mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge remote-tracking branch 'origin/master' into mergebot/pr711
# Conflicts: # apps/cli/README.i18n.yaml # apps/cli/README.md # apps/cli/README.zh.md # apps/cli/cordis.yml # apps/cli/package.json # docs/config-catalog.md # packages/client/runtime/README.i18n.yaml # packages/client/runtime/src/client/contract/sessions.ts # packages/client/test-runtime/src/sessions.ts # packages/client/ui-workspace/README.i18n.yaml # packages/client/ui-workspace/README.md # packages/client/ui-workspace/README.zh.md # packages/client/ui-workspace/src/client/WorkspaceBrowser.tsx # packages/client/ui-workspace/src/client/tree.ts # packages/client/ui-workspace/tests/apply.spec.ts # packages/client/ui-workspace/tests/tree.spec.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/tests/client-handler.spec.ts # packages/host/apiproxy/tests/rpc-schemas.spec.ts # pnpm-lock.yaml
This commit is contained in:
imccyu
@@ -24,17 +24,22 @@ function exitCode(argv: string[]): number {
|
||||
afterEach(() => { vi.restoreAllMocks() })
|
||||
|
||||
describe('parseDshArgs', () => {
|
||||
it('routes each mode by its shape: default TUI, -p headless, web subcommand', () => {
|
||||
it('routes each mode by its shape: default TUI, -p headless, meta and web subcommands', () => {
|
||||
expect(parse([])).toEqual({ mode: 'tui' })
|
||||
expect(parse(['--config', 'custom.yml'])).toEqual({ mode: 'tui', config: 'custom.yml' })
|
||||
expect(parse(['--config-replace', 'tree.yml'])).toEqual({ mode: 'tui', configReplace: 'tree.yml' })
|
||||
expect(parse(['--resume', 'sess', '--config', 'app.yml'])).toEqual({ mode: 'tui', config: 'app.yml', resume: 'sess' })
|
||||
expect(parse(['-p', 'do the thing'])).toEqual({ mode: 'headless', prompt: 'do the thing' })
|
||||
// Bare `web` carries no host/port: the shipped cordis.yml owns the default.
|
||||
expect(parse(['meta'])).toEqual({ mode: 'meta' })
|
||||
// Bare `web` carries no host/port: the shipped Web overlay owns the default.
|
||||
expect(parse(['web'])).toEqual({ mode: 'web', dev: false })
|
||||
expect(parse(['web', '--config', 'web.yml'])).toEqual({ mode: 'web', dev: false, config: 'web.yml' })
|
||||
// Host/port are unvalidated pass-throughs (the webserver schema gates them
|
||||
// at boot); the adapter only coerces the port string to a number.
|
||||
expect(parse(['web', '--host', '0.0.0.0', '--port', '8080', '--dev', '--workspace-root', '/w']))
|
||||
.toEqual({ mode: 'web', host: '0.0.0.0', port: 8080, dev: true, workspaceRoot: '/w' })
|
||||
// Guided fresh-session entries carry nothing: bare mode discriminant only.
|
||||
expect(parse(['upgrade'])).toEqual({ mode: 'upgrade' })
|
||||
// --trusted-host is variadic and repeatable; authorities pass through unvalidated.
|
||||
expect(parse(['web', '--trusted-host', 'harness.internal:3080', 'lab.internal', '--trusted-host', '10.0.0.9']))
|
||||
.toEqual({ mode: 'web', dev: false, trustedHosts: ['harness.internal:3080', 'lab.internal', '10.0.0.9'] })
|
||||
@@ -47,6 +52,8 @@ describe('parseDshArgs', () => {
|
||||
expect(exitCode(['--resume='])).toBe(1)
|
||||
expect(exitCode(['-p', ''])).toBe(1)
|
||||
expect(exitCode(['-p', 'x', '--config', 'c.yml'])).toBe(1)
|
||||
expect(exitCode(['-p', 'x', '--config-replace', 'tree.yml'])).toBe(1)
|
||||
expect(exitCode(['--config', 'c.yml', '--config-replace', 'tree.yml'])).toBe(1)
|
||||
expect(exitCode(['-p', 'x', '--resume', 's'])).toBe(1)
|
||||
expect(exitCode(['--bogus'])).toBe(1)
|
||||
expect(exitCode(['bogus-positional'])).toBe(1)
|
||||
@@ -55,6 +62,20 @@ describe('parseDshArgs', () => {
|
||||
expect(exitCode(['web', '-p', 'task'])).toBe(1)
|
||||
expect(exitCode(['web', '--resume', 's'])).toBe(1)
|
||||
expect(exitCode(['--config', 'c.yml', 'web'])).toBe(1)
|
||||
expect(exitCode(['--config-replace', 'tree.yml', 'web'])).toBe(1)
|
||||
// Same rule for each subcommand that shares no option with the default
|
||||
// surface, so a leaked flag is a typo, not something to ignore.
|
||||
// `meta` fixes its own config tree and always starts fresh, so every
|
||||
// default-surface option is rejected.
|
||||
expect(exitCode(['meta', '--resume', 's'])).toBe(1)
|
||||
expect(exitCode(['meta', '--config', 'c.yml'])).toBe(1)
|
||||
expect(exitCode(['meta', '--config-replace', 'tree.yml'])).toBe(1)
|
||||
expect(exitCode(['meta', '-p', 'task'])).toBe(1)
|
||||
// `upgrade` takes no options: any leaked default-surface flag is a
|
||||
// mistyped invocation, not a silently-dropped input.
|
||||
expect(exitCode(['upgrade', '--resume', 's'])).toBe(1)
|
||||
expect(exitCode(['upgrade', '--config', 'c.yml'])).toBe(1)
|
||||
expect(exitCode(['-p', 'task', 'upgrade'])).toBe(1)
|
||||
})
|
||||
|
||||
it('exits 0 for --help (disclosing web) and --version', () => {
|
||||
|
||||
@@ -16,7 +16,7 @@ import { describe, expect, it } from 'vitest'
|
||||
* node_modules, so no external consumer is assembled; missing-config fail-loud
|
||||
* and full-boot coverage for the shared dsh-app-boot glue live in cli-demo's
|
||||
* built-bin suite, and interactive TTY behavior is PTY-covered by
|
||||
* examples/tui-agent. Skips before the bin is built.
|
||||
* apps/cli/tests. Skips before the bin is built.
|
||||
*/
|
||||
|
||||
const repoRoot = fileURLToPath(new URL('../../../', import.meta.url))
|
||||
|
||||
171
apps/cli/tests/fixtures/tui-scripted-llm.ts
vendored
Normal file
171
apps/cli/tests/fixtures/tui-scripted-llm.ts
vendored
Normal file
@@ -0,0 +1,171 @@
|
||||
import type { Context } from 'cordis'
|
||||
import type {
|
||||
GenerateOptions,
|
||||
LlmModelInfo,
|
||||
LlmResolvedModelInfo,
|
||||
StreamChunk,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import { CallId, LlmAdapter, ReasoningEffortId } from '@deepseek-ai/dsh-llm'
|
||||
|
||||
const CONTROL_PROBE = '\u001b]2;MODEL_CONTROLLED\u0007\u001b[999CMODEL_CURSOR\u009b31mMODEL_C1'
|
||||
const INITIAL_TEXT = `I need one decision before I continue. ${CONTROL_PROBE}`
|
||||
const FINAL_TEXT = 'Decision received. Scripted TUI run complete.'
|
||||
const DEFAULT_MODE_PROBE = 'Confirm the scripted run left plan mode.'
|
||||
const DEFAULT_MODE_TEXT = 'Default mode confirmed.'
|
||||
// The `skill` scenario types `/skill:scripted-skill`; the manual-invocation front
|
||||
// door delivers the loaded skill as a user turn wrapped in `<skill name="…">`. The
|
||||
// body marker below lives in the fixture skill, so echoing it back proves the whole
|
||||
// block (name attribute plus body) reached the model, not just the command text.
|
||||
const SKILL_BLOCK_OPEN = '<skill name="scripted-skill">'
|
||||
const SKILL_BODY_MARKER = 'SCRIPTED SKILL BODY MARKER'
|
||||
const SKILL_RECEIVED_TEXT = 'Scripted skill body received.'
|
||||
const TITLE_TEXT = 'scripted session title'
|
||||
// The failing-bash scenario proves the terminal card reports a non-zero exit
|
||||
// exactly once: the model-facing result carries the `[exit code: N]` marker, and
|
||||
// the card turns it into its own `[exit N]` pill instead of showing both.
|
||||
const BASH_FAILURE_PROBE = 'Run the failing scripted command.'
|
||||
const BASH_FAILURE_COMMAND = 'printf "SCRIPTED_BASH_FAILED\\n"; exit 3'
|
||||
const BASH_FAILURE_TEXT = 'Scripted bash failure observed.'
|
||||
const BASH_FAILURE_CALL_ID = CallId('call-bash-failure')
|
||||
|
||||
function textChunks(text: string): StreamChunk[] {
|
||||
return [
|
||||
{ type: 'block-start', index: 0, blockType: 'text' },
|
||||
...Array.from(text, (char): StreamChunk => ({ type: 'text-delta', index: 0, text: char })),
|
||||
{ type: 'block-end', index: 0, block: { type: 'text', text } },
|
||||
{ type: 'usage', usage: { inputTokens: 20, outputTokens: text.length } },
|
||||
{ type: 'finish', reason: { kind: 'stop' } },
|
||||
]
|
||||
}
|
||||
|
||||
/** Keyless adapter for the real-PTY TUI tests: the two-step conversation and the `/skill:` round-trip. */
|
||||
class ScriptedTuiAdapter extends LlmAdapter {
|
||||
override listModels(provider: string): Promise<readonly LlmModelInfo[]> {
|
||||
return Promise.resolve([
|
||||
{ provider, id: 'tui-scripted-model', name: 'Scripted Base' },
|
||||
{ provider, id: 'tui-scripted-model-pro', name: 'Scripted Pro' },
|
||||
])
|
||||
}
|
||||
|
||||
override resolveModel(
|
||||
provider: string,
|
||||
model: string,
|
||||
): Promise<LlmResolvedModelInfo> {
|
||||
return Promise.resolve({
|
||||
provider,
|
||||
id: model,
|
||||
name: model === 'tui-scripted-model-pro' ? 'Scripted Pro' : 'Scripted Base',
|
||||
context: { contextWindow: 128_000 },
|
||||
...model !== 'tui-scripted-model-pro'
|
||||
? {}
|
||||
: {
|
||||
reasoning: {
|
||||
efforts: [
|
||||
{ id: ReasoningEffortId('off'), name: 'Off' },
|
||||
{ id: ReasoningEffortId('high'), name: 'High' },
|
||||
{ id: ReasoningEffortId('max'), name: 'Max' },
|
||||
],
|
||||
defaultEffort: ReasoningEffortId('high'),
|
||||
},
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
override async * stream(options: GenerateOptions): AsyncIterable<StreamChunk> {
|
||||
// The session-title provider's auxiliary request carries no tool schemas,
|
||||
// unlike every agent turn; answer it with a fixed title so the PTY test can
|
||||
// assert the logged title reaches the terminal window title.
|
||||
if ((options.tools?.length ?? 0) === 0) {
|
||||
for (const chunk of textChunks(TITLE_TEXT)) yield chunk
|
||||
return
|
||||
}
|
||||
if (
|
||||
options.model !== 'tui-scripted-model-pro'
|
||||
|| !options.system?.includes('tui-scripted-model-pro')
|
||||
|| options.reasoningEffort !== ReasoningEffortId('max')
|
||||
) {
|
||||
throw new Error('the scripted TUI request did not apply the selected model and reasoning effort')
|
||||
}
|
||||
const lastMessage = options.messages.at(-1)
|
||||
// The loop appends plugin-sourced context (the plan-mode notice, the
|
||||
// tool-skill catalog) AFTER the admitted prompt, so the scripted trigger
|
||||
// may sit one or more user messages back: scan the whole trailing run of
|
||||
// user-role messages since the last assistant message.
|
||||
const trailingUserTexts: string[] = []
|
||||
for (let index = options.messages.length - 1; index >= 0; index--) {
|
||||
const message = options.messages[index]
|
||||
if (message?.role !== 'user') break
|
||||
for (const block of message.content) {
|
||||
if (block.type === 'text') trailingUserTexts.push(block.text)
|
||||
}
|
||||
}
|
||||
const lastText = trailingUserTexts.join('\n')
|
||||
if (lastText.includes(DEFAULT_MODE_PROBE)) {
|
||||
if (options.system?.includes('Stay in plan mode for this scripted TUI test.')) {
|
||||
throw new Error('the scripted TUI request retained plan guidance after /plan off')
|
||||
}
|
||||
for (const chunk of textChunks(DEFAULT_MODE_TEXT)) yield chunk
|
||||
return
|
||||
}
|
||||
if (lastText.includes(SKILL_BLOCK_OPEN)) {
|
||||
const ack = lastText.includes(SKILL_BODY_MARKER)
|
||||
? SKILL_RECEIVED_TEXT
|
||||
: 'Scripted skill block arrived without its body.'
|
||||
for (const chunk of textChunks(ack)) yield chunk
|
||||
return
|
||||
}
|
||||
|
||||
const blocks = lastMessage?.content ?? []
|
||||
if (blocks.some(block => block.type === 'tool-result')) {
|
||||
const answered = blocks.some(block => block.type === 'tool-result' && block.toolCallId === BASH_FAILURE_CALL_ID)
|
||||
for (const chunk of textChunks(answered ? BASH_FAILURE_TEXT : FINAL_TEXT)) yield chunk
|
||||
return
|
||||
}
|
||||
if (lastText.includes(BASH_FAILURE_PROBE)) {
|
||||
const bashArgs = JSON.stringify({ command: BASH_FAILURE_COMMAND, description: 'Run the failing scripted command' })
|
||||
yield { type: 'block-start', index: 0, blockType: 'tool-call' }
|
||||
yield { type: 'tool-call-delta', index: 0, id: BASH_FAILURE_CALL_ID, name: 'bash', argumentsDelta: bashArgs }
|
||||
yield {
|
||||
type: 'block-end',
|
||||
index: 0,
|
||||
block: { type: 'tool-call', id: BASH_FAILURE_CALL_ID, name: 'bash', arguments: bashArgs },
|
||||
}
|
||||
yield { type: 'usage', usage: { inputTokens: 20, outputTokens: 10 } }
|
||||
yield { type: 'finish', reason: { kind: 'tool-calls' } }
|
||||
return
|
||||
}
|
||||
|
||||
const args = JSON.stringify({
|
||||
questions: [{
|
||||
id: 'mode',
|
||||
header: 'Execution mode',
|
||||
question: 'How should the scripted run proceed?',
|
||||
options: [
|
||||
{ label: 'Safe', description: 'Use the guarded path.' },
|
||||
{ label: 'Fast', description: 'Use the shorter path.' },
|
||||
],
|
||||
}],
|
||||
})
|
||||
const callId = CallId('call-ask-mode')
|
||||
yield { type: 'block-start', index: 0, blockType: 'text' }
|
||||
for (const char of INITIAL_TEXT) yield { type: 'text-delta', index: 0, text: char }
|
||||
yield { type: 'block-end', index: 0, block: { type: 'text', text: INITIAL_TEXT } }
|
||||
yield { type: 'block-start', index: 1, blockType: 'tool-call' }
|
||||
yield { type: 'tool-call-delta', index: 1, id: callId, name: 'ask_user_question', argumentsDelta: args }
|
||||
yield {
|
||||
type: 'block-end',
|
||||
index: 1,
|
||||
block: { type: 'tool-call', id: callId, name: 'ask_user_question', arguments: args },
|
||||
}
|
||||
yield { type: 'usage', usage: { inputTokens: 20, outputTokens: 10 } }
|
||||
yield { type: 'finish', reason: { kind: 'tool-calls' } }
|
||||
}
|
||||
}
|
||||
|
||||
export const name = 'tui-scripted-llm'
|
||||
export const inject = ['llm']
|
||||
|
||||
/** Register the network-free adapter used by the PTY fixture. */
|
||||
export function apply(ctx: Context): void {
|
||||
ctx.llm.registerAdapter(['tui-scripted'], new ScriptedTuiAdapter())
|
||||
}
|
||||
71
apps/cli/tests/fixtures/tui-scripted.cordis.yml
vendored
Normal file
71
apps/cli/tests/fixtures/tui-scripted.cordis.yml
vendored
Normal file
@@ -0,0 +1,71 @@
|
||||
# Overlay for the keyless conversational PTY test: the shipped composition with
|
||||
# only the model replaced, so the terminal interaction is deterministic and
|
||||
# network-free while the agent/TUI/user-question stack stays the production one.
|
||||
#
|
||||
# Passed as `--config`, so the launcher includes `base.cordis.yml`, applies
|
||||
# `tui.cordis.yml`, then this file — all sibling patch lists at one include
|
||||
# level. A patch replaces the targeted row's whole `config`, so each row below
|
||||
# restates every key it owns.
|
||||
|
||||
# The scripted adapter replaces the DeepSeek one: no key, no network. A patch's
|
||||
# `name` is an assertion rather than a replacement, so the base row is disabled
|
||||
# and the adapter inserted. Relative specifiers resolve against the INCLUDED
|
||||
# file's directory (apps/cli/config), because the include moves baseUrl there.
|
||||
- id: llm-deepseek
|
||||
disabled: true
|
||||
|
||||
- insert:
|
||||
- id: scripted-llm
|
||||
name: '../tests/fixtures/tui-scripted-llm.ts'
|
||||
|
||||
- id: agent-loop
|
||||
config:
|
||||
agents:
|
||||
- id: main
|
||||
provider: tui-scripted
|
||||
model: tui-scripted-model
|
||||
# `cwd` scopes the session to this workspace, which is what `/resume`
|
||||
# filters on; dropping it would hide the seeded session.
|
||||
cwd: !!js process.cwd()
|
||||
|
||||
- id: system-prompt
|
||||
config:
|
||||
persona: 'Scripted model {{model}}.'
|
||||
|
||||
# The smoke's log inspection reads plain `.jsonl` under the workspace, so this
|
||||
# fixture pins a project-local root instead of the launcher's shared store, and
|
||||
# keeps the artifacts uncompressed like the other snapshot-facing configs.
|
||||
- id: session-persistence-jsonl
|
||||
config:
|
||||
root: './.sessions'
|
||||
compression: none
|
||||
|
||||
# The derived index must sit under the same root as the logs it indexes; this
|
||||
# fixture pins both to the workspace instead of the launcher's shared store.
|
||||
- id: session-query-sqlite
|
||||
config:
|
||||
path: './.sessions/session-query.db'
|
||||
|
||||
- id: plan-mode
|
||||
config:
|
||||
section: 'Stay in plan mode for this scripted TUI test.'
|
||||
|
||||
# The scripted adapter answers the tool-less title request with a fixed string,
|
||||
# so the PTY test can assert the logged title reaches the terminal window title.
|
||||
- id: session-title-llm
|
||||
config:
|
||||
targetWords: 5
|
||||
targetCjkCharacters: 10
|
||||
maxInputBytes: 4096
|
||||
maxOutputTokens: 64
|
||||
timeoutMs: 10000
|
||||
|
||||
- id: tui
|
||||
config:
|
||||
sessionId: !!js configuredAgentIdentities?.main?.id ?? 'main'
|
||||
welcome: 'scripted TUI ready.'
|
||||
showReasoning: true
|
||||
|
||||
# HMR watches the repository; a PTY subprocess test must not start a watcher.
|
||||
- id: hmr
|
||||
disabled: true
|
||||
@@ -3,7 +3,8 @@
|
||||
*
|
||||
* Only the dedicated Node compatibility gate opts this test in after building
|
||||
* both artifacts; ordinary Vitest inventory deterministically skips it.
|
||||
* The child runs built artifacts under plain Node with the real cordis.yml.
|
||||
* The child runs built artifacts under plain Node with the real shipped
|
||||
* config (base.cordis.yml + the web.cordis.yml overlay).
|
||||
* Its URL line follows AppCLIEntry's settled boot; SIGTERM then exercises the
|
||||
* shipped quiescent disposer.
|
||||
*/
|
||||
@@ -20,7 +21,8 @@ import { describe, expect, it } from 'vitest'
|
||||
const repoRoot = fileURLToPath(new URL('../../../', import.meta.url))
|
||||
const builtBin = join(repoRoot, 'apps/cli/lib/bin.js')
|
||||
const webDist = join(repoRoot, 'apps/web/dist/index.html')
|
||||
const configPath = join(repoRoot, 'apps/cli/cordis.yml')
|
||||
// The web overlay owns the session-query-sqlite lazy-open patch row.
|
||||
const configPath = join(repoRoot, 'apps/cli/config/web.cordis.yml')
|
||||
const requireBuiltArtifacts = process.env.DSH_REQUIRE_BUILT_CLI_SMOKE === '1'
|
||||
|
||||
interface ConfigRow {
|
||||
|
||||
236
apps/cli/tests/pty-harness.ts
Normal file
236
apps/cli/tests/pty-harness.ts
Normal file
@@ -0,0 +1,236 @@
|
||||
import { mkdirSync, writeFileSync } from 'node:fs'
|
||||
import { mkdtemp, rm } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { dirname, join } from 'node:path'
|
||||
import { execa } from 'execa'
|
||||
import { resolveExampleLaunch, type ExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
|
||||
|
||||
const POSIX_PTY_DRIVER = String.raw`
|
||||
import errno, json, os, pty, select, signal, sys, time
|
||||
node, launch_args_json, launch_env_json, cwd, actions_json, expected_exit, timeout_seconds = sys.argv[1:]
|
||||
env = os.environ.copy()
|
||||
env.update(json.loads(launch_env_json))
|
||||
env.update({"COLUMNS": "100", "LINES": "30"})
|
||||
# Deterministic banner: a developer shell's COLORTERM=truecolor would switch the
|
||||
# banner to the per-letter gradient (one SGR per letter), breaking literal
|
||||
# DEEPSEEK assertions. The gradient path has its own unit and snapshot coverage.
|
||||
env.pop("COLORTERM", None)
|
||||
actions = json.loads(actions_json)
|
||||
pid, fd = pty.fork()
|
||||
if pid == 0:
|
||||
os.chdir(cwd)
|
||||
os.execvpe(node, [node, *json.loads(launch_args_json)], env)
|
||||
|
||||
output = bytearray()
|
||||
action_index = 0
|
||||
deadline = time.monotonic() + float(timeout_seconds)
|
||||
status = None
|
||||
while time.monotonic() < deadline:
|
||||
ready, _, _ = select.select([fd], [], [], 0.05)
|
||||
if ready:
|
||||
try:
|
||||
chunk = os.read(fd, 65536)
|
||||
except OSError as error:
|
||||
if error.errno != errno.EIO:
|
||||
raise
|
||||
chunk = b""
|
||||
if chunk:
|
||||
output.extend(chunk)
|
||||
while action_index < len(actions) and actions[action_index]["waitFor"].encode() in output:
|
||||
action = actions[action_index]
|
||||
if "writeFile" in action:
|
||||
target = os.path.join(cwd, action["writeFile"]["path"])
|
||||
os.makedirs(os.path.dirname(target), exist_ok=True)
|
||||
with open(target, "w", encoding="utf-8") as handle:
|
||||
handle.write(action["writeFile"]["content"])
|
||||
if "send" in action:
|
||||
os.write(fd, action["send"].encode())
|
||||
else:
|
||||
os.write(fd, action["send"].encode())
|
||||
action_index += 1
|
||||
waited, candidate = os.waitpid(pid, os.WNOHANG)
|
||||
if waited == pid:
|
||||
status = candidate
|
||||
break
|
||||
|
||||
if status is None:
|
||||
os.kill(pid, signal.SIGKILL)
|
||||
_, status = os.waitpid(pid, 0)
|
||||
sys.stdout.buffer.write(output)
|
||||
if action_index != len(actions):
|
||||
sys.stderr.write(f"completed {action_index}/{len(actions)} PTY actions before timeout\n")
|
||||
sys.exit(124)
|
||||
actual_exit = os.waitstatus_to_exitcode(status)
|
||||
if actual_exit != int(expected_exit):
|
||||
sys.stderr.write(f"expected exit {expected_exit}, got {actual_exit}\n")
|
||||
sys.exit(125)
|
||||
`
|
||||
|
||||
/** One terminal input or workspace mutation performed after its marker renders. */
|
||||
type TuiPtyAction =
|
||||
| { readonly waitFor: string; readonly send: string }
|
||||
| {
|
||||
readonly waitFor: string
|
||||
readonly writeFile: { readonly path: string; readonly content: string }
|
||||
readonly send?: string
|
||||
}
|
||||
|
||||
/** Inputs for a keyless real-Loader TUI process smoke. */
|
||||
export interface TuiPtySmokeOptions {
|
||||
readonly label: string
|
||||
readonly tempDirPrefix: string
|
||||
readonly binScript: string
|
||||
/** Config argument; ignored when {@link configArgs} is set. */
|
||||
readonly configPath?: string
|
||||
/** Full argument vector for the bin (e.g. `[]` for a bin with a built-in default config). */
|
||||
readonly configArgs?: readonly string[]
|
||||
readonly tsconfigPath: string
|
||||
readonly actions?: readonly TuiPtyAction[]
|
||||
readonly env?: Readonly<NodeJS.ProcessEnv>
|
||||
readonly expectedExitCode?: number
|
||||
readonly timeoutMs?: number
|
||||
/** Seed the isolated workspace (`cwd`, with `$DSH_HOME` at `.dsh` and the agents home at `.agents`) before launch. */
|
||||
readonly prepare?: (cwd: string) => Promise<void>
|
||||
/** Inspect the workspace after a passing run, before the temp dir is removed. */
|
||||
readonly inspect?: (cwd: string) => Promise<void>
|
||||
}
|
||||
|
||||
function definedEnv(env: NodeJS.ProcessEnv): Record<string, string> {
|
||||
return Object.fromEntries(
|
||||
Object.entries(env).filter((entry): entry is [string, string] => entry[1] !== undefined),
|
||||
)
|
||||
}
|
||||
|
||||
async function runPosixPtySmoke(
|
||||
launch: ExampleLaunch,
|
||||
cwd: string,
|
||||
options: TuiPtySmokeOptions,
|
||||
timeoutMs: number,
|
||||
): Promise<string> {
|
||||
// The driver owns the PTY deadline (`timeoutMs`); the outer execa deadline
|
||||
// only backstops a wedged python3 process itself.
|
||||
const result = await execa('python3', [
|
||||
'-c',
|
||||
POSIX_PTY_DRIVER,
|
||||
launch.command,
|
||||
JSON.stringify(launch.args),
|
||||
JSON.stringify(launch.env),
|
||||
cwd,
|
||||
JSON.stringify(options.actions ?? []),
|
||||
String(options.expectedExitCode ?? 0),
|
||||
String(timeoutMs / 1_000),
|
||||
], {
|
||||
stdin: 'ignore',
|
||||
timeout: timeoutMs + 5_000,
|
||||
killSignal: 'SIGKILL',
|
||||
reject: false,
|
||||
stripFinalNewline: false,
|
||||
})
|
||||
if (result.timedOut) {
|
||||
throw new Error(`${options.label} PTY driver did not exit. stdout:\n${result.stdout}\nstderr:\n${result.stderr}`)
|
||||
}
|
||||
if (result.failed) {
|
||||
throw new Error(`${options.label} PTY driver exited ${String(result.exitCode)}. stdout:\n${result.stdout}\nstderr:\n${result.stderr}`)
|
||||
}
|
||||
return result.stdout
|
||||
}
|
||||
|
||||
async function runWindowsPtySmoke(
|
||||
launch: ExampleLaunch,
|
||||
cwd: string,
|
||||
options: TuiPtySmokeOptions,
|
||||
timeoutMs: number,
|
||||
): Promise<string> {
|
||||
const pty = await import('node-pty')
|
||||
return await new Promise((resolve, reject) => {
|
||||
const actions = options.actions ?? []
|
||||
const expectedExitCode = options.expectedExitCode ?? 0
|
||||
let output = ''
|
||||
let actionIndex = 0
|
||||
let timedOut = false
|
||||
const terminal = pty.spawn(launch.command, launch.args, {
|
||||
name: 'xterm-256color',
|
||||
cols: 100,
|
||||
rows: 30,
|
||||
cwd,
|
||||
env: definedEnv({
|
||||
...process.env,
|
||||
...launch.env,
|
||||
// Match the POSIX driver: no COLORTERM, so the banner never takes the
|
||||
// truecolor gradient path under a developer's shell.
|
||||
COLORTERM: undefined,
|
||||
COLUMNS: '100',
|
||||
LINES: '30',
|
||||
}),
|
||||
})
|
||||
const timer = setTimeout(() => {
|
||||
timedOut = true
|
||||
terminal.kill()
|
||||
}, timeoutMs)
|
||||
terminal.onData((chunk) => {
|
||||
output += chunk
|
||||
while (actionIndex < actions.length && output.includes(actions[actionIndex]!.waitFor)) {
|
||||
const action = actions[actionIndex]!
|
||||
if ('writeFile' in action) {
|
||||
const target = join(cwd, action.writeFile.path)
|
||||
mkdirSync(dirname(target), { recursive: true })
|
||||
writeFileSync(target, action.writeFile.content)
|
||||
const input = action.send
|
||||
if (input !== undefined) terminal.write(input)
|
||||
} else {
|
||||
terminal.write(action.send)
|
||||
}
|
||||
actionIndex += 1
|
||||
}
|
||||
})
|
||||
terminal.onExit(({ exitCode, signal }) => {
|
||||
clearTimeout(timer)
|
||||
if (timedOut) {
|
||||
reject(new Error(`${options.label} PTY process did not exit before ${String(timeoutMs)}ms. output:\n${output}`))
|
||||
} else if (actionIndex !== actions.length) {
|
||||
reject(new Error(`${options.label} completed ${String(actionIndex)}/${String(actions.length)} PTY actions. output:\n${output}`))
|
||||
} else if (exitCode !== expectedExitCode) {
|
||||
reject(new Error(`${options.label} expected exit ${String(expectedExitCode)}, got ${String(exitCode)} (signal ${String(signal)}). output:\n${output}`))
|
||||
} else {
|
||||
resolve(output)
|
||||
}
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* Boot an example in a real pseudo-terminal (ConPTY on Windows), drive
|
||||
* marker-gated input, and return captured bytes after the expected process exit.
|
||||
* @param options - launch paths, environment, actions, and expected exit code.
|
||||
* @returns complete pseudo-terminal output.
|
||||
*/
|
||||
export async function runTuiPtySmoke(options: TuiPtySmokeOptions): Promise<string> {
|
||||
const cwd = await mkdtemp(join(tmpdir(), options.tempDirPrefix))
|
||||
const timeoutMs = options.timeoutMs ?? 25_000
|
||||
try {
|
||||
await options.prepare?.(cwd)
|
||||
const launch = resolveExampleLaunch({
|
||||
srcBin: options.binScript,
|
||||
// `configPath` is the dsh `--config <path>` tree override; `configArgs`
|
||||
// is the raw-args escape (e.g. `['--resume', <id>]`) for other flags.
|
||||
configArgs: options.configArgs !== undefined
|
||||
? [...options.configArgs]
|
||||
/* v8 ignore next -- every caller passes configPath or configArgs; the fallback keeps the type total */
|
||||
: options.configPath !== undefined ? ['--config', options.configPath] : [],
|
||||
tsconfigPath: options.tsconfigPath,
|
||||
env: {
|
||||
DSH_HOME: join(cwd, '.dsh'),
|
||||
DSH_AGENTS_HOME: join(cwd, '.agents'),
|
||||
...options.env,
|
||||
},
|
||||
})
|
||||
const output = process.platform === 'win32'
|
||||
? await runWindowsPtySmoke(launch, cwd, options, timeoutMs)
|
||||
: await runPosixPtySmoke(launch, cwd, options, timeoutMs)
|
||||
// Inspect the workspace before `finally` removes it (e.g. the session log).
|
||||
await options.inspect?.(cwd)
|
||||
return output
|
||||
} finally {
|
||||
await rm(cwd, { recursive: true, force: true })
|
||||
}
|
||||
}
|
||||
30
apps/cli/tests/snapshots/bash-terminal-card/session.jsonl
Normal file
30
apps/cli/tests/snapshots/bash-terminal-card/session.jsonl
Normal file
@@ -0,0 +1,30 @@
|
||||
{"type":"session","version":0,"id":"e128dda9-ed11-4868-8266-0ef90d03c3d6","createdAt":1783352050748,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":1783352050753,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783352050753,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783352050755,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783352050756,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783352051421,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":5,"time0":1783352051422,"data":{"turn":1,"step":1,"index":0,"dt":[168,28,0,1,0,0,26,30,0,0,1,0,27,1,0,0,0],"texts":["The"," user"," wants"," me"," to"," run"," a"," simple"," bash"," command"," and"," then"," reply"," with"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":23,"time":1783352051790,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":24,"time0":1783352051791,"data":{"turn":1,"step":1,"index":1,"dt":[29,0,0,0,0,28,0,0,0,29,0,0,28,1,0,29,0,0,0,32,0,0,0,0,0,74,0,0,13,0],"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","args":["","{","\"","command","\"",": ","\"","echo"," TER","MIN","AL","_OK","\"",", ","\"","description","\"",": ","\"","E","cho"," TER","MIN","AL","_OK"," to"," verify"," terminal"," access","\"","}"]}}
|
||||
{"type":"assistant/chunk","seq":55,"time":1783352052117,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."}}}}
|
||||
{"type":"assistant/chunk","seq":56,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":57,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}}}}
|
||||
{"type":"assistant/chunk","seq":58,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":59,"time":1783352052121,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":60,"time":1783352052121,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}}
|
||||
{"type":"tool/result","seq":61,"time":1783352052136,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","content":[{"type":"text","text":"TERMINAL_OK\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":62,"time":1783352052137,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":63,"time":1783352052137,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":64,"time":1783352052701,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":65,"time0":1783352052702,"data":{"turn":1,"step":2,"index":0,"dt":[78,29,29,0,0,29,0,0,0,0,0,28,1,28,1,0,0,32,0,0,0],"texts":["The"," command"," ran"," successfully"," and"," output"," \"","TER","MIN","AL","_OK","\"."," I"," should"," now"," reply"," with"," just"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":87,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":88,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
|
||||
{"type":"assistant/chunk","seq":89,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
|
||||
{"type":"assistant/chunk","seq":90,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."}}}}
|
||||
{"type":"assistant/chunk","seq":91,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":92,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}}}}
|
||||
{"type":"assistant/chunk","seq":93,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":94,"time":1783352052987,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":95,"time":1783352052987,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":96,"time":1783352052987,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,55 @@
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Use the bash tool to — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=24 bufferRow=24
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Use the bash tool to"
|
||||
style 1-20 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop. "
|
||||
6| <blank>
|
||||
7| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
8| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
9| "The user wants me to run a simple bash command and then reply with \"DONE\". "
|
||||
style 0-73 dim italic
|
||||
10| <blank>
|
||||
11| "● Tool / bash / Echo TERMINAL_OK to verify terminal access"
|
||||
style 0-57 fg=green
|
||||
12| "$ echo TERMINAL_OK "
|
||||
style 0-17 dim
|
||||
13| "TERMINAL_OK "
|
||||
style 0-10 dim
|
||||
14| "[exit 0] "
|
||||
style 0-7 dim
|
||||
15| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
16| <blank>
|
||||
17| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
18| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
19| "The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\". "
|
||||
style 0-90 dim italic
|
||||
20| "DONE "
|
||||
21| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
22| <blank>
|
||||
23| "/workspace/project deepseek-v4-flash ↑3.0k ↓115 cache 48% 3% contex"
|
||||
style 0-46 fg=bright-magenta bold
|
||||
style 49-65 dim
|
||||
style 68-88 dim
|
||||
style 91-99 dim
|
||||
24| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
25-35| <blank>
|
||||
@@ -0,0 +1,32 @@
|
||||
{"type":"session","version":0,"id":"main-session","createdAt":1785052797743,"cwd":"{{cwd}}"}
|
||||
{"type":"turn/start","seq":0,"time":1785052797817,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1785052797818,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool exactly once with the command `seq 1 200 | awk '{printf \"line %04d: the quick brown fox jumps over the lazy dog\\n\", $1}'`, then return ONLY the number of lines in its output. Reply with just that number and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785052797825,"data":{"title":"Using ONE run_code program: call","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785052797826,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785052797827,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785052798220,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785052798221,"data":{"turn":1,"step":1,"index":0,"dt":[170,30,0,0,0,30,1,0,0,28,0,0,0,29,30,0,30,0,30,0,0,0,30,0,0,0,0,0,30,30,1],"texts":["The"," user"," wants"," me"," to"," write"," a"," single"," run","_code"," program"," that"," calls"," bash"," exactly"," once"," with"," a"," specific"," command",","," then"," returns"," only"," the"," number"," of"," lines"," in"," its"," output","."]}}
|
||||
{"type":"assistant/chunk","seq":38,"time":1785052798781,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":39,"time0":1785052798781,"data":{"turn":1,"step":1,"index":1,"dt":[0,0,28,0,0,0,30,29,1,0,30,30,1,0,30,0,0,28,1,0,0,30,0,0,0,0,1,28,1,0,0,0,0,58,1,0,15,0,0,0,0,39,0,1,0,28,0,0,29,0,0,0,0,0,30,0,0,0,0,1,29,1,0,0,0,29,0,0,40,0,0,20,1,29,0,30,0,30,0,0,31,0,0,30,0,0,30,0,0,30,0,1,0,29,0,0,30,31,0,0,0,0,0,30,0,0,0,1,0,28,0,0],"id":"call_00_R6g9Uzx4h0jeUv9g3fno7490","name":"run_code","args":["","{","\"","description","\"",": ","\"","Count"," lines"," in"," seq","/","awk"," output","\"",", ","\"","code","\"",": ","\"","const"," result"," ="," await"," tools",".b","ash","({\\n"," "," command",":"," \\\"","seq"," ","1"," ","200"," |"," awk"," '{","printf"," \\\\\\\"","line"," %","04","d",":"," the"," quick"," brown"," fox"," jumps"," over"," the"," lazy"," dog","\\\\\\\\","n","\\\\\\\","," $","1","}'","\\\",\\n"," "," description",":"," \\\"","Generate"," ","200"," lines"," of"," text","\\\"\\n","});\\n\\n","//"," Count"," lines"," in"," stdout","\\n","const"," lines"," ="," result",".k","ind"," ==="," \\\"","fore","ground","\\\""," ?"," result",".stdout",".text",".trim","().","split","(\\\"\\\\","n","\\\").","length"," :"," ","0",";\\n","return"," lines",";","\"","}"]}}
|
||||
{"type":"assistant/chunk","seq":152,"time":1785052799793,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to write a single run_code program that calls bash exactly once with a specific command, then returns only the number of lines in its output."}}}}
|
||||
{"type":"assistant/chunk","seq":153,"time":1785052799793,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_R6g9Uzx4h0jeUv9g3fno7490","name":"run_code","arguments":"{\"description\": \"Count lines in seq/awk output\", \"code\": \"const result = await tools.bash({\\n command: \\\"seq 1 200 | awk '{printf \\\\\\\"line %04d: the quick brown fox jumps over the lazy dog\\\\\\\\n\\\\\\\", $1}'\\\",\\n description: \\\"Generate 200 lines of text\\\"\\n});\\n\\n// Count lines in stdout\\nconst lines = result.kind === \\\"foreground\\\" ? result.stdout.text.trim().split(\\\"\\\\n\\\").length : 0;\\nreturn lines;\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":154,"time":1785052799794,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":90,"outputTokens":186,"cacheReadTokens":3968,"reasoningTokens":32}}}}
|
||||
{"type":"assistant/chunk","seq":155,"time":1785052799794,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":156,"time":1785052799798,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to write a single run_code program that calls bash exactly once with a specific command, then returns only the number of lines in its output."},{"type":"tool-call","id":"call_00_R6g9Uzx4h0jeUv9g3fno7490","name":"run_code","arguments":"{\"description\": \"Count lines in seq/awk output\", \"code\": \"const result = await tools.bash({\\n command: \\\"seq 1 200 | awk '{printf \\\\\\\"line %04d: the quick brown fox jumps over the lazy dog\\\\\\\\n\\\\\\\", $1}'\\\",\\n description: \\\"Generate 200 lines of text\\\"\\n});\\n\\n// Count lines in stdout\\nconst lines = result.kind === \\\"foreground\\\" ? result.stdout.text.trim().split(\\\"\\\\n\\\").length : 0;\\nreturn lines;\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":90,"outputTokens":186,"cacheReadTokens":3968,"reasoningTokens":32}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":157,"time":1785052799799,"data":{"turn":1,"step":1,"callId":"call_00_R6g9Uzx4h0jeUv9g3fno7490","name":"run_code","arguments":"{\"description\": \"Count lines in seq/awk output\", \"code\": \"const result = await tools.bash({\\n command: \\\"seq 1 200 | awk '{printf \\\\\\\"line %04d: the quick brown fox jumps over the lazy dog\\\\\\\\n\\\\\\\", $1}'\\\",\\n description: \\\"Generate 200 lines of text\\\"\\n});\\n\\n// Count lines in stdout\\nconst lines = result.kind === \\\"foreground\\\" ? result.stdout.text.trim().split(\\\"\\\\n\\\").length : 0;\\nreturn lines;\"}"}}
|
||||
{"type":"tool/code-dispatch-start","seq":158,"time":1785052799893,"data":{"parentCallId":"call_00_R6g9Uzx4h0jeUv9g3fno7490","subCallId":"call_00_R6g9Uzx4h0jeUv9g3fno7490:code:1","name":"bash","arguments":{"command":"seq 1 200 | awk '{printf \"line %04d: the quick brown fox jumps over the lazy dog\\n\", $1}'","description":"Generate 200 lines of text"}}}
|
||||
{"type":"tool/code-dispatch","seq":159,"time":1785052799923,"data":{"parentCallId":"call_00_R6g9Uzx4h0jeUv9g3fno7490","subCallId":"call_00_R6g9Uzx4h0jeUv9g3fno7490:code:1","name":"bash","arguments":{"command":"seq 1 200 | awk '{printf \"line %04d: the quick brown fox jumps over the lazy dog\\n\", $1}'","description":"Generate 200 lines of text"},"isError":false,"content":[{"type":"text","text":"line 0001: the quick brown fox jumps over the lazy dog\nline 0002: the quick brown fox jumps over the lazy dog\nline 0003: the quick brown fox jumps over the lazy dog\nline 0004: the quick s over the lazy dog\nline 0198: the quick brown fox jumps over the lazy dog\nline 0199: the quick brown fox jumps over the lazy dog\nline 0200: the quick brown fox jumps over the lazy dog\n\n\n(Omitted 10629 bytes. Full formatted result stored at: {{cwd}}/.spill/session-2d2b9e84a250/825a63550249-bash.txt. Use read with offset/limit, or grep this path to search within it.)"}]}}
|
||||
{"type":"tool/result","seq":160,"time":1785052799925,"data":{"turn":1,"step":1,"callId":"call_00_R6g9Uzx4h0jeUv9g3fno7490","content":[{"type":"text","text":"200"}],"isError":false},"sourceEventSeqs":[157],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":161,"time":1785052799926,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":162,"time":1785052799928,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":163,"time":1785052800414,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":164,"time0":1785052800415,"data":{"turn":1,"step":2,"index":0,"dt":[157,32,0,0,0,1,30,1,30,0,0,0,33,1,0,0,0,31,0],"texts":["The"," result"," is"," ","200"," lines","."," The"," user"," wants"," me"," to"," reply"," with"," just"," that"," number"," and"," stop","."]}}
|
||||
{"type":"assistant/chunk","seq":184,"time":1785052800731,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":185,"time":1785052800731,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"200"}}}
|
||||
{"type":"assistant/chunk","seq":186,"time":1785052800731,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The result is 200 lines. The user wants me to reply with just that number and stop."}}}}
|
||||
{"type":"assistant/chunk","seq":187,"time":1785052800731,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"200"}}}}
|
||||
{"type":"assistant/chunk","seq":188,"time":1785052800732,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":33,"outputTokens":22,"cacheReadTokens":4224,"reasoningTokens":20}}}}
|
||||
{"type":"assistant/chunk","seq":189,"time":1785052800732,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":190,"time":1785052800733,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The result is 200 lines. The user wants me to reply with just that number and stop."},{"type":"text","text":"200"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":33,"outputTokens":22,"cacheReadTokens":4224,"reasoningTokens":20}},"sourceEventSeqs":[163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":191,"time":1785052800733,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":192,"time":1785052800733,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,59 @@
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Using ONE run_code program: call — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=26 bufferRow=26
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Using ONE run_code program: call"
|
||||
style 1-32 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Using ONE run_code program: call the bash tool exactly once with the command seq 1 200 | awk "
|
||||
style 77-99 fg=cyan
|
||||
6| "'{printf \"line %04d: the quick brown fox jumps over the lazy dog\\n\", $1}', then return ONLY the "
|
||||
style 0-72 fg=cyan
|
||||
7| "number of lines in its output. Reply with just that number and stop. "
|
||||
8| <blank>
|
||||
9| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
10| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
11| "The user wants me to write a single run_code program that calls bash exactly once with a specific "
|
||||
style 0-99 dim italic
|
||||
12| "command, then returns only the number of lines in its output. "
|
||||
style 0-60 dim italic
|
||||
13| <blank>
|
||||
14| "● Tool / run_code"
|
||||
style 0-16 fg=green
|
||||
15| "Count lines in seq/awk output "
|
||||
style 0-99 dim
|
||||
16| "200 "
|
||||
style 0-99 dim
|
||||
17| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
18| <blank>
|
||||
19| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
20| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
21| "The result is 200 lines. The user wants me to reply with just that number and stop. "
|
||||
style 0-82 dim italic
|
||||
22| "200 "
|
||||
23| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
24| <blank>
|
||||
25| "/workspace/project deepseek-v4-flash ↑123 ↓208 cache 99% 3% c"
|
||||
style 0-52 fg=bright-magenta bold
|
||||
style 55-71 dim
|
||||
style 74-93 dim
|
||||
style 96-99 dim
|
||||
26| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
27-35| <blank>
|
||||
34
apps/cli/tests/snapshots/code-mode/session.jsonl
Normal file
34
apps/cli/tests/snapshots/code-mode/session.jsonl
Normal file
@@ -0,0 +1,34 @@
|
||||
{"type":"session","version":0,"id":"main-session","createdAt":1785014512062,"cwd":"{{cwd}}"}
|
||||
{"type":"turn/start","seq":0,"time":1785014512139,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1785014512140,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO`. Inside that same program, console.log exactly `captured output`, then return the two outputs joined with a plus sign. Reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":2,"time":1785014512146,"data":{"title":"Using ONE run_code program: call","messageSeqs":[1],"source":{"kind":"fallback"}}}
|
||||
{"type":"step/start","seq":3,"time":1785014512147,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":4,"time":1785014512148,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785014512526,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":6,"time0":1785014512527,"data":{"turn":1,"step":1,"index":0,"dt":[92,26,0,0,0,27,0,1,20,1,0,0,0,25,1,0,0,0,24,1,24,26,0,24,1,25,0,0,0,1,0,24,0,1,0,0,0,24,1,0,0,0,24,0,1,0,24,1,0,0,0,0,24,1,0,24,0,0,0,1,1,23,0,0,0,0,1,24,25,1,24,1,0,0,0,25,0,25,1,0,0,25,0,0,24,1,0,0,0,25,0,0,24,1,0,25,1,0,0,25,23,26,1,0,0,25,0,0,24,1,0,0,24,0,1,0,24,1,0,0,25,0,0,1,0,0,23,0,1,0,0,0,24,1,0,0,0,0,24,0,0,0,0,1,24,1,0,0,0,0,25,0,0,0,0,1,24,0,0,24,1,0,0,0,24,0,1,0,0,0,33,0,0,0,16,1,0,0,24,1,0,0,0,26,1,0,23,25,0,0,25,1,0,24,0,1,0,0,24,1,0],"texts":["The"," user"," wants"," me"," to"," write"," a"," single"," `","run","_code","`"," program"," that",":\n","1","."," Calls"," `","bash","`"," tool"," twice"," -"," first"," with"," `","echo"," CODE","_","ONE","`,"," then"," with"," `","echo"," CODE","_T","WO","`\n","2","."," `","console",".log","`"," exactly"," `","capt","ured"," output","`\n","3","."," Returns"," the"," two"," outputs"," joined"," with"," a"," plus"," sign","\n\n","Let"," me"," think"," about"," the"," structure","."," The"," `","bash","`"," tool"," returns"," an"," object"," with"," stdout","/st","derr","."," I"," need"," to"," extract"," the"," stdout"," text"," from"," each"," call",".\n\n","Looking"," at"," the"," bash"," output"," type",":\n","```\n","{\n"," "," kind",":"," \"","fore","ground","\";\n"," "," exit","Code",":"," number"," |"," null",";\n"," "," signal",":"," string"," |"," null",";\n"," "," timed","Out",":"," boolean",";\n"," "," ab","orted",":"," boolean",";\n"," "," timeout","Ms",":"," number",";\n"," "," stdout",":"," {\n"," "," text",":"," string",";\n"," "," truncated",":"," boolean",";\n"," "," spill","Path","?:"," string",";\n"," "," };\n"," "," st","derr",":"," {"," ..."," };\n"," "," sand","box","?:"," {"," ..."," };\n","}\n","```\n\n","So"," I"," need"," to"," access"," `.","std","out",".text","`"," from"," each"," result",".\n\n","Let"," me"," write"," the"," program","."]}}
|
||||
{"type":"assistant/chunk","seq":208,"time":1785014513974,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":209,"time0":1785014513974,"data":{"turn":1,"step":1,"index":1,"dt":[24,1,0,0,0,24,1,0,24,0,0,40,10,26,0,25,1,0,0,24,1,0,0,0,29,0,0,0,0,0,20,1,0,0,0,24,0,0,0,0,1,25,0,1,0,26,0,0,0,0,0,23,0,0,0,0,0,25,0,0,0,0,0,24,0,0,0,0,1,25,0,0,0,0,0,24,1,0,0,0,0,31,1,17,1,24,0,25,1,0,0,0,24,1,0,0,0,25,25,25,0,0,0,0,0,26,0,0,0,0,1,23,0,1,0,0,0,24,1,24,1,0,24,1,0,0,0,25,0],"id":"call_00_D5QaUXWyA2cPRIFIT6o05977","name":"run_code","args":["","{","\"","description","\"",": ","\"","Call"," bash"," twice",","," log",","," join"," outputs","\"",", ","\"","code","\"",": ","\"","\\n","const"," r","1"," ="," await"," tools",".b","ash","({\\n"," "," command",":"," \\\"","echo"," CODE","_","ONE","\\\",\\n"," "," description",":"," \\\"","E","cho"," CODE","_","ONE","\\\"\\n","});\\n\\n","const"," r","2"," ="," await"," tools",".b","ash","({\\n"," "," command",":"," \\\"","echo"," CODE","_T","WO","\\\",\\n"," "," description",":"," \\\"","E","cho"," CODE","_T","WO","\\\"\\n","});\\n\\n","//"," Extract"," stdout"," text"," and"," trim"," trailing"," new","lines","\\n","const"," out","1"," ="," r","1",".stdout",".text",".trim","();\\n","const"," out","2"," ="," r","2",".stdout",".text",".trim","();\\n\\n","console",".log","(\\\"","capt","ured"," output","\\\");\\n\\n","return"," out","1"," +"," \\\"+","\\\""," +"," out","2",";\\n","\"","}"]}}
|
||||
{"type":"assistant/chunk","seq":339,"time":1785014514829,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to write a single `run_code` program that:\n1. Calls `bash` tool twice - first with `echo CODE_ONE`, then with `echo CODE_TWO`\n2. `console.log` exactly `captured output`\n3. Returns the two outputs joined with a plus sign\n\nLet me think about the structure. The `bash` tool returns an object with stdout/stderr. I need to extract the stdout text from each call.\n\nLooking at the bash output type:\n```\n{\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: { ... };\n sandbox?: { ... };\n}\n```\n\nSo I need to access `.stdout.text` from each result.\n\nLet me write the program."}}}}
|
||||
{"type":"assistant/chunk","seq":340,"time":1785014514830,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_D5QaUXWyA2cPRIFIT6o05977","name":"run_code","arguments":"{\"description\": \"Call bash twice, log, join outputs\", \"code\": \"\\nconst r1 = await tools.bash({\\n command: \\\"echo CODE_ONE\\\",\\n description: \\\"Echo CODE_ONE\\\"\\n});\\n\\nconst r2 = await tools.bash({\\n command: \\\"echo CODE_TWO\\\",\\n description: \\\"Echo CODE_TWO\\\"\\n});\\n\\n// Extract stdout text and trim trailing newlines\\nconst out1 = r1.stdout.text.trim();\\nconst out2 = r2.stdout.text.trim();\\n\\nconsole.log(\\\"captured output\\\");\\n\\nreturn out1 + \\\"+\\\" + out2;\\n\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":341,"time":1785014514830,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":85,"outputTokens":373,"cacheReadTokens":3968,"reasoningTokens":202}}}}
|
||||
{"type":"assistant/chunk","seq":342,"time":1785014514830,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":343,"time":1785014514837,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to write a single `run_code` program that:\n1. Calls `bash` tool twice - first with `echo CODE_ONE`, then with `echo CODE_TWO`\n2. `console.log` exactly `captured output`\n3. Returns the two outputs joined with a plus sign\n\nLet me think about the structure. The `bash` tool returns an object with stdout/stderr. I need to extract the stdout text from each call.\n\nLooking at the bash output type:\n```\n{\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: { ... };\n sandbox?: { ... };\n}\n```\n\nSo I need to access `.stdout.text` from each result.\n\nLet me write the program."},{"type":"tool-call","id":"call_00_D5QaUXWyA2cPRIFIT6o05977","name":"run_code","arguments":"{\"description\": \"Call bash twice, log, join outputs\", \"code\": \"\\nconst r1 = await tools.bash({\\n command: \\\"echo CODE_ONE\\\",\\n description: \\\"Echo CODE_ONE\\\"\\n});\\n\\nconst r2 = await tools.bash({\\n command: \\\"echo CODE_TWO\\\",\\n description: \\\"Echo CODE_TWO\\\"\\n});\\n\\n// Extract stdout text and trim trailing newlines\\nconst out1 = r1.stdout.text.trim();\\nconst out2 = r2.stdout.text.trim();\\n\\nconsole.log(\\\"captured output\\\");\\n\\nreturn out1 + \\\"+\\\" + out2;\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":85,"outputTokens":373,"cacheReadTokens":3968,"reasoningTokens":202}},"sourceEventSeqs":[5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339,340,341,342],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":344,"time":1785014514839,"data":{"turn":1,"step":1,"callId":"call_00_D5QaUXWyA2cPRIFIT6o05977","name":"run_code","arguments":"{\"description\": \"Call bash twice, log, join outputs\", \"code\": \"\\nconst r1 = await tools.bash({\\n command: \\\"echo CODE_ONE\\\",\\n description: \\\"Echo CODE_ONE\\\"\\n});\\n\\nconst r2 = await tools.bash({\\n command: \\\"echo CODE_TWO\\\",\\n description: \\\"Echo CODE_TWO\\\"\\n});\\n\\n// Extract stdout text and trim trailing newlines\\nconst out1 = r1.stdout.text.trim();\\nconst out2 = r2.stdout.text.trim();\\n\\nconsole.log(\\\"captured output\\\");\\n\\nreturn out1 + \\\"+\\\" + out2;\\n\"}"}}
|
||||
{"type":"tool/code-dispatch-start","seq":345,"time":1785014514956,"data":{"parentCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977","subCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"Echo CODE_ONE"}}}
|
||||
{"type":"tool/code-dispatch","seq":346,"time":1785014514990,"data":{"parentCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977","subCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"Echo CODE_ONE"},"isError":false,"content":[{"type":"text","text":"CODE_ONE\n"}]}}
|
||||
{"type":"tool/code-dispatch-start","seq":347,"time":1785014514991,"data":{"parentCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977","subCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Echo CODE_TWO"}}}
|
||||
{"type":"tool/code-dispatch","seq":348,"time":1785014515013,"data":{"parentCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977","subCallId":"call_00_D5QaUXWyA2cPRIFIT6o05977:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Echo CODE_TWO"},"isError":false,"content":[{"type":"text","text":"CODE_TWO\n"}]}}
|
||||
{"type":"tool/result","seq":349,"time":1785014515017,"data":{"turn":1,"step":1,"callId":"call_00_D5QaUXWyA2cPRIFIT6o05977","content":[{"type":"text","text":"captured output\nCODE_ONE+CODE_TWO"}],"isError":false},"sourceEventSeqs":[344],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":350,"time":1785014515018,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":351,"time":1785014515022,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":352,"time":1785014515610,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":353,"time0":1785014515611,"data":{"turn":1,"step":2,"index":0,"dt":[116,25,0,26,1,0,25,26,1,0,0,26,1,0,0,25,0,0,26,0,0,26,0,0,0,1,1,24,0,1,0,0,25,26,0,0,0,0,2,24,0,1,0,25,1,0,0,0,25,1,0,0,0,25,0,0,0,0,0,26,1,0,0,0],"texts":["The"," program"," ran"," successfully","."," The"," output"," shows",":\n","-"," `","capt","ured"," output","`"," (","from"," console",".log",")\n","-"," `","CODE","_","ONE","+","CODE","_T","WO","`"," (","the"," returned"," joined"," string",")\n\n","The"," user"," asked"," me"," to"," reply"," with"," that"," joined"," string"," only"," and"," stop","."," So"," I","'ll"," reply"," with"," just"," `","CODE","_","ONE","+","CODE","_T","WO","`."]}}
|
||||
{"type":"assistant/chunk","seq":418,"time":1785014516169,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"text-chunks","seq0":419,"time0":1785014516169,"data":{"turn":1,"step":2,"index":1,"dt":[0,0,0,0,1,27],"texts":["CODE","_","ONE","+","CODE","_T","WO"]}}
|
||||
{"type":"assistant/chunk","seq":426,"time":1785014516199,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The program ran successfully. The output shows:\n- `captured output` (from console.log)\n- `CODE_ONE+CODE_TWO` (the returned joined string)\n\nThe user asked me to reply with that joined string only and stop. So I'll reply with just `CODE_ONE+CODE_TWO`."}}}}
|
||||
{"type":"assistant/chunk","seq":427,"time":1785014516200,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CODE_ONE+CODE_TWO"}}}}
|
||||
{"type":"assistant/chunk","seq":428,"time":1785014516200,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":97,"outputTokens":73,"cacheReadTokens":4352,"reasoningTokens":65}}}}
|
||||
{"type":"assistant/chunk","seq":429,"time":1785014516200,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":430,"time":1785014516201,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The program ran successfully. The output shows:\n- `captured output` (from console.log)\n- `CODE_ONE+CODE_TWO` (the returned joined string)\n\nThe user asked me to reply with that joined string only and stop. So I'll reply with just `CODE_ONE+CODE_TWO`."},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":73,"cacheReadTokens":4352,"reasoningTokens":65}},"sourceEventSeqs":[352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,380,381,382,383,384,385,386,387,388,389,390,391,392,393,394,395,396,397,398,399,400,401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428,429],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":431,"time":1785014516202,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":432,"time":1785014516202,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
143
apps/cli/tests/snapshots/code-mode/terminal.expected.txt
Normal file
143
apps/cli/tests/snapshots/code-mode/terminal.expected.txt
Normal file
@@ -0,0 +1,143 @@
|
||||
terminal 100x36 buffer=normal length=62 base=26 viewport=26
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Using ONE run_code program: call — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=35 bufferRow=61
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Using ONE run_code program: call"
|
||||
style 1-32 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Using ONE run_code program: call the bash tool twice — exactly echo CODE_ONE then exactly echo "
|
||||
style 63-75 fg=cyan
|
||||
style 90-99 fg=cyan
|
||||
6| "CODE_TWO. Inside that same program, console.log exactly captured output, then return the two outputs"
|
||||
style 0-7 fg=cyan
|
||||
style 56-70 fg=cyan
|
||||
7| "joined with a plus sign. Reply with that joined string only and stop. "
|
||||
8| <blank>
|
||||
9| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
10| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
11| "The user wants me to write a single run_code program that: "
|
||||
style 0-35 dim italic
|
||||
style 36-43 fg=cyan
|
||||
style 44-57 dim italic
|
||||
12| "1. Calls bash tool twice - first with echo CODE_ONE, then with echo CODE_TWO "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-8 dim italic
|
||||
style 9-12 fg=cyan
|
||||
style 13-37 dim italic
|
||||
style 38-50 fg=cyan
|
||||
style 51-62 dim italic
|
||||
style 63-75 fg=cyan
|
||||
13| "2. console.log exactly captured output "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-13 fg=cyan
|
||||
style 14-22 dim italic
|
||||
style 23-37 fg=cyan
|
||||
14| "3. Returns the two outputs joined with a plus sign "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-49 dim italic
|
||||
15| " "
|
||||
16| "Let me think about the structure. The bash tool returns an object with stdout/stderr. I need to "
|
||||
style 0-37 dim italic
|
||||
style 38-41 fg=cyan
|
||||
style 42-99 dim italic
|
||||
17| "extract the stdout text from each call. "
|
||||
style 0-38 dim italic
|
||||
18| " "
|
||||
19| "Looking at the bash output type: "
|
||||
style 0-31 dim italic
|
||||
20| " "
|
||||
21| " "
|
||||
22| " { "
|
||||
style 2-2 fg=cyan
|
||||
23| " kind: \"foreground\"; "
|
||||
style 2-22 fg=cyan
|
||||
24| " exitCode: number | null; "
|
||||
style 2-27 fg=cyan
|
||||
25| " signal: string | null; "
|
||||
style 2-25 fg=cyan
|
||||
26| " timedOut: boolean; "
|
||||
style 2-21 fg=cyan
|
||||
27| " aborted: boolean; "
|
||||
style 2-20 fg=cyan
|
||||
28| " timeoutMs: number; "
|
||||
style 2-21 fg=cyan
|
||||
29| " stdout: { "
|
||||
style 2-12 fg=cyan
|
||||
30| " text: string; "
|
||||
style 2-18 fg=cyan
|
||||
31| " truncated: boolean; "
|
||||
style 2-24 fg=cyan
|
||||
32| " spillPath?: string; "
|
||||
style 2-24 fg=cyan
|
||||
33| " }; "
|
||||
style 2-5 fg=cyan
|
||||
34| " stderr: { ... }; "
|
||||
style 2-19 fg=cyan
|
||||
35| " sandbox?: { ... }; "
|
||||
style 2-21 fg=cyan
|
||||
36| " } "
|
||||
style 2-2 fg=cyan
|
||||
37| " "
|
||||
38| " "
|
||||
39| "So I need to access .stdout.text from each result. "
|
||||
style 0-19 dim italic
|
||||
style 20-31 fg=cyan
|
||||
style 32-49 dim italic
|
||||
40| " "
|
||||
41| "Let me write the program. "
|
||||
style 0-24 dim italic
|
||||
42| <blank>
|
||||
43| "● Tool / run_code"
|
||||
style 0-16 fg=green
|
||||
44| "Call bash twice, log, join outputs "
|
||||
style 0-99 dim
|
||||
45| "captured output "
|
||||
style 0-99 dim
|
||||
46| "CODE_ONE+CODE_TWO "
|
||||
style 0-99 dim
|
||||
47| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
48| <blank>
|
||||
49| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
50| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
51| "The program ran successfully. The output shows: "
|
||||
style 0-46 dim italic
|
||||
52| "- captured output (from console.log) "
|
||||
style 0-1 fg=bright-magenta
|
||||
style 2-16 fg=cyan
|
||||
style 17-35 dim italic
|
||||
53| "- CODE_ONE+CODE_TWO (the returned joined string) "
|
||||
style 0-1 fg=bright-magenta
|
||||
style 2-18 fg=cyan
|
||||
style 19-47 dim italic
|
||||
54| " "
|
||||
55| "The user asked me to reply with that joined string only and stop. So I'll reply with just "
|
||||
style 0-99 dim italic
|
||||
56| "CODE_ONE+CODE_TWO. "
|
||||
style 0-16 fg=cyan
|
||||
style 17-17 dim italic
|
||||
57| "CODE_ONE+CODE_TWO "
|
||||
58| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
59| <blank>
|
||||
60| "/workspace/project deepseek-v4-flash ↑182 ↓446 cache 98% 4% context"
|
||||
style 0-37 fg=bright-magenta bold
|
||||
style 40-56 dim
|
||||
style 59-78 dim
|
||||
style 81-90 dim
|
||||
61| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
@@ -0,0 +1,13 @@
|
||||
{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"{{cwd}}","parentSession":"11111111-1111-4111-8111-111111111111","delegationDepth":1}
|
||||
{"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,13 @@
|
||||
{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"{{cwd}}","parentSession":"11111111-1111-4111-8111-111111111111","delegationDepth":1}
|
||||
{"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,64 @@
|
||||
{"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1783950000000,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}
|
||||
{"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"Temporary Plugin dyn-1 is running (plugin \"snapshot-marker\"; available until unmounted or DSH restarts)."}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":13,"time":1783957884489,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":14,"time":1783950000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":15,"time":1783950000016,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Verify the temporary marker Plugin\"}"}}}
|
||||
{"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Verify the temporary marker Plugin\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Verify the temporary marker Plugin\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.cordis_inspect({ what: 'temporary' })\", \"description\": \"Verify the temporary marker Plugin\"}"}}
|
||||
{"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"temporary"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}}
|
||||
{"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":23,"time":1783957884561,"data":{"turn":1,"step":2}}
|
||||
{"type":"step/start","seq":24,"time":1783957884562,"data":{"turn":1,"step":3}}
|
||||
{"type":"assistant/chunk","seq":25,"time":1783950000026,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":26,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}
|
||||
{"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}
|
||||
{"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}}
|
||||
{"type":"step/start","seq":34,"time":1783957884594,"data":{"turn":1,"step":4}}
|
||||
{"type":"assistant/chunk","seq":35,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":36,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}
|
||||
{"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}
|
||||
{"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}
|
||||
{"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}}
|
||||
{"type":"step/start","seq":44,"time":1783957884718,"data":{"turn":1,"step":5}}
|
||||
{"type":"assistant/chunk","seq":45,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":46,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}}
|
||||
{"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}
|
||||
{"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"Temporary Plugin dyn-1 was unmounted and removed."}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}}
|
||||
{"type":"step/start","seq":54,"time":1783957884720,"data":{"turn":1,"step":6}}
|
||||
{"type":"assistant/chunk","seq":55,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":56,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}
|
||||
{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}
|
||||
{"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
|
||||
{"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}}
|
||||
{"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,110 @@
|
||||
terminal 100x36 buffer=normal length=59 base=23 viewport=23
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Run this advanced flow exactly — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=35 bufferRow=58
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Run this advanced flow exactly"
|
||||
style 1-30 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Run this advanced flow exactly once: try a no-op temporary Cordis Plugin named snapshot-marker; use "
|
||||
6| "run_code to inspect the live temporary Plugins through tools.cordis_inspect; delegate once to a "
|
||||
7| "direct spawn child; run one workflow that delegates to another spawn child; stop dyn-1; then reply "
|
||||
8| "with exactly ADVANCED_ACP_OK. "
|
||||
9| <blank>
|
||||
10| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
11| <blank>
|
||||
12| "● Tool / cordis_mount"
|
||||
style 0-20 fg=green
|
||||
13| "Mount temporary Cordis Plugin "
|
||||
style 0-99 dim
|
||||
14| "Temporary Plugin dyn-1 is running (plugin \"snapshot-marker\"; available until unmounted or DSH "
|
||||
style 0-99 dim
|
||||
15| "restarts). "
|
||||
style 0-99 dim
|
||||
16| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
17| <blank>
|
||||
18| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
19| <blank>
|
||||
20| "● Tool / run_code"
|
||||
style 0-16 fg=green
|
||||
21| "Verify the temporary marker Plugin "
|
||||
style 0-99 dim
|
||||
22| " "
|
||||
23| "Temporary Plugins "
|
||||
style 0-16 fg=bright-magenta bold dim
|
||||
24| " "
|
||||
25| "- Temporary Plugin dyn-1: snapshot-marker [running] — provides: none; waiting for: none; lifetime: "
|
||||
style 0-1 fg=bright-magenta dim
|
||||
style 2-99 dim
|
||||
26| " until unmounted or DSH restarts "
|
||||
style 0-99 dim
|
||||
27| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
28| <blank>
|
||||
29| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
30| <blank>
|
||||
31| "● Tool / subagent"
|
||||
style 0-16 fg=green
|
||||
32| "DIRECT_CHILD_OK "
|
||||
style 0-99 dim
|
||||
33| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
34| <blank>
|
||||
35| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
36| <blank>
|
||||
37| "● Tool / workflow"
|
||||
style 0-16 fg=green
|
||||
38| "workflow: advanced-acp-snapshot "
|
||||
style 0-99 dim
|
||||
39| "workflow \"advanced-acp-snapshot\" completed (1 agent). "
|
||||
style 0-99 dim
|
||||
40| "Return value: "
|
||||
style 0-99 dim
|
||||
41| "{ "
|
||||
style 0-99 dim
|
||||
42| " \"reply\": \"WORKFLOW_CHILD_OK\" "
|
||||
style 0-99 dim
|
||||
43| "} "
|
||||
style 0-99 dim
|
||||
44| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
45| <blank>
|
||||
46| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
47| <blank>
|
||||
48| "● Tool / cordis_unmount"
|
||||
style 0-22 fg=green
|
||||
49| "Unmount temporary Cordis Plugin dyn-1 "
|
||||
style 0-99 dim
|
||||
50| "Temporary Plugin dyn-1 was unmounted and removed. "
|
||||
style 0-99 dim
|
||||
51| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
52| <blank>
|
||||
53| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
54| "ADVANCED_ACP_OK "
|
||||
55| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
56| <blank>
|
||||
57| "/workspace/project deepseek-v4-flash ↑18 ↓18 cache 0% 8% cont"
|
||||
style 0-52 fg=bright-magenta bold
|
||||
style 55-71 dim
|
||||
style 74-90 dim
|
||||
style 93-99 dim
|
||||
58| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
16
apps/cli/tests/snapshots/dynamic-workflow/session.1.jsonl
Normal file
16
apps/cli/tests/snapshots/dynamic-workflow/session.1.jsonl
Normal file
@@ -0,0 +1,16 @@
|
||||
{"type":"session","version":0,"id":"583a4db2-3350-436c-b4a5-5615fd159052","createdAt":1783600636316,"cwd":"{{cwd}}","parentSession":"3fd7d599-56b1-493a-930d-f1fc5e1556e8","delegationDepth":1}
|
||||
{"type":"turn/start","seq":0,"time":1783600636316,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783600636316,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783600636316,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":5,"time0":1783600638073,"data":{"turn":1,"step":1,"index":0,"dt":[100,16,0,0,0,0,24,0,0,0,0,29,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," \"","WF","_CH","ILD","_OK","\""," and"," nothing"," else","."]}}
|
||||
{"type":"assistant/chunk","seq":23,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"text-chunks","seq0":24,"time0":1783600638276,"data":{"turn":1,"step":1,"index":1,"dt":[0,0,0],"texts":["WF","_CH","ILD","_OK"]}}
|
||||
{"type":"assistant/chunk","seq":28,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."}}}}
|
||||
{"type":"assistant/chunk","seq":29,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WF_CHILD_OK"}}}}
|
||||
{"type":"assistant/chunk","seq":30,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}}}}
|
||||
{"type":"assistant/chunk","seq":31,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":33,"time":1783600638281,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":34,"time":1783600638281,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
29
apps/cli/tests/snapshots/dynamic-workflow/session.jsonl
Normal file
29
apps/cli/tests/snapshots/dynamic-workflow/session.jsonl
Normal file
@@ -0,0 +1,29 @@
|
||||
{"type":"session","version":0,"id":"3fd7d599-56b1-493a-930d-f1fc5e1556e8","createdAt":1783600631835,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":1783600631838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783600631838,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783600631839,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":5,"time0":1783600634643,"data":{"turn":1,"step":1,"index":0,"dt":[991,0,0,0,0,0,0,0,0,0,1,0,0,0,108,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,8,0,0,0,0,0,0,2,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," workflow"," tool"," exactly"," once"," with"," specific"," parameters","."," Let"," me"," carefully"," follow"," the"," instructions",":\n\n","1","."," args"," omitted"," (","so"," I"," don","'t"," include"," it",")\n","2","."," meta"," ="," {"," \"","name","\":"," \"","sn","apshot","-flow","\","," \"","description","\":"," \"","one"," child"," for"," the"," snapshot","\""," }\n","3","."," script"," ="," as"," given"," verb","atim","\n","4","."," After"," it"," returns",","," reply"," with"," \"","WORK","FL","OW","_D","ONE","\"\n\n","Let"," me"," do"," exactly"," that","."]}}
|
||||
{"type":"assistant/chunk","seq":93,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":94,"time0":1783600635756,"data":{"turn":1,"step":1,"index":1,"dt":[0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0,0,0,5,0,275,0,0,0,0,206,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0],"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","args":["","{","\"","meta","\"",": ","{\"","name","\":"," \"","sn","apshot","-flow","\","," \"","description","\":"," \"","one"," child"," for"," the"," snapshot","\"","}",", ","\"","script","\"",": ","\"","\\n","phase","('","Run","')\\n","const"," reply"," ="," await"," agent","('","Reply"," with"," exactly"," the"," word"," WF","_CH","ILD","_OK"," and"," nothing"," else",".')\\n","return"," {"," reply"," }\\n","\"","}"]}}
|
||||
{"type":"assistant/chunk","seq":155,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."}}}}
|
||||
{"type":"assistant/chunk","seq":156,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":157,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}}}}
|
||||
{"type":"assistant/chunk","seq":158,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":160,"time":1783600636247,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}}
|
||||
{"type":"tool/result","seq":161,"time":1783600638304,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","content":[{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":162,"time":1783600638304,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":163,"time":1783600638305,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":164,"time":1783600640028,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":165,"time0":1783600640028,"data":{"turn":1,"step":2,"index":0,"dt":[106,28,33,667,0,0,0,0,0,0,2,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0],"texts":["The"," workflow"," returned"," successfully"," with"," the"," reply"," \"","WF","_CH","ILD","_OK","\"."," Now"," I"," need"," to"," reply"," with"," exactly"," \"","WORK","FL","OW","_D","ONE","\""," and"," stop","."]}}
|
||||
{"type":"assistant/chunk","seq":195,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"text-chunks","seq0":196,"time0":1783600640865,"data":{"turn":1,"step":2,"index":1,"dt":[0,0,0,0],"texts":["WORK","FL","OW","_D","ONE"]}}
|
||||
{"type":"assistant/chunk","seq":201,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."}}}}
|
||||
{"type":"assistant/chunk","seq":202,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WORKFLOW_DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":203,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}}}}
|
||||
{"type":"assistant/chunk","seq":204,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":206,"time":1783600640865,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":207,"time":1783600640865,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,86 @@
|
||||
terminal 100x36 buffer=normal length=43 base=7 viewport=7
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Use the workflow tool exactly — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=35 bufferRow=42
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Use the workflow tool exactly"
|
||||
style 1-29 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", "
|
||||
6| "\"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim): "
|
||||
7| "phase('Run') "
|
||||
8| "const reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.') "
|
||||
9| "return { reply } "
|
||||
10| "After the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other "
|
||||
11| "tool. "
|
||||
12| <blank>
|
||||
13| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
14| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
15| "The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully "
|
||||
style 0-99 dim italic
|
||||
16| "follow the instructions: "
|
||||
style 0-23 dim italic
|
||||
17| " "
|
||||
18| "1. args omitted (so I don't include it) "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-38 dim italic
|
||||
19| "2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" } "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-81 dim italic
|
||||
20| "3. script = as given verbatim "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-28 dim italic
|
||||
21| "4. After it returns, reply with \"WORKFLOW_DONE\" "
|
||||
style 0-2 fg=bright-magenta
|
||||
style 3-46 dim italic
|
||||
22| " "
|
||||
23| "Let me do exactly that. "
|
||||
style 0-22 dim italic
|
||||
24| <blank>
|
||||
25| "● Tool / workflow"
|
||||
style 0-16 fg=green
|
||||
26| "workflow: snapshot-flow "
|
||||
style 0-99 dim
|
||||
27| "workflow \"snapshot-flow\" completed (1 agent). "
|
||||
style 0-99 dim
|
||||
28| "Return value: "
|
||||
style 0-99 dim
|
||||
29| "{ "
|
||||
style 0-99 dim
|
||||
30| " \"reply\": \"WF_CHILD_OK\" "
|
||||
style 0-99 dim
|
||||
31| "} "
|
||||
style 0-99 dim
|
||||
32| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
33| <blank>
|
||||
34| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
35| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
36| "The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly "
|
||||
style 0-99 dim italic
|
||||
37| "\"WORKFLOW_DONE\" and stop. "
|
||||
style 0-24 dim italic
|
||||
38| "WORKFLOW_DONE "
|
||||
39| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
40| <blank>
|
||||
41| "/workspace/project deepseek-v4-flash ↑3.5k ↓227 cache 47% 3% context"
|
||||
style 0-44 fg=bright-magenta bold
|
||||
style 47-63 dim
|
||||
style 66-86 dim
|
||||
style 89-98 dim
|
||||
42| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
@@ -0,0 +1,31 @@
|
||||
{"type":"session","version":0,"id":"228b7b82-84ed-49b7-a567-981c03b28c77","createdAt":1783352113760,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":1783352113765,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783352113765,"data":{"content":[{"type":"text","text":"Reply with exactly the word: ONE. No tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783352113767,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783352113768,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":5,"time0":1783352114428,"data":{"turn":1,"step":1,"index":0,"dt":[114,28,1,0,0,1,28,1,1,0,0,1,24,1,29,1,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","ONE","\""," and"," use"," no"," tools","."]}}
|
||||
{"type":"assistant/chunk","seq":23,"time":1783352114658,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":24,"time":1783352114658,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
|
||||
{"type":"assistant/chunk","seq":25,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."}}}}
|
||||
{"type":"assistant/chunk","seq":26,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ONE"}}}}
|
||||
{"type":"assistant/chunk","seq":27,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}}}}
|
||||
{"type":"assistant/chunk","seq":28,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":29,"time":1783352114690,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":30,"time":1783352114690,"data":{"turn":1,"step":1}}
|
||||
{"type":"turn/end","seq":31,"time":1783352114690,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
{"type":"turn/start","seq":32,"time":1783352114699,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":33,"time":1783352114699,"data":{"content":[{"type":"text","text":"Reply with exactly the word: TWO. No tools."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":34,"time":1783352114700,"data":{"turn":2,"step":1}}
|
||||
{"type":"assistant/chunk","seq":35,"time":1783352115341,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":36,"time0":1783352115341,"data":{"turn":2,"step":1,"index":0,"dt":[124,27,1,0,0,28,0,0,31,0,0,0,0,28,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","T","WO","\""," and"," no"," tools","."]}}
|
||||
{"type":"assistant/chunk","seq":54,"time":1783352115609,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":55,"time":1783352115609,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"T"}}}
|
||||
{"type":"assistant/chunk","seq":56,"time":1783352115609,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"WO"}}}
|
||||
{"type":"assistant/chunk","seq":57,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."}}}}
|
||||
{"type":"assistant/chunk","seq":58,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"TWO"}}}}
|
||||
{"type":"assistant/chunk","seq":59,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}}
|
||||
{"type":"assistant/chunk","seq":60,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":61,"time":1783352115611,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":62,"time":1783352115611,"data":{"turn":2,"step":1}}
|
||||
{"type":"turn/end","seq":63,"time":1783352115611,"data":{"turn":2,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,62 @@
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Reply with exactly the word: — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=30 bufferRow=30
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Reply with exactly the word:"
|
||||
style 1-28 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Reply with exactly the word: ONE. No tools. "
|
||||
6| <blank>
|
||||
7| "Plan mode on. Use /plan off to leave. "
|
||||
style 0-36 dim
|
||||
8| <blank>
|
||||
9| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
10| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
11| "The user wants me to reply with exactly the word \"ONE\" and use no tools. "
|
||||
style 0-71 dim italic
|
||||
12| "ONE "
|
||||
13| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
14| <blank>
|
||||
15| "Context · plan-mode"
|
||||
style 0-18 dim
|
||||
16| "The user switched this session back to the default mode. "
|
||||
style 0-55 dim
|
||||
17| <blank>
|
||||
18| "Plan mode off. "
|
||||
style 0-13 dim
|
||||
19| <blank>
|
||||
20| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
21| "Reply with exactly the word: TWO. No tools. "
|
||||
22| <blank>
|
||||
23| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
24| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
25| "The user wants me to reply with exactly the word \"TWO\" and no tools. "
|
||||
style 0-67 dim italic
|
||||
26| "TWO "
|
||||
27| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
28| <blank>
|
||||
29| "/workspace/project deepseek-v4-flash ↑2.9k ↓41 cache 49% 3% co"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-92 dim
|
||||
style 95-99 dim
|
||||
30| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
31-35| <blank>
|
||||
28
apps/cli/tests/snapshots/parallel-file-reads/session.jsonl
Normal file
28
apps/cli/tests/snapshots/parallel-file-reads/session.jsonl
Normal file
@@ -0,0 +1,28 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_read_a","name":"read","argumentsDelta":"{\"file_path\":\"a.txt\"}"}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_read_b","name":"read","argumentsDelta":"{\"file_path\":\"b.txt\"}"}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":12,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"},{"type":"tool-call","id":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":13,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"}}
|
||||
{"type":"tool/call","seq":14,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}}
|
||||
{"type":"tool/result","seq":15,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_a","content":[{"type":"text","text":"<path>{{cwd}}/a.txt</path>\n<type>file</type>\n<content>\n1: alpha\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"}
|
||||
{"type":"tool/result","seq":16,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_b","content":[{"type":"text","text":"<path>{{cwd}}/b.txt</path>\n<type>file</type>\n<content>\n1: beta\n\n(End of file - total 1 lines)\n</content>"}],"isError":false},"sourceEventSeqs":[14],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":17,"time":0,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":18,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
|
||||
{"type":"assistant/chunk","seq":21,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":22,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":1}}}}
|
||||
{"type":"assistant/chunk","seq":23,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":24,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":1}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":25,"time":0,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":26,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -0,0 +1,58 @@
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Use the read tool twice — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=27 bufferRow=27
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Use the read tool twice"
|
||||
style 1-23 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE. "
|
||||
6| <blank>
|
||||
7| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
8| <blank>
|
||||
9| "● Tool / read"
|
||||
style 0-12 fg=green
|
||||
10| "Read a.txt "
|
||||
style 0-99 dim
|
||||
11| "1: alpha "
|
||||
style 0-99 dim
|
||||
12| " "
|
||||
13| "(End of file - total 1 lines) "
|
||||
style 0-99 dim
|
||||
14| <blank>
|
||||
15| "● Tool / read"
|
||||
style 0-12 fg=green
|
||||
16| "Read b.txt "
|
||||
style 0-99 dim
|
||||
17| "1: beta "
|
||||
style 0-99 dim
|
||||
18| " "
|
||||
19| "(End of file - total 1 lines) "
|
||||
style 0-99 dim
|
||||
20| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
21| <blank>
|
||||
22| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
23| "DONE "
|
||||
24| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
25| <blank>
|
||||
26| "/workspace/project deepseek-v4-flash ↑20 ↓6 cache 0% 3% context"
|
||||
style 0-47 fg=bright-magenta bold
|
||||
style 50-66 dim
|
||||
style 69-84 dim
|
||||
style 87-96 dim
|
||||
27| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
28-35| <blank>
|
||||
@@ -0,0 +1 @@
|
||||
alpha
|
||||
@@ -0,0 +1 @@
|
||||
beta
|
||||
@@ -0,0 +1,5 @@
|
||||
{"type":"session","version":0,"id":"31f63cc0-0198-4ab2-bfde-79a4eb4f1867","createdAt":1783352180000,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"assistant/chunk","seq":0,"time":1783352180001,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":1,"time":1783352180002,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"USER-ONLY SKILL LOADED"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1783352180003,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"USER-ONLY SKILL LOADED"}}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1783352180004,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
@@ -0,0 +1,157 @@
|
||||
=== skill autocomplete ===
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "DSH TUI snapshot"
|
||||
cursor hidden column=13 viewportRow=5 bufferRow=5
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Recorded replay: skill-invocation-policy"
|
||||
style 1-40 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "/workspace/project deepseek-v4-flash ↑0 ↓0 0% context"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-77 dim
|
||||
style 80-89 dim
|
||||
5| " dsh > /skill "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 13-13 inverse
|
||||
6| " → skill:user-only-skill (project) — User-only assembled snapshot skill. "
|
||||
style 7-78 fg=bright-magenta
|
||||
7-35| <blank>
|
||||
|
||||
|
||||
=== loaded exact invocation ===
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "<skill name=\"user-only-skill\"> Reference — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=30 bufferRow=30
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " <skill name=\"user-only-skill\"> Reference"
|
||||
style 1-40 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "<skill name=\"user-only-skill\"> "
|
||||
6| "References in this skill are relative to "
|
||||
7| "/workspace/project/.agents/skills/user-only-skill. "
|
||||
8| " "
|
||||
9| "USER-ONLY BODY "
|
||||
10| "</skill> "
|
||||
11| <blank>
|
||||
12| "Context · dsh-tool-skill"
|
||||
style 0-23 dim
|
||||
13| "A skill is a reusable set of task-specific instructions. The following skills are available in this "
|
||||
style 0-99 dim
|
||||
14| "session: "
|
||||
style 0-7 dim
|
||||
15| " "
|
||||
16| "<available_skills> "
|
||||
style 0-17 dim
|
||||
17| "- `model-only-skill`: Model-only assembled snapshot skill. "
|
||||
style 0-57 dim
|
||||
18| "</available_skills> "
|
||||
style 0-18 dim
|
||||
19| " "
|
||||
20| "If the user names a skill, or the task clearly matches a skill's description, call the `skill` tool "
|
||||
style 0-99 dim
|
||||
21| "with the exact skill name before taking task actions. Load all applicable skills, then follow their "
|
||||
style 0-99 dim
|
||||
22| "full instructions. This catalog contains summaries only; do not infer or follow a skill's "
|
||||
style 0-99 dim
|
||||
23| "instructions until it has been loaded. "
|
||||
style 0-37 dim
|
||||
24| <blank>
|
||||
25| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
26| "USER-ONLY SKILL LOADED "
|
||||
27| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
28| <blank>
|
||||
29| "/workspace/project deepseek-v4-flash ↑0 ↓0 3% context"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-77 dim
|
||||
style 80-89 dim
|
||||
30| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
31-35| <blank>
|
||||
|
||||
|
||||
=== denied exact invocation ===
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "<skill name=\"user-only-skill\"> Reference — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=32 bufferRow=32
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " <skill name=\"user-only-skill\"> Reference"
|
||||
style 1-40 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "<skill name=\"user-only-skill\"> "
|
||||
6| "References in this skill are relative to "
|
||||
7| "/workspace/project/.agents/skills/user-only-skill. "
|
||||
8| " "
|
||||
9| "USER-ONLY BODY "
|
||||
10| "</skill> "
|
||||
11| <blank>
|
||||
12| "Context · dsh-tool-skill"
|
||||
style 0-23 dim
|
||||
13| "A skill is a reusable set of task-specific instructions. The following skills are available in this "
|
||||
style 0-99 dim
|
||||
14| "session: "
|
||||
style 0-7 dim
|
||||
15| " "
|
||||
16| "<available_skills> "
|
||||
style 0-17 dim
|
||||
17| "- `model-only-skill`: Model-only assembled snapshot skill. "
|
||||
style 0-57 dim
|
||||
18| "</available_skills> "
|
||||
style 0-18 dim
|
||||
19| " "
|
||||
20| "If the user names a skill, or the task clearly matches a skill's description, call the `skill` tool "
|
||||
style 0-99 dim
|
||||
21| "with the exact skill name before taking task actions. Load all applicable skills, then follow their "
|
||||
style 0-99 dim
|
||||
22| "full instructions. This catalog contains summaries only; do not infer or follow a skill's "
|
||||
style 0-99 dim
|
||||
23| "instructions until it has been loaded. "
|
||||
style 0-37 dim
|
||||
24| <blank>
|
||||
25| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
26| "USER-ONLY SKILL LOADED "
|
||||
27| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
28| <blank>
|
||||
29| "Skill \"model-only-skill\" is not available for user invocation. "
|
||||
style 0-61 fg=yellow
|
||||
30| <blank>
|
||||
31| "/workspace/project deepseek-v4-flash ↑0 ↓0 3% context"
|
||||
style 0-51 fg=bright-magenta bold
|
||||
style 54-70 dim
|
||||
style 73-77 dim
|
||||
style 80-89 dim
|
||||
32| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
33-35| <blank>
|
||||
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: model-only-skill
|
||||
description: Model-only assembled snapshot skill.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
MODEL-ONLY BODY MUST NOT LOAD
|
||||
@@ -0,0 +1,7 @@
|
||||
---
|
||||
name: user-only-skill
|
||||
description: User-only assembled snapshot skill.
|
||||
disable-model-invocation: true
|
||||
---
|
||||
|
||||
USER-ONLY BODY
|
||||
31
apps/cli/tests/snapshots/todo-plan/session.jsonl
Normal file
31
apps/cli/tests/snapshots/todo-plan/session.jsonl
Normal file
@@ -0,0 +1,31 @@
|
||||
{"type":"session","version":0,"id":"b0f1f758-dcf0-474e-851d-e62c11ec0a09","createdAt":1783352057652,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"turn/start","seq":0,"time":1783352057655,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}
|
||||
{"type":"user/message","seq":1,"time":1783352057655,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
|
||||
{"type":"step/start","seq":2,"time":1783352057657,"data":{"turn":1,"step":1}}
|
||||
{"type":"request/header","seq":3,"time":1783352057657,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":5,"time0":1783352058320,"data":{"turn":1,"step":1,"index":0,"dt":[106,40,1,0,0,0,17,0,0,0,1,26,1,1,0,0,1,26,0,31,1,25,0,0,0,29,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," todo","_write"," tool"," to"," record"," a"," plan"," with"," exactly"," three"," todos"," in"," the"," specified"," status","es",","," then"," reply"," with"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":36,"time":1783352058717,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":37,"time0":1783352058717,"data":{"turn":1,"step":1,"index":1,"dt":[29,1,0,0,28,0,1,29,1,0,0,0,0,26,0,0,0,0,0,30,1,0,0,0,0,26,1,0,0,0,0,28,0,0,0,0,0,29,0,0,0,0,1,28,0,0,0,1,0,27,1,0,28],"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","args":["","{","\"","t","odos","\"",": ","[","{\"","content","\":"," \"","read"," the"," code","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","write"," the"," fix","\","," \"","status","\":"," \"","pending","\"},"," {\"","content","\":"," \"","run"," the"," tests","\","," \"","status","\":"," \"","pending","\"","}]","}"]}}
|
||||
{"type":"assistant/chunk","seq":91,"time":1783352059095,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."}}}}
|
||||
{"type":"assistant/chunk","seq":92,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}}
|
||||
{"type":"assistant/chunk","seq":93,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}}}}
|
||||
{"type":"assistant/chunk","seq":94,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":95,"time":1783352059099,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":96,"time":1783352059099,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}
|
||||
{"type":"todo/write","seq":97,"time":1783352059100,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}}
|
||||
{"type":"tool/result","seq":98,"time":1783352059101,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[96],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":99,"time":1783352059101,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":100,"time":1783352059102,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":101,"time":1783352059732,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":102,"time0":1783352059733,"data":{"turn":1,"step":2,"index":0,"dt":[102,28,0,1,0,28,0,1,0,27,0,1,0,0,29,0,0,0,1,0],"texts":["The"," todos"," have"," been"," written"," successfully","."," Now"," I"," just"," need"," to"," reply"," with"," the"," single"," word"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":123,"time":1783352059979,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":124,"time":1783352059979,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
|
||||
{"type":"assistant/chunk","seq":125,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
|
||||
{"type":"assistant/chunk","seq":126,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."}}}}
|
||||
{"type":"assistant/chunk","seq":127,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":128,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}}}}
|
||||
{"type":"assistant/chunk","seq":129,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":130,"time":1783352059981,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":131,"time":1783352059981,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":132,"time":1783352059981,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
65
apps/cli/tests/snapshots/todo-plan/terminal.expected.txt
Normal file
65
apps/cli/tests/snapshots/todo-plan/terminal.expected.txt
Normal file
@@ -0,0 +1,65 @@
|
||||
terminal 100x36 buffer=normal length=36 base=0 viewport=0
|
||||
lifecycle started=1 stopped=0 progress=inactive
|
||||
title "Use the todo_write tool to — DSH TUI snapshot"
|
||||
cursor hidden column=7 viewportRow=31 bufferRow=31
|
||||
buffer
|
||||
0| " DEEPSEEK HARNESS"
|
||||
style 1-8 fg=bright-magenta bold
|
||||
style 10-16 bold
|
||||
1| " Use the todo_write tool to"
|
||||
style 1-26 dim
|
||||
2| " main-session"
|
||||
style 1-12 dim
|
||||
3| <blank>
|
||||
4| "You "
|
||||
style 0-2 fg=bright-magenta bold underline
|
||||
5| "Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), "
|
||||
6| "\"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then "
|
||||
7| "reply with the single word DONE and stop. "
|
||||
8| <blank>
|
||||
9| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
10| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
11| "The user wants me to use the todo_write tool to record a plan with exactly three todos in the "
|
||||
style 0-99 dim italic
|
||||
12| "specified statuses, then reply with \"DONE\". "
|
||||
style 0-42 dim italic
|
||||
13| <blank>
|
||||
14| "● Tool / todo_write"
|
||||
style 0-18 fg=green
|
||||
15| "Update todo list "
|
||||
style 0-99 dim
|
||||
16| "Updated todo list: 2 pending, 1 in progress, 0 completed. "
|
||||
style 0-99 dim
|
||||
17| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
18| <blank>
|
||||
19| "Assistant "
|
||||
style 0-8 fg=bright-magenta bold underline
|
||||
20| "Reasoning "
|
||||
style 0-8 dim italic
|
||||
21| "The todos have been written successfully. Now I just need to reply with the single word \"DONE\". "
|
||||
style 0-94 dim italic
|
||||
22| "DONE "
|
||||
23| "Model wait 0.0s · Completed 2026-07-21 12:00:00 "
|
||||
style 0-46 dim
|
||||
24-25| <blank>
|
||||
26| "Plan"
|
||||
style 0-3 fg=bright-magenta bold
|
||||
27| " ● read the code"
|
||||
style 2-2 fg=yellow
|
||||
28| " ○ write the fix"
|
||||
style 2-2 dim
|
||||
29| " ○ run the tests"
|
||||
style 2-2 dim
|
||||
30| "/workspace/project deepseek-v4-flash ↑3.1k ↓145 cache 47% 3% context"
|
||||
style 0-37 fg=bright-magenta bold
|
||||
style 40-56 dim
|
||||
style 59-79 dim
|
||||
style 82-91 dim
|
||||
31| " dsh ◍ "
|
||||
style 1-3 fg=bright-magenta bold
|
||||
style 5-6 dim
|
||||
style 7-7 inverse
|
||||
32-35| <blank>
|
||||
516
apps/cli/tests/tui-keyless-smoke.e2e.ts
Normal file
516
apps/cli/tests/tui-keyless-smoke.e2e.ts
Normal file
@@ -0,0 +1,516 @@
|
||||
import { createUserMessage, createMessage } from '@deepseek-ai/dsh-llm'
|
||||
import { realpathSync } from 'node:fs'
|
||||
import { mkdir, readdir, readFile, writeFile } from 'node:fs/promises'
|
||||
import { dirname, join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { LOADER_SMOKE_TEST_TIMEOUT_MS } from '@deepseek-ai/dsh-loader-smoke'
|
||||
import { packChunkRuns, SessionId, type SessionEvent, type SessionHeader } from '@deepseek-ai/dsh-session'
|
||||
import { logPath, toHeaderLine } from '../../../packages/session-persistence/session-persistence-jsonl/src/format.ts'
|
||||
import { runTuiPtySmoke, type TuiPtySmokeOptions } from './pty-harness.ts'
|
||||
|
||||
const dshBinScript = fileURLToPath(new URL('../src/bin.ts', import.meta.url))
|
||||
// `--config` layers an overlay over the shared base, so the default surface
|
||||
// needs no config argument at all; these are the overlays under test.
|
||||
const scriptedConfigPath = fileURLToPath(new URL('./fixtures/tui-scripted.cordis.yml', import.meta.url))
|
||||
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
|
||||
|
||||
/**
|
||||
* Seed the isolated process workspace: ordinary files land in `cwd`, personal
|
||||
* files in the Harness home (`.dsh`), and skill bundles under the agents
|
||||
* home's `skills/` root — the same trees `$DSH_HOME` /
|
||||
* `$DSH_AGENTS_HOME` point the child at.
|
||||
*/
|
||||
function seedWorkspace(
|
||||
files: {
|
||||
workspace?: Record<string, string>
|
||||
personal?: Record<string, string>
|
||||
skills?: Record<string, string>
|
||||
},
|
||||
): (cwd: string) => Promise<void> {
|
||||
return async (cwd) => {
|
||||
for (const [name, content] of Object.entries(files.workspace ?? {})) {
|
||||
const file = join(cwd, name)
|
||||
await mkdir(dirname(file), { recursive: true })
|
||||
await writeFile(file, content)
|
||||
}
|
||||
for (const [name, content] of Object.entries(files.personal ?? {})) {
|
||||
const file = join(cwd, '.dsh', name)
|
||||
await mkdir(dirname(file), { recursive: true })
|
||||
await writeFile(file, content)
|
||||
}
|
||||
for (const [name, content] of Object.entries(files.skills ?? {})) {
|
||||
const file = join(cwd, '.agents', 'skills', name)
|
||||
await mkdir(dirname(file), { recursive: true })
|
||||
await writeFile(file, content)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/** Seed one real plaintext JSONL session for the `/resume` selector and host handoff smoke. */
|
||||
async function seedResumeSession(cwd: string): Promise<void> {
|
||||
const sessionCwd = realpathSync.native(cwd)
|
||||
const id = SessionId('resume-target')
|
||||
const meta: SessionHeader = { version: 0, id, createdAt: 1_700_000_000_000, cwd: sessionCwd }
|
||||
const events: SessionEvent[] = [
|
||||
{ type: 'turn/start', seq: 0, time: 1_700_000_000_001, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } },
|
||||
{ type: 'user/message', seq: 1, time: 1_700_000_000_002, data: createUserMessage({
|
||||
content: [{ type: 'text', text: 'persisted prompt' }], source: { kind: 'user' },
|
||||
}), surfaceOp: 'append' },
|
||||
{ type: 'step/start', seq: 2, time: 1_700_000_000_003, data: { turn: 1, step: 1 } },
|
||||
{ type: 'request/header', seq: 3, time: 1_700_000_000_004, data: { header: { config: { provider: 'tui-scripted', model: 'tui-scripted-model' } }, reason: 'initial' } },
|
||||
{ type: 'assistant/message', seq: 4, time: 1_700_000_000_005, data: {
|
||||
turn: 1, step: 1,
|
||||
message: createMessage({
|
||||
role: 'assistant',
|
||||
content: [{ type: 'text', text: 'persisted answer' }],
|
||||
source: {
|
||||
kind: 'model',
|
||||
...{ provider: 'tui-scripted', model: 'tui-scripted-model' },
|
||||
},
|
||||
}),
|
||||
}, surfaceOp: 'append' },
|
||||
{ type: 'step/end', seq: 5, time: 1_700_000_000_006, data: { turn: 1, step: 1 } },
|
||||
{ type: 'session/title', seq: 6, time: 1_700_000_000_007, data: { title: 'Resume selector design', messageSeqs: [1], source: { kind: 'fallback' } } },
|
||||
{ type: 'todo/write', seq: 7, time: 1_700_000_000_008, data: { todos: [{ content: 'Preserve restored state', status: 'in_progress' }] } },
|
||||
{ type: 'turn/end', seq: 8, time: 1_700_000_000_009, data: { turn: 1, reason: { kind: 'completed' } } },
|
||||
]
|
||||
const file = logPath(join(cwd, '.sessions'), sessionCwd, id, 'none')
|
||||
await mkdir(dirname(file), { recursive: true })
|
||||
await writeFile(file, [
|
||||
JSON.stringify(toHeaderLine(meta)),
|
||||
...packChunkRuns(events).map(record => JSON.stringify(record)),
|
||||
'',
|
||||
].join('\n'))
|
||||
}
|
||||
|
||||
/** Model-visible startup context from the first request in the workspace's persisted session log. */
|
||||
interface LoggedRequestContext {
|
||||
/** The system prompt string the launcher sends. */
|
||||
system: string
|
||||
/** The durable skill-catalog message serialized to text. */
|
||||
skillCatalog: string
|
||||
}
|
||||
|
||||
async function readLoggedRequestContext(cwd: string): Promise<LoggedRequestContext> {
|
||||
const sessionsDir = join(cwd, '.sessions')
|
||||
const entries = await readdir(sessionsDir, { recursive: true })
|
||||
// A single keyless run writes one session log; the source section is global, so any log carries it.
|
||||
const logRelPath = entries.find(name => name.endsWith('.jsonl'))
|
||||
if (logRelPath === undefined) throw new Error(`no session log written under ${sessionsDir}`)
|
||||
const lines = (await readFile(join(sessionsDir, logRelPath), 'utf8')).split('\n').filter(Boolean)
|
||||
let skillCatalog = ''
|
||||
for (const line of lines) {
|
||||
const event = JSON.parse(line) as SessionEvent
|
||||
if (
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'plugin'
|
||||
&& event.data.source.plugin === 'dsh-tool-skill'
|
||||
) {
|
||||
skillCatalog = JSON.stringify(event.data.content)
|
||||
}
|
||||
if (event.type === 'request/header') {
|
||||
return {
|
||||
system: event.data.header.system ?? '',
|
||||
skillCatalog,
|
||||
}
|
||||
}
|
||||
}
|
||||
throw new Error(`session log ${logRelPath} has no request/header event`)
|
||||
}
|
||||
|
||||
/**
|
||||
* Shared defaults: the keyless key and the dsh bin. Each case supplies either
|
||||
* `configArgs: []` (boot the shipped composition, `base.cordis.yml` +
|
||||
* `tui.cordis.yml`, with no flags) or `configPath` (an overlay layered over that
|
||||
* same base through `--config`).
|
||||
*/
|
||||
function smoke(overrides: Partial<TuiPtySmokeOptions> & { label: string }): Promise<string> {
|
||||
return runTuiPtySmoke({
|
||||
tempDirPrefix: 'dsh-tui-smoke-',
|
||||
binScript: dshBinScript,
|
||||
tsconfigPath,
|
||||
env: { DEEPSEEK_API_KEY: 'keyless-tui-no-call' },
|
||||
// Artifact CI builds and smokes concurrently on a contended runner.
|
||||
...(process.env.DSH_EXAMPLE_MODE === 'lib' ? { timeoutMs: 60_000 } : {}),
|
||||
...overrides,
|
||||
})
|
||||
}
|
||||
|
||||
// The scripted conversation switches to the pro model first: the scripted
|
||||
// adapter proves routing + prompt variables by rejecting tool-ful calls on any
|
||||
// other route (see fixtures/tui-scripted-llm.ts).
|
||||
const SELECT_PRO_MODEL = [
|
||||
{ waitFor: 'scripted TUI ready.', send: '/model\r' },
|
||||
{ waitFor: 'Select model', send: '\x1b[B\x1b[Z\r' },
|
||||
] as const
|
||||
|
||||
describe('dsh TUI keyless smoke (real Loader tree in a PTY)', () => {
|
||||
it('boots pi-tui, sweeps the borderless banner in, enters plan mode, and restores the terminal', async () => {
|
||||
// With no configured welcome the borderless banner sweeps in left-to-right;
|
||||
// the detail line's session id (`main-session-<uuid>`) renders only once
|
||||
// the sweep reaches it, so it marks a settled banner.
|
||||
const output = await smoke({
|
||||
label: 'dsh boot',
|
||||
configArgs: [],
|
||||
actions: [
|
||||
{ waitFor: 'main-session-', send: '/plan' },
|
||||
{ waitFor: '[off|message] — Enter or leave plan mode', send: '\r' },
|
||||
{ waitFor: 'Plan mode on. Use /plan off to leave.', send: '/exit\r' },
|
||||
],
|
||||
})
|
||||
expect(output).toContain('DEEPSEEK')
|
||||
expect(output).toContain('HARNESS')
|
||||
expect(output).toContain('main-session-')
|
||||
expect(output).toContain('[off|message] — Enter or leave plan mode')
|
||||
expect(output).toContain('Plan mode on. Use /plan off to leave.')
|
||||
// Borderless: no box-drawing frame around the banner.
|
||||
expect(output).not.toContain('╭')
|
||||
expect(output).not.toContain('╮')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('switches models, streams a response, answers a user-question dialog, and exits cleanly', async () => {
|
||||
const output = await smoke({
|
||||
label: 'dsh conversation',
|
||||
tempDirPrefix: 'dsh-tui-conversation-',
|
||||
configPath: scriptedConfigPath,
|
||||
actions: [
|
||||
...SELECT_PRO_MODEL,
|
||||
{ waitFor: 'Model selected: tui-scripted/tui-scripted-model-pro.', send: '/plan exercise the TUI\r' },
|
||||
// The question text first appears in the streamed tool-call card. Wait
|
||||
// for the dialog's input legend so Enter cannot arrive before it owns
|
||||
// terminal input when pre-dispatch policy yields.
|
||||
{ waitFor: 'Tab custom answer • ↑/↓ navigate • Enter submit • Esc interrupt', send: '\r' },
|
||||
{ waitFor: 'Decision received. Scripted TUI run complete.', send: '' },
|
||||
// Session title: the first user message drives the first-message-llm
|
||||
// provider's tool-less title call; the scripted adapter answers it, the
|
||||
// accepted title lands in the log, and the TUI renders the terminal
|
||||
// window title as `<session title> — <configured title>` via OSC 0.
|
||||
// Gating /status on it keeps the assertion race-free; the diagnostics
|
||||
// card is then exercised through the same real Loader/PTY composition.
|
||||
{ waitFor: 'scripted session title — DeepSeek Harness', send: '/plan off\r' },
|
||||
{ waitFor: 'Plan mode off.', send: 'Confirm the scripted run left plan mode.\r' },
|
||||
{ waitFor: 'Default mode confirmed.', send: '/status\r' },
|
||||
{ waitFor: 'Session status', send: '/exit\r' },
|
||||
],
|
||||
})
|
||||
expect(output).toContain('I need one decision before I continue.')
|
||||
expect(output).toContain('Reasoning effort: Max.')
|
||||
expect(output).toContain('Plan mode on. Use /plan off to leave.')
|
||||
expect(output).toContain('Plan mode off.')
|
||||
expect(output).toContain('Default mode confirmed.')
|
||||
expect(output).toContain(String.raw`\x1b]2;MODEL_CONTROLLED\x07`)
|
||||
expect(output).toContain(String.raw`\x1b[999CMODEL_CURSOR`)
|
||||
expect(output).toContain(String.raw`\x9b31mMODEL_C1`)
|
||||
expect(output).not.toContain('\u001B]2;MODEL_CONTROLLED\u0007')
|
||||
expect(output).not.toContain('\u001B[999CMODEL_CURSOR')
|
||||
expect(output).not.toContain('\u009B31mMODEL_C1')
|
||||
expect(output).toContain('Safe')
|
||||
expect(output).toContain('\u001B]0;scripted session title — DeepSeek Harness\u0007')
|
||||
expect(output).toContain('Session status')
|
||||
expect(output).toContain('Title')
|
||||
expect(output).toContain('scripted session title')
|
||||
expect(output).toContain('Model')
|
||||
expect(output).toContain('tui-scripted/tui-scripted-model-pro')
|
||||
expect(output).toContain('KV cache')
|
||||
expect(output).toContain('Context')
|
||||
expect(output).toContain('128,000')
|
||||
expect(output).toContain('System prompt')
|
||||
expect(output).toContain('You are an AI agent powered by the DeepSeek Harness SDK.')
|
||||
expect(output).toContain('Registered tools')
|
||||
expect(output).toContain('ask_user_question')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('loads a local skill via /skill: and delivers its body to the model as a user turn', async () => {
|
||||
// The whole user-only invocation path in one keyless boot: `ctx.get('skills')`
|
||||
// resolves in the shipped tree, the client-side `/skill:` command parses,
|
||||
// and the local provider admits a model-disabled skill by the omitted
|
||||
// `user-invocable` default. The rendered `<skill name="…">` block reaches
|
||||
// the model — proven by the scripted adapter echoing the fixture's body
|
||||
// marker only when it arrives.
|
||||
const output = await smoke({
|
||||
label: 'dsh skill',
|
||||
tempDirPrefix: 'dsh-tui-skill-',
|
||||
configPath: scriptedConfigPath,
|
||||
prepare: seedWorkspace({
|
||||
skills: {
|
||||
'scripted-skill/SKILL.md': [
|
||||
'---',
|
||||
'name: scripted-skill',
|
||||
'description: Keyless PTY proof that the skill command loads a local skill into the conversation.',
|
||||
'disable-model-invocation: true',
|
||||
'---',
|
||||
'',
|
||||
'SCRIPTED SKILL BODY MARKER',
|
||||
'',
|
||||
].join('\n'),
|
||||
},
|
||||
}),
|
||||
actions: [
|
||||
...SELECT_PRO_MODEL,
|
||||
{ waitFor: 'Model selected: tui-scripted/tui-scripted-model-pro.', send: '/skill:scripted-skill\r' },
|
||||
{ waitFor: 'Scripted skill body received.', send: '/exit\r' },
|
||||
],
|
||||
})
|
||||
expect(output).not.toContain('[instructions]')
|
||||
expect(output).toContain('Scripted skill body received.')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('adds a watched local skill to live /skill: autocomplete without restarting', async () => {
|
||||
const skill = [
|
||||
'---',
|
||||
'name: hot-added-skill',
|
||||
'description: HOT_ADDED_COMPLETION_MARKER',
|
||||
'---',
|
||||
'',
|
||||
'Hot-added body.',
|
||||
'',
|
||||
].join('\n')
|
||||
const output = await smoke({
|
||||
label: 'tui-agent hot-added skill autocomplete',
|
||||
tempDirPrefix: 'tui-agent-hot-skill-',
|
||||
configPath: scriptedConfigPath,
|
||||
actions: [
|
||||
{
|
||||
waitFor: 'scripted TUI ready.',
|
||||
writeFile: {
|
||||
path: '.agents/skills/hot-added-skill/SKILL.md',
|
||||
content: skill,
|
||||
},
|
||||
send: '/skill:hot',
|
||||
},
|
||||
{ waitFor: 'HOT_ADDED_COMPLETION_MARKER', send: '\x03/exit\r' },
|
||||
],
|
||||
})
|
||||
expect(output).toContain('HOT_ADDED_COMPLETION_MARKER')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it.skipIf(process.env.DSH_EXAMPLE_MODE === 'lib')('fuzzy-completes an @file path without reading or submitting the file', async () => {
|
||||
const output = await smoke({
|
||||
label: 'dsh file autocomplete',
|
||||
tempDirPrefix: 'dsh-tui-file-autocomplete-',
|
||||
// Source-plane PTY coverage complements the deterministic package-level
|
||||
// autocomplete tests. Artifact CI omits this timing-sensitive terminal
|
||||
// rendering assertion; built boot is covered by the neighboring cases.
|
||||
configArgs: [],
|
||||
prepare: seedWorkspace({
|
||||
workspace: {
|
||||
'src/terminal-special-case.ts': 'export const marker = true\n',
|
||||
'src/other.ts': 'export const other = true\n',
|
||||
},
|
||||
}),
|
||||
actions: [
|
||||
{ waitFor: 'main-session-', send: '@tsc' },
|
||||
{ waitFor: 'File · terminal-special-case.t', send: '\t' },
|
||||
{ waitFor: '@src/terminal-special-case.ts', send: '\x03/exit\r' },
|
||||
],
|
||||
})
|
||||
expect(output).toContain('File · terminal-special-case.t')
|
||||
expect(output).toContain('@src/terminal-special-case.ts')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
})
|
||||
|
||||
describe('dsh CLI keyless smoke (apps/cli through the same PTY)', () => {
|
||||
it('exec-replaces the TUI for /resume and restores the same session state', async () => {
|
||||
const output = await smoke({
|
||||
label: 'dsh in-place resume',
|
||||
tempDirPrefix: 'dsh-in-place-resume-',
|
||||
binScript: dshBinScript,
|
||||
configPath: scriptedConfigPath,
|
||||
prepare: seedResumeSession,
|
||||
actions: [
|
||||
{ waitFor: 'scripted TUI ready.', send: '/resume\r' },
|
||||
{ waitFor: 'Resume selector design', send: 'Resume selector design' },
|
||||
{ waitFor: '⌕ Resume selector design', send: '\r' },
|
||||
{ waitFor: 'Preserve restored state', send: '/exit\r' },
|
||||
],
|
||||
})
|
||||
const released = output.indexOf('\u001B[?2004l')
|
||||
const restored = output.indexOf('Resume selector design — DeepSeek Harness')
|
||||
expect(released).toBeGreaterThanOrEqual(0)
|
||||
expect(restored).toBeGreaterThan(released)
|
||||
expect(output).toContain('Preserve restored state')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('boots the shipped default config with no arguments and no personal overlay', async () => {
|
||||
const output = await smoke({
|
||||
label: 'dsh default boot',
|
||||
tempDirPrefix: 'dsh-default-boot-',
|
||||
binScript: dshBinScript,
|
||||
configArgs: [],
|
||||
actions: [{ waitFor: 'main-session-', send: '/exit\r' }],
|
||||
})
|
||||
expect(output).toContain('DEEPSEEK')
|
||||
expect(output).toContain('main-session-')
|
||||
expect(output).not.toContain('╭')
|
||||
expect(output).not.toContain('╮')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('applies the personal overlay: config.yaml patches an overlay-inserted row, the invoking directory\'s .env feeds its !!js, and the home .env stays out of the environment', async () => {
|
||||
// The whole personal-config chain in one boot, plus the environment layer
|
||||
// it deliberately excludes. config.yaml patches the `tui` row — a row the
|
||||
// SURFACE OVERLAY inserted, not one the base declares — proving a later
|
||||
// patch list reaches a row an earlier one inserted. The single `!!js`
|
||||
// expression prefers the PERSONAL variable, so the welcome can only render
|
||||
// the project value while the harness home's .env — the credential store
|
||||
// of `dsh-credentials-local` — is NOT hoisted into `process.env`; hoisting
|
||||
// it would make every stored key read as a read-only launch override on
|
||||
// the next run and hand it to every subprocess the agent starts.
|
||||
const output = await smoke({
|
||||
label: 'dsh personal overlay',
|
||||
tempDirPrefix: 'dsh-personal-overlay-',
|
||||
binScript: dshBinScript,
|
||||
configArgs: [],
|
||||
prepare: seedWorkspace({
|
||||
workspace: { '.env': 'DSH_PROJECT_WELCOME=PROJECT OVERLAY READY.\n' },
|
||||
personal: {
|
||||
'.env': 'DSH_PERSONAL_WELCOME=HOME ENV LEAKED.\n',
|
||||
'config.yaml': [
|
||||
'- id: workspace-context',
|
||||
' disabled: true',
|
||||
'- id: tui',
|
||||
' config:',
|
||||
" sessionId: !!js configuredAgentIdentities?.main?.id ?? 'main'",
|
||||
' welcome: !!js process.env.DSH_PERSONAL_WELCOME ?? process.env.DSH_PROJECT_WELCOME',
|
||||
'',
|
||||
].join('\n'),
|
||||
},
|
||||
}),
|
||||
actions: [{ waitFor: 'PROJECT OVERLAY READY.', send: '/exit\r' }],
|
||||
})
|
||||
expect(output).toContain('PROJECT OVERLAY READY.')
|
||||
expect(output).not.toContain('HOME ENV LEAKED.')
|
||||
expect(output).toContain('\u001B[?2004l')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('fails loud instead of booting when the personal config.yaml is invalid', async () => {
|
||||
const output = await smoke({
|
||||
label: 'dsh invalid personal config',
|
||||
tempDirPrefix: 'dsh-invalid-personal-',
|
||||
binScript: dshBinScript,
|
||||
configArgs: [],
|
||||
prepare: seedWorkspace({ personal: { 'config.yaml': 'id: not-a-list\n' } }),
|
||||
expectedExitCode: 1,
|
||||
})
|
||||
expect(output).toContain('must be a top-level YAML array of loader patch entries')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('routes the --resume flag into the launcher session-identity slot, failing loud on a missing id', async () => {
|
||||
// The flag path end to end: apps/cli parses `--resume missing-session`,
|
||||
// provides it as the launcher-owned identity on the boot context, and the
|
||||
// resume fails loud — proving the printed hint reaches the app's resume
|
||||
// intake with no config key and no environment variable.
|
||||
const output = await smoke({
|
||||
label: 'dsh resume flag failure',
|
||||
tempDirPrefix: 'dsh-resume-flag-',
|
||||
binScript: dshBinScript,
|
||||
configArgs: ['--resume', 'missing-session'],
|
||||
expectedExitCode: 1,
|
||||
})
|
||||
expect(output).toContain('ui-tui: session "missing-session" failed to start:')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('prints the launcher-owned resume command on exit, naming the booted config', async () => {
|
||||
// The exit line is built by apps/cli from this invocation, so it must carry
|
||||
// `--config`: a hint that omitted it would resume into the default tree.
|
||||
const output = await smoke({
|
||||
label: 'dsh goodbye message',
|
||||
tempDirPrefix: 'dsh-goodbye-',
|
||||
binScript: dshBinScript,
|
||||
configPath: scriptedConfigPath,
|
||||
actions: [{ waitFor: 'scripted TUI ready.', send: '/exit\r' }],
|
||||
})
|
||||
expect(output).toMatch(/To resume this session: dsh --resume=main-session-[0-9a-f-]{36} --config/)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('keeps resume working when the personal overlay replaces the whole agent-loop config', async () => {
|
||||
// Loader patches replace a targeted `config` key wholesale, so a personal
|
||||
// overlay repointing the model route drops every identity key the shipped
|
||||
// row declared. Launcher-owned identity makes that unreachable: agent-loop
|
||||
// applies the launcher's id over whatever route survives.
|
||||
const output = await smoke({
|
||||
label: 'dsh overlay keeps resume',
|
||||
tempDirPrefix: 'dsh-overlay-resume-',
|
||||
binScript: dshBinScript,
|
||||
configArgs: [],
|
||||
prepare: seedWorkspace({
|
||||
personal: {
|
||||
'config.yaml': [
|
||||
'- id: workspace-context',
|
||||
' disabled: true',
|
||||
'- id: agent-loop',
|
||||
' config:',
|
||||
' agents:',
|
||||
' - id: main',
|
||||
' provider: deepseek',
|
||||
' model: deepseek-v4-flash',
|
||||
' cwd: !!js process.cwd()',
|
||||
'- id: tui',
|
||||
' config:',
|
||||
" sessionId: !!js configuredAgentIdentities?.main?.id ?? 'main'",
|
||||
' welcome: OVERLAY REPLACED THE CONFIG.',
|
||||
'',
|
||||
].join('\n'),
|
||||
},
|
||||
}),
|
||||
actions: [{ waitFor: 'OVERLAY REPLACED THE CONFIG.', send: '/exit\r' }],
|
||||
})
|
||||
expect(output).toMatch(/To resume this session: dsh --resume=main-session-[0-9a-f-]{36}/)
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('reports a failing bash command exactly once, as the terminal card exit pill', async () => {
|
||||
// The model-facing result ends in `[exit code: 3]`, which the terminal card
|
||||
// consumes into its own `[exit 3]` pill. Rendering both would report the same
|
||||
// exit twice, so the marker must not survive into the card body.
|
||||
const output = await smoke({
|
||||
label: 'dsh bash exit pill',
|
||||
tempDirPrefix: 'dsh-bash-exit-pill-',
|
||||
configPath: scriptedConfigPath,
|
||||
actions: [
|
||||
...SELECT_PRO_MODEL,
|
||||
{
|
||||
waitFor: 'Model selected: tui-scripted/tui-scripted-model-pro.',
|
||||
send: 'Run the failing scripted command.\r',
|
||||
},
|
||||
{ waitFor: 'Scripted bash failure observed.', send: '/exit\r' },
|
||||
],
|
||||
})
|
||||
// The command really ran: its stdout is in the card body.
|
||||
expect(output).toContain('SCRIPTED_BASH_FAILED')
|
||||
expect(output).toContain('[exit 3]')
|
||||
expect(output).not.toContain('[exit code: 3]')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
|
||||
it('tells the model its source path and offers the bundled maintenance skills', async () => {
|
||||
// The launcher resolves the checkout root three hops up from apps/cli/{src,lib};
|
||||
// this test file sits an equal depth under the same root, so the same hop applies.
|
||||
// The source-path line is a system-prompt section; the bundled skills reach the
|
||||
// model through a durable user message, so each assertion targets its own field.
|
||||
const sourceRoot = fileURLToPath(new URL('../../..', import.meta.url))
|
||||
let context: LoggedRequestContext = { system: '', skillCatalog: '' }
|
||||
await smoke({
|
||||
label: 'dsh source-path prompt',
|
||||
tempDirPrefix: 'dsh-source-path-',
|
||||
binScript: dshBinScript,
|
||||
configPath: scriptedConfigPath,
|
||||
actions: [
|
||||
...SELECT_PRO_MODEL,
|
||||
{ waitFor: 'Model selected: tui-scripted/tui-scripted-model-pro.', send: 'exercise the TUI\r' },
|
||||
{ waitFor: 'How should the scripted run proceed?', send: '\r' },
|
||||
{ waitFor: 'Decision received. Scripted TUI run complete.', send: '/exit\r' },
|
||||
],
|
||||
inspect: async (cwd) => { context = await readLoggedRequestContext(cwd) },
|
||||
})
|
||||
expect(context.system).toContain(`Your own source code is the checkout at ${sourceRoot}; you can read it there to learn how dsh works and how to extend it.`)
|
||||
expect(context.skillCatalog).toContain("- `dsh-customize`: Customize or maintain any dsh source checkout — the one powering the current DSH process, the installed `dsh` command, or a sibling dsh/deepseek-harness clone. Use before any requested action that alters such a checkout's files or git state. Read-only questions that only inspect the checkout do not trigger this. Do not edit the personal staging checkout directly.")
|
||||
expect(context.skillCatalog).toContain('- `dsh-upgrade`: Upgrades a source-installed, personally customized DSH checkout to upstream master while preserving local changes and an unchanged rollback worktree. Use when the user asks to update or upgrade DSH.')
|
||||
expect(context.skillCatalog).toContain('- `dsh-upstream-customization`: Classifies personal DSH customizations for upstream contribution and, after explicit per-feature approval, rebuilds one on upstream master and opens a draft pull request. Use when the user asks to contribute, publish, or upstream a local DSH change, or asks whether one is worth proposing.')
|
||||
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
|
||||
})
|
||||
536
apps/cli/tests/tui.snapshot.ts
Normal file
536
apps/cli/tests/tui.snapshot.ts
Normal file
@@ -0,0 +1,536 @@
|
||||
import { cp, mkdir, mkdtemp, readFile, readdir, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { basename, dirname, isAbsolute, join, relative, sep } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { scrubRequestHeaders, tokenizeSessionFixtureCwd } from '@deepseek-ai/dsh-acp-snapshot'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import * as AgentCore from '@deepseek-ai/dsh-agent-spine-demo'
|
||||
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
||||
import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
|
||||
import WorkerCodeRuntime from '@deepseek-ai/dsh-code-runtime-worker'
|
||||
import CommandService from '@deepseek-ai/dsh-commands'
|
||||
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
|
||||
import * as FsPolicy from '@deepseek-ai/dsh-fs-policy'
|
||||
import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { installLlmReplay, parseSessionLog } from '@deepseek-ai/dsh-llm-replay'
|
||||
import PlanModeService from '@deepseek-ai/dsh-plan-mode'
|
||||
import TokenMeterService from '@deepseek-ai/dsh-token-meter'
|
||||
import { packChunkRuns, SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import SubagentService from '@deepseek-ai/dsh-subagent'
|
||||
import * as SubagentSpawn from '@deepseek-ai/dsh-subagent-spawn'
|
||||
import * as ToolSubagent from '@deepseek-ai/dsh-tool-subagent'
|
||||
import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
import * as ToolRalph from '@deepseek-ai/dsh-tool-ralph'
|
||||
import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow'
|
||||
import { createTuiChat, FILE_REFERENCE_PROMPT, TuiPromptService } from '@deepseek-ai/dsh-tui'
|
||||
import LocalSpillStore from '@deepseek-ai/dsh-spill-local'
|
||||
import * as SpillPolicy from '@deepseek-ai/dsh-spill-policy'
|
||||
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
|
||||
import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread'
|
||||
import { HeadlessTerminal } from '../../../packages/ui/tui/tests/headless-terminal.ts'
|
||||
|
||||
const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
|
||||
// Keep pre-normalization layout widths identical across macOS and Linux.
|
||||
const SNAPSHOT_TMP_ROOT = process.platform === 'win32' ? tmpdir() : '/tmp'
|
||||
const PROVIDERS = [{ id: 'deepseek', models: [{ id: 'deepseek-v4-flash', contextWindow: 128_000 }] }]
|
||||
const UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi
|
||||
|
||||
type SnapshotMode = 'replay' | 'record' | 'refresh'
|
||||
type Composition = 'native' | 'code' | 'advanced'
|
||||
type ScenarioInteraction = 'skill-invocation-policy'
|
||||
|
||||
interface Scenario {
|
||||
name: string
|
||||
composition: Composition
|
||||
expectedTools: string[]
|
||||
expectedEventCounts?: Record<string, number>
|
||||
childSessions?: number
|
||||
enterPlanMode?: boolean
|
||||
leavePlanModeAfterFirstTurn?: boolean
|
||||
recorded: boolean
|
||||
seedWorkspace?: boolean
|
||||
/**
|
||||
* Load the opt-in `todo_write` tool for this scenario. The shipped TUI
|
||||
* config omits it, so only the todo-plan scenario (the enabled-path proof)
|
||||
* mounts it; the rest cover the default, todo-free composition.
|
||||
*/
|
||||
enableTodo?: boolean
|
||||
/**
|
||||
* Mount the spill stack (local backend + policy) with this inline cap, as the
|
||||
* shipped configs do. The dispatch-spill scenario proves the durable
|
||||
* `tool/code-dispatch` copy of an oversized sub-result is bounded to a
|
||||
* preview + locator while the program value stays whole.
|
||||
*/
|
||||
spillMaxInlineBytes?: number
|
||||
/** Run scenario-specific terminal input instead of replaying recorded user prompts. */
|
||||
interaction?: ScenarioInteraction
|
||||
}
|
||||
|
||||
const SCENARIOS: Scenario[] = [
|
||||
{
|
||||
name: 'multi-turn-conversation',
|
||||
composition: 'native',
|
||||
expectedTools: [],
|
||||
expectedEventCounts: { 'plan/mode': 2 },
|
||||
enterPlanMode: true,
|
||||
leavePlanModeAfterFirstTurn: true,
|
||||
recorded: true,
|
||||
},
|
||||
{
|
||||
name: 'todo-plan',
|
||||
composition: 'native',
|
||||
expectedTools: ['todo_write'],
|
||||
expectedEventCounts: { 'todo/write': 1 },
|
||||
recorded: true,
|
||||
enableTodo: true,
|
||||
},
|
||||
{
|
||||
name: 'bash-terminal-card',
|
||||
composition: 'native',
|
||||
expectedTools: ['bash'],
|
||||
recorded: true,
|
||||
},
|
||||
{
|
||||
name: 'parallel-file-reads',
|
||||
composition: 'native',
|
||||
expectedTools: ['read', 'read'],
|
||||
recorded: true,
|
||||
seedWorkspace: true,
|
||||
},
|
||||
{
|
||||
name: 'skill-invocation-policy',
|
||||
composition: 'native',
|
||||
expectedTools: [],
|
||||
recorded: false,
|
||||
seedWorkspace: true,
|
||||
interaction: 'skill-invocation-policy',
|
||||
},
|
||||
{
|
||||
name: 'code-mode',
|
||||
composition: 'code',
|
||||
expectedTools: ['run_code'],
|
||||
expectedEventCounts: { 'tool/code-dispatch': 2 },
|
||||
recorded: true,
|
||||
},
|
||||
{
|
||||
name: 'code-mode-dispatch-spill',
|
||||
composition: 'code',
|
||||
expectedTools: ['run_code'],
|
||||
expectedEventCounts: { 'tool/code-dispatch-start': 1, 'tool/code-dispatch': 1 },
|
||||
recorded: true,
|
||||
spillMaxInlineBytes: 600,
|
||||
},
|
||||
{
|
||||
name: 'dynamic-workflow',
|
||||
composition: 'native',
|
||||
expectedTools: ['workflow'],
|
||||
childSessions: 1,
|
||||
recorded: true,
|
||||
},
|
||||
{
|
||||
name: 'cordis-dynamic-toolchain',
|
||||
composition: 'advanced',
|
||||
expectedTools: ['cordis_mount', 'run_code', 'subagent', 'workflow', 'cordis_unmount'],
|
||||
expectedEventCounts: { 'tool/code-dispatch': 1 },
|
||||
childSessions: 2,
|
||||
recorded: false,
|
||||
},
|
||||
]
|
||||
|
||||
function snapshotModeFromEnv(value: string | undefined): SnapshotMode {
|
||||
if (value === undefined || value === '' || value === 'replay') return 'replay'
|
||||
if (value === 'record' || value === 'refresh') return value
|
||||
throw new Error(`DSH_SNAPSHOT must be replay, record, or refresh; got ${JSON.stringify(value)}`)
|
||||
}
|
||||
|
||||
const MODE = snapshotModeFromEnv(process.env.DSH_SNAPSHOT)
|
||||
const observedScenarios = new Set<string>()
|
||||
|
||||
function snapshotDisplayPath(displayPath: string, cwd: string, displayCwd: string): string {
|
||||
const rel = relative(cwd, displayPath)
|
||||
if (rel === '') return displayCwd
|
||||
if (isAbsolute(rel) || rel === '..' || rel.startsWith(`..${sep}`)) return displayPath
|
||||
return `${displayCwd}/${rel.split(sep).join('/')}`
|
||||
}
|
||||
|
||||
function scenarioDir(scenario: Scenario): string {
|
||||
return join(SNAPSHOTS_DIR, scenario.name)
|
||||
}
|
||||
|
||||
function childFixturePaths(scenario: Scenario): string[] {
|
||||
return Array.from(
|
||||
{ length: scenario.childSessions ?? 0 },
|
||||
(_, index) => join(scenarioDir(scenario), `session.${index + 1}.jsonl`),
|
||||
)
|
||||
}
|
||||
|
||||
function userPrompts(rawLog: string): string[] {
|
||||
return parseSessionLog(rawLog).flatMap((event) => {
|
||||
if (event.type !== 'user/message' || event.data.source.kind !== 'user') return []
|
||||
const text = event.data.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
return text.length > 0 ? [text] : []
|
||||
})
|
||||
}
|
||||
|
||||
function rawSessionLog(session: Session): string {
|
||||
return [
|
||||
JSON.stringify({ type: 'session', ...session.header }),
|
||||
...packChunkRuns(session.events).map(record => JSON.stringify(record)),
|
||||
'',
|
||||
].join('\n')
|
||||
}
|
||||
|
||||
function normalizeTerminalSnapshot(snapshot: string, cwd: string, displayCwd: string): string {
|
||||
return snapshot
|
||||
.split(`/private${cwd}`).join('/workspace/project')
|
||||
.split(displayCwd).join('/workspace/project')
|
||||
.split(cwd).join('/workspace/project')
|
||||
.replace(UUID_RE, '{{uuid}}')
|
||||
}
|
||||
|
||||
async function settleTerminal(terminal: HeadlessTerminal): Promise<void> {
|
||||
let stable = 0
|
||||
for (let attempt = 0; attempt < 20 && stable < 3; attempt++) {
|
||||
const before = terminal.frames
|
||||
await new Promise(resolve => setTimeout(resolve, 10))
|
||||
await terminal.flush()
|
||||
stable = terminal.frames === before ? stable + 1 : 0
|
||||
}
|
||||
if (stable < 3) throw new Error('TUI frames did not quiesce within 200ms')
|
||||
}
|
||||
|
||||
async function mountScenarioContext(
|
||||
scenario: Scenario,
|
||||
cwd: string,
|
||||
displayCwd: string,
|
||||
fixtureFile: string,
|
||||
childFiles: string[],
|
||||
): Promise<Context> {
|
||||
class SnapshotLocalFileSystem extends LocalFileSystem {
|
||||
override async resolve(
|
||||
path: string,
|
||||
opts?: { cwd?: string; signal?: AbortSignal },
|
||||
): Promise<Awaited<ReturnType<LocalFileSystem['resolve']>>> {
|
||||
const target = await super.resolve(path, opts)
|
||||
return { ...target, displayPath: snapshotDisplayPath(target.displayPath, cwd, displayCwd) }
|
||||
}
|
||||
}
|
||||
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(AgentCore, {
|
||||
agents: [],
|
||||
dshHome: join(cwd, '.dsh'),
|
||||
workspaceContext: false,
|
||||
tools: { mode: scenario.composition === 'code' ? 'code' : scenario.composition === 'advanced' ? 'both' : 'native' },
|
||||
skills: { local: { agentsHome: join(cwd, '.agents') } },
|
||||
})
|
||||
await ctx.plugin(TokenMeterService)
|
||||
await ctx.plugin(LocalSubprocessService)
|
||||
await ctx.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
|
||||
await ctx.plugin(SnapshotLocalFileSystem, { cwd: '/' })
|
||||
await ctx.plugin(FsPolicy)
|
||||
await ctx.plugin(ToolFs)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(TuiPromptService)
|
||||
// todo_write is opt-in: only the todo-plan scenario mounts it, matching the shipped
|
||||
// config that omits it. The other scenarios prove the default todo-free composition.
|
||||
if (scenario.enableTodo === true) await ctx.plugin(ToolTodo)
|
||||
await ctx.plugin(SubagentService)
|
||||
await ctx.plugin(SubagentSpawn, { providerName: 'spawn' })
|
||||
await ctx.plugin(ToolSubagent, { provider: 'spawn', toolName: 'subagent', enableRunInBackground: false })
|
||||
await ctx.plugin(WorkerWorkflowEngine, { provider: 'spawn' })
|
||||
await ctx.plugin(ToolWorkflow)
|
||||
await ctx.plugin(ToolRalph)
|
||||
await ctx.plugin(CommandService)
|
||||
if (scenario.enterPlanMode === true) {
|
||||
await ctx.plugin(PlanModeService, { section: 'Snapshot plan mode instructions.' })
|
||||
}
|
||||
if (scenario.composition === 'code' || scenario.composition === 'advanced') {
|
||||
await ctx.plugin(WorkerCodeRuntime, {})
|
||||
}
|
||||
if (scenario.spillMaxInlineBytes !== undefined) {
|
||||
await ctx.plugin(LocalSpillStore, { root: join(cwd, '.spill') })
|
||||
await ctx.plugin(SpillPolicy, { maxInlineBytes: scenario.spillMaxInlineBytes })
|
||||
}
|
||||
if (scenario.composition === 'advanced') await ctx.plugin(ToolCordis, { vmTimeoutMs: 5_000 })
|
||||
if (MODE === 'record' && scenario.recorded) {
|
||||
await ctx.plugin(LlmDeepSeek)
|
||||
} else {
|
||||
installLlmReplay(ctx, { file: fixtureFile, childFiles, providers: PROVIDERS })
|
||||
}
|
||||
return ctx
|
||||
}
|
||||
|
||||
interface ScenarioResult {
|
||||
terminal: string
|
||||
parent: Session
|
||||
children: Session[]
|
||||
workflowEvents: string[]
|
||||
}
|
||||
|
||||
async function runScenario(scenario: Scenario): Promise<ScenarioResult> {
|
||||
const clock = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 12, 0, 0).getTime())
|
||||
const dir = scenarioDir(scenario)
|
||||
const fixtureFile = join(dir, 'session.jsonl')
|
||||
const childFiles = childFixturePaths(scenario)
|
||||
const prompts = userPrompts(await readFile(fixtureFile, 'utf8'))
|
||||
if (scenario.interaction === undefined) {
|
||||
expect(prompts.length, `${scenario.name} must carry at least one recorded user prompt`).toBeGreaterThan(0)
|
||||
}
|
||||
|
||||
const cwd = await mkdtemp(join(SNAPSHOT_TMP_ROOT, `dsh-tui-snapshot-${scenario.name}-`))
|
||||
const displayCwd = `/tmp/${basename(cwd)}`
|
||||
let ctx: Context | undefined
|
||||
let controller: ReturnType<typeof createTuiChat> | undefined
|
||||
const terminal = new HeadlessTerminal(100, 36)
|
||||
try {
|
||||
if (scenario.seedWorkspace === true) {
|
||||
const source = join(scenarioDir(scenario), 'workspace')
|
||||
await cp(source, cwd, { recursive: true })
|
||||
}
|
||||
ctx = await mountScenarioContext(scenario, cwd, displayCwd, fixtureFile, childFiles)
|
||||
const disposedSessions: Session[] = []
|
||||
ctx.on('session/disposed', (session) => { disposedSessions.push(session) })
|
||||
const workflowEvents: string[] = []
|
||||
for (const name of ['workflow/start', 'workflow/phase', 'workflow/agent-start', 'workflow/agent-end', 'workflow/end'] as const) {
|
||||
ctx.on(name, () => { workflowEvents.push(name) })
|
||||
}
|
||||
const handle = await ctx.agents.create({
|
||||
sessionId: SessionId('main-session'),
|
||||
meta: { cwd },
|
||||
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
|
||||
})
|
||||
const agent: Agent = handle.agent
|
||||
controller = createTuiChat(ctx, {
|
||||
sessionId: 'main-session',
|
||||
theme: { color: true },
|
||||
showReasoning: true,
|
||||
title: 'DSH TUI snapshot',
|
||||
welcome: `Recorded replay: ${scenario.name}`,
|
||||
maxToolOutputLines: 8,
|
||||
}, {
|
||||
terminal,
|
||||
exit: () => {},
|
||||
formatCwd: () => displayCwd,
|
||||
})
|
||||
await settleTerminal(terminal)
|
||||
|
||||
let interactionSnapshot: string | undefined
|
||||
if (scenario.interaction === 'skill-invocation-policy') {
|
||||
terminal.send('/skill')
|
||||
await settleTerminal(terminal)
|
||||
const discovery = normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
expect(discovery).toContain('user-only-skill')
|
||||
expect(discovery).not.toContain('model-only-skill')
|
||||
|
||||
terminal.send('\x03')
|
||||
await settleTerminal(terminal)
|
||||
const skillContext = ctx
|
||||
const skillTurnEnded = new Promise<void>((resolve) => {
|
||||
const detach = skillContext.on('session/event', (session, event) => {
|
||||
if (session !== agent.session || event.type !== 'turn/end') return
|
||||
detach()
|
||||
resolve()
|
||||
})
|
||||
})
|
||||
terminal.send('/skill:user-only-skill')
|
||||
terminal.send('\r')
|
||||
await skillTurnEnded
|
||||
await agent.whenIdle()
|
||||
await settleTerminal(terminal)
|
||||
const loaded = normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
expect(loaded).toContain('USER-ONLY SKILL LOADED')
|
||||
|
||||
terminal.send('/skill:model-only-skill')
|
||||
terminal.send('\r')
|
||||
await settleTerminal(terminal)
|
||||
const denied = normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
expect(denied).toContain('model-only-skill')
|
||||
expect(denied).toContain('not available for user invocation.')
|
||||
expect(denied).not.toContain('MODEL-ONLY BODY MUST NOT LOAD')
|
||||
interactionSnapshot = [
|
||||
'=== skill autocomplete ===',
|
||||
discovery,
|
||||
'',
|
||||
'=== loaded exact invocation ===',
|
||||
loaded,
|
||||
'',
|
||||
'=== denied exact invocation ===',
|
||||
denied,
|
||||
].join('\n')
|
||||
}
|
||||
|
||||
let remainingPrompts = prompts
|
||||
if (scenario.enterPlanMode === true) {
|
||||
const firstPrompt = prompts[0]!
|
||||
terminal.send(`/plan ${firstPrompt}`)
|
||||
terminal.send('\r')
|
||||
await agent.whenIdle()
|
||||
await settleTerminal(terminal)
|
||||
remainingPrompts = prompts.slice(1)
|
||||
}
|
||||
|
||||
if (scenario.leavePlanModeAfterFirstTurn === true) {
|
||||
terminal.send('/plan off')
|
||||
terminal.send('\r')
|
||||
await settleTerminal(terminal)
|
||||
}
|
||||
|
||||
for (const prompt of remainingPrompts) {
|
||||
terminal.send(prompt)
|
||||
terminal.send('\r')
|
||||
await agent.whenIdle()
|
||||
await settleTerminal(terminal)
|
||||
}
|
||||
|
||||
const events: SessionEvent[] = [...agent.session.events]
|
||||
const firstHeader = events.find(event => event.type === 'request/header')
|
||||
expect(firstHeader?.type === 'request/header' && firstHeader.data.header.system)
|
||||
.toContain(FILE_REFERENCE_PROMPT)
|
||||
expect(events.filter(event => event.type === 'tool/call').map(event => event.data.name)).toEqual(scenario.expectedTools)
|
||||
for (const [type, count] of Object.entries(scenario.expectedEventCounts ?? {})) {
|
||||
expect(events.filter(event => event.type === type), `${scenario.name} must emit ${type}`).toHaveLength(count)
|
||||
}
|
||||
if (scenario.enterPlanMode === true) {
|
||||
expect(ctx.planMode.get(agent)).toEqual({
|
||||
active: scenario.leavePlanModeAfterFirstTurn !== true,
|
||||
})
|
||||
const planMode = events.find(event => event.type === 'plan/mode')
|
||||
if (planMode === undefined || firstHeader === undefined) {
|
||||
throw new Error('plan-mode command snapshot needs plan/mode before its first request/header')
|
||||
}
|
||||
expect(planMode.seq).toBeLessThan(firstHeader.seq)
|
||||
expect(firstHeader.data.header.system).toContain('Snapshot plan mode instructions.')
|
||||
const firstMessage = events.find(event => event.type === 'user/message')
|
||||
expect(firstMessage?.data.content).toEqual([{ type: 'text', text: prompts[0] }])
|
||||
}
|
||||
if (scenario.leavePlanModeAfterFirstTurn === true) {
|
||||
const planModes = events.filter(event => event.type === 'plan/mode')
|
||||
expect(planModes.map(event => event.data.active)).toEqual([true, false])
|
||||
const headers = events.filter(event => event.type === 'request/header')
|
||||
const exit = planModes[1]
|
||||
const afterExit = headers[1]
|
||||
if (exit === undefined || afterExit === undefined) {
|
||||
throw new Error('active plan exit snapshot needs a committed exit and changed request header')
|
||||
}
|
||||
expect(exit.seq).toBeLessThan(afterExit.seq)
|
||||
expect(afterExit.data.header.system).not.toContain('Snapshot plan mode instructions.')
|
||||
expect(events.filter(event => event.type === 'user/message' && event.data.source.kind === 'plugin').map(event => (event.data as { content: unknown }).content))
|
||||
.toContainEqual([{ type: 'text', text: 'The user switched this session back to the default mode.' }])
|
||||
}
|
||||
if (scenario.spillMaxInlineBytes !== undefined) {
|
||||
// The REAL pipeline ran (tools execute on replay too): the durable
|
||||
// dispatch copy is bounded to a preview + locator under the run cwd,
|
||||
// while the outer result still carries the program's whole value.
|
||||
const dispatch = events.find(event => (event.type as string) === 'tool/code-dispatch')
|
||||
const content = (dispatch?.data as { content: { type: string; text?: string }[] }).content
|
||||
const text = content.filter(block => block.type === 'text').map(block => block.text ?? '').join('')
|
||||
expect(Buffer.byteLength(text, 'utf8')).toBeLessThanOrEqual(scenario.spillMaxInlineBytes)
|
||||
expect(text).toContain('Full formatted result stored at:')
|
||||
expect(text).toContain('.spill')
|
||||
}
|
||||
expect(events.filter(event => event.type === 'tool/result').every(event => !event.data.message.content[0].isError)).toBe(true)
|
||||
expect(events.filter(event => event.type === 'turn/end').every(event => event.data.reason.kind !== 'error')).toBe(true)
|
||||
if (scenario.name === 'dynamic-workflow' || scenario.name === 'cordis-dynamic-toolchain') {
|
||||
expect(workflowEvents).toEqual([
|
||||
'workflow/start',
|
||||
'workflow/phase',
|
||||
'workflow/agent-start',
|
||||
'workflow/agent-end',
|
||||
'workflow/end',
|
||||
])
|
||||
}
|
||||
|
||||
expect(terminal.themeViolations(), `${scenario.name} must remain theme-agnostic`).toEqual([])
|
||||
const snapshot = interactionSnapshot ?? normalizeTerminalSnapshot(
|
||||
await terminal.snapshot({ includeScrollback: true }),
|
||||
cwd,
|
||||
displayCwd,
|
||||
)
|
||||
await handle.dispose()
|
||||
const children = disposedSessions
|
||||
.filter(session => session !== agent.session)
|
||||
.sort((a, b) => a.header.createdAt - b.header.createdAt)
|
||||
expect(children).toHaveLength(scenario.childSessions ?? 0)
|
||||
return { terminal: snapshot, parent: agent.session, children, workflowEvents }
|
||||
} finally {
|
||||
await controller?.dispose()
|
||||
await ctx?.fiber.dispose()
|
||||
await terminal.dispose()
|
||||
await rm(cwd, { recursive: true, force: true })
|
||||
clock.mockRestore()
|
||||
}
|
||||
}
|
||||
|
||||
async function writeRecording(scenario: Scenario, result: ScenarioResult): Promise<void> {
|
||||
const dir = scenarioDir(scenario)
|
||||
await mkdir(dir, { recursive: true })
|
||||
await writeFile(
|
||||
join(dir, 'session.jsonl'),
|
||||
scrubRequestHeaders(tokenizeSessionFixtureCwd(rawSessionLog(result.parent))),
|
||||
)
|
||||
expect(result.children).toHaveLength(scenario.childSessions ?? 0)
|
||||
for (const [index, child] of result.children.entries()) {
|
||||
await writeFile(
|
||||
join(dir, `session.${index + 1}.jsonl`),
|
||||
scrubRequestHeaders(tokenizeSessionFixtureCwd(rawSessionLog(child))),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
describe('TUI recorded-session terminal snapshots', () => {
|
||||
for (const scenario of SCENARIOS) {
|
||||
it(scenario.name, async () => {
|
||||
observedScenarios.add(scenario.name)
|
||||
const result = await runScenario(scenario)
|
||||
const terminalFile = join(scenarioDir(scenario), 'terminal.expected.txt')
|
||||
if (MODE === 'record' || MODE === 'refresh') {
|
||||
await mkdir(scenarioDir(scenario), { recursive: true })
|
||||
await writeFile(terminalFile, result.terminal)
|
||||
}
|
||||
if (MODE === 'record' && scenario.recorded) await writeRecording(scenario, result)
|
||||
await expect(result.terminal).toMatchFileSnapshot(terminalFile)
|
||||
}, 120_000)
|
||||
}
|
||||
})
|
||||
|
||||
afterAll(async () => {
|
||||
expect([...observedScenarios].sort()).toEqual(SCENARIOS.map(scenario => scenario.name).sort())
|
||||
const directories = (await readdir(SNAPSHOTS_DIR, { withFileTypes: true }))
|
||||
.filter(entry => entry.isDirectory())
|
||||
.map(entry => entry.name)
|
||||
.sort()
|
||||
expect(directories).toEqual(SCENARIOS.map(scenario => scenario.name).sort())
|
||||
for (const scenario of SCENARIOS) {
|
||||
const expected = [
|
||||
'session.jsonl',
|
||||
'terminal.expected.txt',
|
||||
...scenario.seedWorkspace === true ? ['workspace'] : [],
|
||||
...Array.from({ length: scenario.childSessions ?? 0 }, (_, index) => `session.${index + 1}.jsonl`),
|
||||
].sort()
|
||||
expect((await readdir(scenarioDir(scenario))).sort()).toEqual(expected)
|
||||
for (const fixture of ['session.jsonl', ...childFixturePaths(scenario).map(path => basename(path))]) {
|
||||
const content = await readFile(join(scenarioDir(scenario), fixture), 'utf8')
|
||||
expect(scrubRequestHeaders(content), `${scenario.name}/${fixture} carries request-header bulk`).toBe(content)
|
||||
}
|
||||
}
|
||||
})
|
||||
Reference in New Issue
Block a user