('agent loop', () => {
|
||||
// NO system field at all (not an empty string).
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} }))
|
||||
ctx.on('system-prompt/assemble', async () => ({ sections: [], contexts: [], tools: [], variables: {} }))
|
||||
const agent = ctx.agentLoop.create(SessionId('a-no-system'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
send(agent, 'hi')
|
||||
@@ -268,6 +268,178 @@ describe('agent loop', () => {
|
||||
expect('system' in adapter.requests[0]!).toBe(false)
|
||||
})
|
||||
|
||||
it('materializes changed runtime context at the history tail without rewriting the system header', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
textResponse('one'),
|
||||
textResponse('two'),
|
||||
textResponse('three'),
|
||||
textResponse('four'),
|
||||
textResponse('five'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
let mode = 'read-only'
|
||||
const dispose = ctx.systemPrompt.context({ name: 'policy', order: 0, text: () => `Mode: ${mode}.` })
|
||||
const agent = ctx.agentLoop.create(SessionId('a-runtime-context'), { provider: 'mock', model: 'mock' })
|
||||
const contextEvents = () => agent.session.events.flatMap(event =>
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& event.data.source.plugin === '@deepseek-ai/dsh-system-prompt'
|
||||
? [event]
|
||||
: [])
|
||||
|
||||
send(agent, 'first')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(contextEvents()).toHaveLength(1)
|
||||
expect(contextEvents()[0]?.data.content).toEqual([{
|
||||
type: 'text',
|
||||
text: 'Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nMode: read-only.',
|
||||
}])
|
||||
|
||||
send(agent, 'unchanged')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(contextEvents()).toHaveLength(1)
|
||||
|
||||
mode = 'danger-full-access'
|
||||
send(agent, 'changed')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(contextEvents()).toHaveLength(2)
|
||||
const changedBlock = contextEvents()[1]?.data.content[0]
|
||||
expect(changedBlock?.type).toBe('text')
|
||||
if (changedBlock?.type !== 'text') throw new Error('changed runtime context is not text')
|
||||
expect(changedBlock.text).toContain('danger-full-access')
|
||||
|
||||
dispose()
|
||||
send(agent, 'cleared')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(contextEvents()).toHaveLength(3)
|
||||
expect(contextEvents()[2]?.data.content).toEqual([{
|
||||
type: 'text',
|
||||
text: 'Current runtime context: none. Earlier runtime-context snapshots no longer apply.',
|
||||
}])
|
||||
|
||||
send(agent, 'still clear')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(contextEvents()).toHaveLength(3)
|
||||
expect(adapter.requests.map(request => request.system)).toEqual(Array(5).fill(adapter.requests[0]?.system))
|
||||
expect(agent.session.events.filter(event => event.type === 'request/header')).toHaveLength(1)
|
||||
})
|
||||
|
||||
it('re-emits unchanged runtime context when a surface replacement removed the retained snapshot', async () => {
|
||||
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
|
||||
const ctx = await harness(adapter)
|
||||
ctx.systemPrompt.context({ name: 'policy', order: 0, text: 'Mode: read-only.' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a-runtime-context-compacted'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
send(agent, 'first')
|
||||
await waitForIdle(ctx, agent)
|
||||
const contextEvent = agent.session.events.find(event =>
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& event.data.source.plugin === '@deepseek-ai/dsh-system-prompt')
|
||||
if (contextEvent?.type !== 'user/message') throw new Error('first turn did not materialize runtime context')
|
||||
agent.session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'compacted summary' }],
|
||||
source: { kind: 'plugin', plugin: 'test-compaction' },
|
||||
}), {
|
||||
surfaceOp: { op: 'replace', start: contextEvent.seq, end: contextEvent.seq },
|
||||
sourceEventSeqs: [contextEvent.seq],
|
||||
})
|
||||
|
||||
send(agent, 'after compaction')
|
||||
await waitForIdle(ctx, agent)
|
||||
const runtimeContexts = agent.session.events.flatMap(event =>
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& event.data.source.plugin === '@deepseek-ai/dsh-system-prompt'
|
||||
? [event]
|
||||
: [])
|
||||
expect(runtimeContexts).toHaveLength(2)
|
||||
expect(adapter.requests[1]?.messages.some(message =>
|
||||
message.source.kind === 'plugin'
|
||||
&& message.source.plugin === '@deepseek-ai/dsh-system-prompt')).toBe(true)
|
||||
})
|
||||
|
||||
it('clears compacted runtime context after the active set becomes empty', async () => {
|
||||
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
|
||||
const ctx = await harness(adapter)
|
||||
const dispose = ctx.systemPrompt.context({ name: 'policy', order: 0, text: 'Mode: read-only.' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a-runtime-context-compacted-clear'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
send(agent, 'first')
|
||||
await waitForIdle(ctx, agent)
|
||||
const contextEvent = agent.session.events.find(event =>
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& event.data.source.plugin === '@deepseek-ai/dsh-system-prompt')
|
||||
if (contextEvent?.type !== 'user/message') throw new Error('first turn did not materialize runtime context')
|
||||
agent.session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'summary retaining old mode: read-only' }],
|
||||
source: { kind: 'plugin', plugin: 'test-compaction' },
|
||||
}), {
|
||||
surfaceOp: { op: 'replace', start: contextEvent.seq, end: contextEvent.seq },
|
||||
sourceEventSeqs: [contextEvent.seq],
|
||||
})
|
||||
dispose()
|
||||
|
||||
send(agent, 'after compaction')
|
||||
await waitForIdle(ctx, agent)
|
||||
const clearing = adapter.requests[1]?.messages.find(message =>
|
||||
message.source.kind === 'plugin'
|
||||
&& message.source.plugin === '@deepseek-ai/dsh-system-prompt')
|
||||
expect(clearing?.content).toEqual([{
|
||||
type: 'text',
|
||||
text: 'Current runtime context: none. Earlier runtime-context snapshots no longer apply.',
|
||||
}])
|
||||
})
|
||||
|
||||
it('does not clear runtime context after an unrelated replacement', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(SessionId('a-runtime-context-unrelated-compaction'), { provider: 'mock', model: 'mock' })
|
||||
const original = agent.session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'old context' }],
|
||||
source: { kind: 'plugin', plugin: 'test-context' },
|
||||
}), { surfaceOp: 'append' })
|
||||
agent.session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'compacted summary' }],
|
||||
source: { kind: 'plugin', plugin: 'test-compaction' },
|
||||
}), {
|
||||
surfaceOp: { op: 'replace', start: original.seq, end: original.seq },
|
||||
sourceEventSeqs: [original.seq],
|
||||
})
|
||||
|
||||
send(agent, 'after compaction')
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(adapter.requests[0]?.messages.some(message =>
|
||||
message.source.kind === 'plugin'
|
||||
&& message.source.plugin === '@deepseek-ai/dsh-system-prompt')).toBe(false)
|
||||
})
|
||||
|
||||
it('replaces a malformed retained runtime-context message with the current complete snapshot', async () => {
|
||||
const adapter = new MockAdapter([textResponse('ok')])
|
||||
const ctx = await harness(adapter)
|
||||
ctx.systemPrompt.context({ name: 'policy', order: 0, text: 'Mode: read-only.' })
|
||||
const agent = ctx.agentLoop.create(SessionId('a-runtime-context-malformed'), { provider: 'mock', model: 'mock' })
|
||||
agent.session.append('user/message', createUserMessage({
|
||||
content: [{ type: 'text', text: 'broken' }, { type: 'text', text: 'snapshot' }],
|
||||
source: { kind: 'plugin', plugin: '@deepseek-ai/dsh-system-prompt' },
|
||||
}), { surfaceOp: 'append' })
|
||||
|
||||
send(agent, 'repair context')
|
||||
await waitForIdle(ctx, agent)
|
||||
const runtimeContexts = agent.session.events.flatMap(event =>
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& event.data.source.plugin === '@deepseek-ai/dsh-system-prompt'
|
||||
? [event]
|
||||
: [])
|
||||
expect(runtimeContexts).toHaveLength(2)
|
||||
expect(runtimeContexts[1]?.data.content).toEqual([{
|
||||
type: 'text',
|
||||
text: 'Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nMode: read-only.',
|
||||
}])
|
||||
})
|
||||
|
||||
it('records raw chunks for replay as assistant/chunk session events', async () => {
|
||||
const adapter = new MockAdapter([textResponse('abc')])
|
||||
const ctx = await harness(adapter)
|
||||
|
||||
Reference in New Issue
Block a user