Merge remote-tracking branch 'origin/master' into codex/session-title
# Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl # examples/headless-agent/tests/headless.snapshot.ts # packages/examples/README.md # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/package.json # packages/ui/README.md # packages/ui/acp/README.md
This commit is contained in:
Tianyi Cui
@@ -18,8 +18,9 @@
|
||||
|
||||
import { cp, mkdtemp, readFile, readdir, rm } from 'node:fs/promises'
|
||||
import { existsSync } from 'node:fs'
|
||||
import { createHash } from 'node:crypto'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join, delimiter } from 'node:path'
|
||||
import { basename, dirname, join, delimiter } from 'node:path'
|
||||
import {
|
||||
ClientSideConnection,
|
||||
PROTOCOL_VERSION,
|
||||
@@ -41,12 +42,15 @@ export type { AgentUnderTest } from './launcher.ts'
|
||||
* the client observes the selected update (`agent_message_chunk` by default),
|
||||
* then cancels and awaits completion. A named `waitForToolCallUpdate` keeps the
|
||||
* step open for a terminal tool update that may follow the prompt response.
|
||||
* `promptAndWaitForAgentMessage` arms an exact text-chunk waiter before sending
|
||||
* the prompt, then keeps the application live until that later update arrives.
|
||||
*/
|
||||
export type InputStep =
|
||||
| { op: 'initialize'; terminalOutput?: boolean }
|
||||
| { op: 'newSession' }
|
||||
| { op: 'newSessionExpectError'; additionalDirectories?: string[] }
|
||||
| { op: 'prompt'; text: string }
|
||||
| { op: 'promptAndWaitForAgentMessage'; text: string; waitForText: string }
|
||||
| { op: 'promptExpectError'; text: string }
|
||||
| {
|
||||
op: 'promptAndCancel'
|
||||
@@ -149,6 +153,13 @@ export interface RunOptions {
|
||||
configPath?: string
|
||||
}
|
||||
|
||||
/** Derive one stable, fixed-length spill root owned by this scenario. */
|
||||
function scenarioSpillRoot(fixtureFile: string): string {
|
||||
const scenario = basename(dirname(fixtureFile))
|
||||
const key = createHash('sha256').update(scenario).digest('hex').slice(0, 9)
|
||||
return `/tmp/dsh-acp-snap-${key}`
|
||||
}
|
||||
|
||||
/**
|
||||
* Run a scenario end-to-end against a freshly-spawned subprocess. Owns the
|
||||
* child and its temp dirs; always tears them down. Returns the captured stdout
|
||||
@@ -163,7 +174,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise
|
||||
const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-snap-sessions-'))
|
||||
// Fixed path length: spill-policy budgets the preview against the REAL path
|
||||
// before stdout normalization, so tmpdir() length differences churn expected outputs.
|
||||
const spillRoot = '/tmp/dsh-acp-snapshot-spill'
|
||||
// Scenario ownership also matters: replay runs concurrently, and one teardown
|
||||
// must never delete another scenario's in-flight full-output recovery file.
|
||||
const spillRoot = scenarioSpillRoot(opts.fixtureFile)
|
||||
// Everything past the temp-dir creation is followed by failure-safe cleanup,
|
||||
// so a failure in workspace seeding, spawn, or any step never leaks resources.
|
||||
let launched: LaunchedAcpTestAgent | undefined
|
||||
@@ -331,6 +344,15 @@ async function runStep(
|
||||
await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
|
||||
return
|
||||
}
|
||||
case 'promptAndWaitForAgentMessage': {
|
||||
const sessionId = getSessionId()
|
||||
if (sessionId === undefined) throw new Error('snapshot-harness: promptAndWaitForAgentMessage before newSession')
|
||||
const updateDone = waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk'
|
||||
&& update.content.type === 'text' && update.content.text === step.waitForText)
|
||||
await client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] })
|
||||
await updateDone
|
||||
return
|
||||
}
|
||||
case 'promptExpectError': {
|
||||
const sessionId = getSessionId()
|
||||
if (sessionId === undefined) throw new Error('snapshot-harness: promptExpectError before newSession')
|
||||
|
||||
@@ -21,7 +21,7 @@ const LOCAL_SPILL_PATH_RE = new RegExp(
|
||||
'g',
|
||||
)
|
||||
const SNAPSHOT_SPILL_PATH_RE = new RegExp(
|
||||
String.raw`/tmp/dsh-acp-snapshot-spill/session-[0-9a-f]{12}/[0-9a-f]{12}-([A-Za-z0-9._~-]+?)`
|
||||
String.raw`/tmp/(?:dsh-acp-snap-[0-9a-f]{9}|dsh-acp-snapshot-spill)/session-[0-9a-f]{12}/[0-9a-f]{12}-([A-Za-z0-9._~-]+?)`
|
||||
+ String.raw`(?=\. Use read with offset/limit|[\s)]|$)`,
|
||||
'g',
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user