mward4/deepseek-harness
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 29 Wiki Activity

refactor(tools): remove mixed tool presentation

Browse Source
This commit is contained in:
Tianyi Cui committed 2026-10-07 01:57:57 +08:00
1 parent e14182df7b
commit 4359d3ee17
117 files changed
+11266 -1569
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/gen-tool-catalog.ts
+1 -1
View File
@@ -252,7 +252,7 @@ const TOOL_PACKAGES: ToolPackage[] = [
toolsConfig: { mode: 'ptc' },
async mount() {},
note:
'Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: ptc` / `mode: both` (see the PTC mode Agent Note). Under `ptc` it is the registry\'s only wire contribution; the other visible capabilities are declared in a generated SDK section in the loaded runtime\'s language, and a program calls them through bindings scheduled under the native concurrency contract (submission-ordered starts and policy; concurrency-safe bodies overlap up to `maxParallelSubCalls`) that re-enter the complete guarded tool pipeline and link each nested execution to this outer result.',
'Owned by the tool registry as a reserved transport outside filterable capability layers under `mode: ptc` (see the PTC mode Agent Note). Under `ptc` it is the registry\'s only wire contribution; the other visible capabilities are declared in a generated SDK section in the loaded runtime\'s language, and a program calls them through bindings scheduled under the native concurrency contract (submission-ordered starts and policy; concurrency-safe bodies overlap up to `maxParallelSubCalls`) that re-enter the complete guarded tool pipeline and link each nested execution to this outer result.',
},
{
pkg: '@deepseek-ai/dsh-plan-mode',
scripts/session-snapshot-corpus-policy.spec.ts
+29 -20
View File
@@ -56,20 +56,28 @@ describe('recorded-session corpus policy', () => {
.toThrow('Session corpus lacks v3 coverage: adjacent-migration')
})
it('retains retired tools in the current format without claiming migration coverage', () => {
const retired = {
key: 'web/retired', selectedVersions: [SESSION_FORMAT_VERSION],
retained: { version: SESSION_FORMAT_VERSION, coverage: ['retired-tools'] as const },
}
expect(assertSnapshotCorpusPolicy([current, baseline, completeV0, ...adjacent, retired]).retainedScenarios)
.toBe(2 + adjacent.length)
expect(() => assertSnapshotCorpusPolicy([current, completeV0, retired]))
.toThrow('coverage: adjacent-migration')
expect(() => assertSnapshotCorpusPolicy([current, completeV0, ...adjacent, {
...retired, selectedVersions: [SESSION_FORMAT_VERSION + 1],
retained: { ...retired.retained, version: SESSION_FORMAT_VERSION + 1 },
}])).toThrow('retained Session format must precede')
})
it.each(['retired-tools', 'recorded-behavior'] as const)(
'retains %s independently from migration coverage', (reason) => {
const retired = {
key: 'web/retired', selectedVersions: [SESSION_FORMAT_VERSION],
retained: { version: SESSION_FORMAT_VERSION, coverage: [reason] },
}
expect(assertSnapshotCorpusPolicy([current, baseline, completeV0, ...adjacent, retired]).retainedScenarios)
.toBe(2 + adjacent.length)
expect(() => assertSnapshotCorpusPolicy([current, completeV0, retired]))
.toThrow('coverage: adjacent-migration')
expect(() => assertSnapshotCorpusPolicy([current, baseline, completeV0, adjacent[1]!, {
...retired, selectedVersions: [1], retained: { version: 1, coverage: [reason] },
}])).toThrow('Session corpus lacks v1 coverage: adjacent-migration')
expect(() => assertSnapshotCorpusPolicy([current, baseline, completeV0, ...adjacent, {
...retired, retained: { version: SESSION_FORMAT_VERSION, coverage: [reason, 'adjacent-migration'] },
}])).toThrow('retained Session format must precede')
expect(() => assertSnapshotCorpusPolicy([current, completeV0, ...adjacent, {
...retired, selectedVersions: [SESSION_FORMAT_VERSION + 1],
retained: { ...retired.retained, version: SESSION_FORMAT_VERSION + 1 },
}])).toThrow('retained Session format must precede')
},
)
it('requires v0 coverage from v0 fixtures', () => {
expect(() => assertSnapshotCorpusPolicy([baseline, ...adjacent]))
@@ -126,14 +134,15 @@ describe('recorded-session corpus policy', () => {
)
it('bounds explicitly retained roles and requires a baseline/current majority', () => {
const currentMajority = { ...current, selectedVersions: Array<number>(10).fill(SESSION_FORMAT_VERSION) }
expect(assertSnapshotCorpusPolicy([
baseline, current,
{ ...completeV0, selectedVersions: Array<number>(9).fill(0) }, ...adjacent,
]).retainedRoles).toBe(11)
baseline, currentMajority,
{ ...completeV0, selectedVersions: Array<number>(15).fill(0) }, ...adjacent,
]).retainedRoles).toBe(17)
expect(() => assertSnapshotCorpusPolicy([
baseline, current,
{ ...completeV0, selectedVersions: Array<number>(10).fill(0) }, ...adjacent,
])).toThrow('Session corpus retains 12 historical roles; maximum is 11')
baseline, currentMajority,
{ ...completeV0, selectedVersions: Array<number>(16).fill(0) }, ...adjacent,
])).toThrow('Session corpus retains 18 historical roles; maximum is 17')
expect(() => assertSnapshotCorpusPolicy([
{ ...baseline, selectedVersions: [3] }, completeV0, ...adjacent,
])).toThrow(`Session corpus requires a baseline/current majority; baseline=1, current=0, retained=${1 + adjacent.length}`)
scripts/session-snapshot-corpus-policy.ts
+6 -5
View File
@@ -22,7 +22,7 @@ export interface SnapshotCorpusGenerationSummary {
}
const RETAINED_BASELINE_VERSION = 3
const MAX_RETAINED_ROLES = 11
const MAX_RETAINED_ROLES = 17
const REQUIRED_V0_COVERAGE = new Set([
'multi-hop',
'packed-row',
@@ -71,13 +71,14 @@ export function assertSnapshotCorpusPolicy(
`${scenario.key}: selected Session generation v${mismatched} does not match expected v${expectedVersion}`,
)
}
const retiredTools = scenario.retained.coverage.length === 1 && scenario.retained.coverage[0] === 'retired-tools'
const nonMigration = scenario.retained.coverage.length === 1
&& (scenario.retained.coverage[0] === 'retired-tools' || scenario.retained.coverage[0] === 'recorded-behavior')
if (!Number.isSafeInteger(scenario.retained.version)
|| scenario.retained.version < 0 || scenario.retained.version > SESSION_FORMAT_VERSION
|| (scenario.retained.version === SESSION_FORMAT_VERSION && !retiredTools)) {
throw new Error(`${scenario.key}: retained Session format must precede current v${SESSION_FORMAT_VERSION} unless it pins retired tools at that version`)
|| (scenario.retained.version === SESSION_FORMAT_VERSION && !nonMigration)) {
throw new Error(`${scenario.key}: retained Session format must precede current v${SESSION_FORMAT_VERSION} unless it pins retired tools or recorded behavior at that version`)
}
const allowedCoverage = retiredTools ? new Set(['retired-tools']) : scenario.retained.version === 0
const allowedCoverage = nonMigration ? new Set(['retired-tools', 'recorded-behavior']) : scenario.retained.version === 0
? REQUIRED_V0_COVERAGE
: REQUIRED_ADJACENT_COVERAGE
if (scenario.retained.coverage.some(item => !allowedCoverage.has(item))) {
scripts/session-snapshot-corpus.corpus.ts
+2 -2
View File
@@ -205,7 +205,7 @@ it('keeps V3 replay input plus bounded declared historical migration coverage',
const summary = assertSnapshotCorpusPolicy(inventory)
expect(summary.baselineRoles).toBeGreaterThan(0)
expect(summary).toMatchObject({
retainedRoles: 11,
retainedScenarios: 8,
retainedRoles: 17,
retainedScenarios: 12,
})
})
scripts/smoke-python-runtime.py
+90 -68
View File
@@ -22,7 +22,7 @@ import time
import zipfile
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import TYPE_CHECKING, Callable
from typing import TYPE_CHECKING, Callable, Literal
if TYPE_CHECKING:
from deepseek_harness import Notification, RunResult
@@ -114,11 +114,9 @@ SNAPSHOT_WORKFLOW_SCRIPT = (
f"const reply = await agent('{SNAPSHOT_WORKFLOW_CHILD_PROMPT}', {{ label: 'workflow-child' }})\n"
"return { reply }"
)
ADVANCED_SNAPSHOT_DIRECTORY = (
Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe" / "advanced"
)
ADVANCED_SNAPSHOT_ROOT = Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe"
ADVANCED_SNAPSHOT_FILENAMES = (
"result.json", "session.v3.jsonl", "session.1.v3.jsonl", "session.2.v3.jsonl",
"result.json", "session.v4.jsonl", "session.1.v4.jsonl", "session.2.v4.jsonl",
)
MINIMAL_SNAPSHOT_DIRECTORY = (
Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe" / "minimal"
@@ -135,13 +133,13 @@ DYNAMIC_TOOLS_SNAPSHOT_DIRECTORY = (
)
DYNAMIC_TOOLS_SNAPSHOT_FILENAMES = ("tool-history.json",)
RESTART_SNAPSHOT_DIRECTORY = (
Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe" / "restart"
Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe" / "restart-native"
)
RESTART_SNAPSHOT_FILENAMES = (
"result.json", "requests.json", "session.1.v3.jsonl", "session.2.v3.jsonl",
"result.json", "requests.json", "session.1.v4.jsonl", "session.2.v4.jsonl",
)
RECOVERY_SNAPSHOT_DIRECTORY = (
Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe" / "scheduler-recovery"
Path(__file__).resolve().parent / "snapshots" / "python-sdk-single-exe" / "scheduler-recovery-native"
)
RECOVERY_SNAPSHOT_FILENAMES = ("result.json", "requests.json", "session.v4.jsonl")
MCP_SERVER_SCRIPT = """\
@@ -241,10 +239,12 @@ def write_profile_patch(
return path
def write_advanced_profile_patch(root: Path, name: str, sessions: Path) -> Path:
def write_advanced_profile_patch(
root: Path, name: str, sessions: Path, mode: Literal["native", "ptc"] = "native",
) -> Path:
"""Write the shared custom, snapshot, and restart profile patch."""
return write_profile_patch(root, name, sessions, [
{"id": "tools", "config": {"mode": "both"}},
{"id": "tools", "config": {"mode": mode}},
{
"id": "system-prompt",
"config": {
@@ -444,13 +444,16 @@ def completion_chunks(body: dict[str, object]) -> list[dict[str, object]]:
if prompt == SNAPSHOT_WORKFLOW_CHILD_PROMPT:
return text_chunks("WORKFLOW_CHILD_OK")
if prompt == SNAPSHOT_PROMPT:
if "run_code" in advertised_tool_names(body):
if advertised_tool_names(body) != {"run_code"}:
raise AssertionError("PTC mode must advertise only run_code")
return tool_call_chunks(
"advanced-code", "run_code",
{"code": "return await tools.snapshot_double({ value: 21 })",
"description": "Call the configured Plugin tool"},
)
assert_advertised_tool(body, "snapshot_double")
assert_advertised_tool(body, "run_code")
return tool_call_chunks(
"advanced-code", "run_code",
{"code": "return await tools.snapshot_double({ value: 21 })",
"description": "Call the configured Plugin tool"},
)
return tool_call_chunks("advanced-native", "snapshot_double", {"value": 21})
if prompt == RESTART_FIRST_PROMPT:
return text_chunks(RESTART_FIRST_TEXT)
if prompt == DYNAMIC_TOOLS_PROMPT:
@@ -619,15 +622,13 @@ def advanced_tool_followup(
"""Advance the executable snapshot's deterministic parent tool chain."""
if not call_id.startswith("advanced-"):
return None
if call_id == "advanced-native" and tool_name == "snapshot_double":
if tool_text != "42":
raise AssertionError(f"native call returned no configured-tool value: {tool_text}")
return tool_call_chunks("advanced-denied-native", "snapshot_double", {"value": -1})
if call_id == "advanced-code" and tool_name == "run_code":
if "42" not in tool_text:
raise AssertionError(f"run_code returned no configured-tool value: {tool_text}")
return tool_call_chunks("advanced-denied-native", "snapshot_double", {"value": -1})
if call_id == "advanced-denied-native" and tool_name == "snapshot_double":
if 'Auto review rejected tool "snapshot_double"; its body was not executed' not in tool_text:
raise AssertionError(f"native denial did not preserve the model result: {tool_text}")
if "transport raw" in tool_text:
raise AssertionError("native denial leaked its user-facing reason to the model")
return tool_call_chunks("advanced-denied-ptc", "run_code", {
"code": "try { await tools.snapshot_double({ value: -1 }) } catch (error) { return error.message }",
"description": "Catch a structured inner tool denial",
@@ -637,6 +638,12 @@ def advanced_tool_followup(
raise AssertionError(f"PTC denial did not preserve the model result: {tool_text}")
if "transport raw" in tool_text:
raise AssertionError("PTC denial leaked its user-facing reason to the model")
return text_chunks(SNAPSHOT_FINAL_TEXT)
if call_id == "advanced-denied-native" and tool_name == "snapshot_double":
if 'Auto review rejected tool "snapshot_double"; its body was not executed' not in tool_text:
raise AssertionError(f"native denial did not preserve the model result: {tool_text}")
if "transport raw" in tool_text:
raise AssertionError("native denial leaked its user-facing reason to the model")
assert_advertised_tool(body, "subagent")
return tool_call_chunks(
"advanced-direct-child",
@@ -1203,33 +1210,35 @@ def smoke_sdk_default(base_url: str) -> None:
def smoke_sdk_custom(base_url: str, executable: Path) -> None:
from deepseek_harness import DeepSeekHarness
with tempfile.TemporaryDirectory(prefix="dsh-sdk-custom-") as temporary:
root = Path(temporary).resolve()
dsh_home = root / "home"
sessions = dsh_home / "sessions"
patch = write_advanced_profile_patch(root, "custom.patch.yml", sessions)
with DeepSeekHarness(
provider="deepseek-official",
model="smoke-model",
cwd=str(root),
dsh_bin=str(executable),
dsh_home=str(dsh_home),
patches=(str(patch),),
env={
"DSH_PERMISSION_MODE": "danger-full-access",
"DSH_TELEMETRY_DISABLED": "1",
},
api_key="sk-keyless-smoke",
base_url=base_url,
request_timeout_seconds=60,
) as harness:
text_result = harness.run("reply with the smoke text", session_id="custom-smoke")
code_result = harness.run(CODE_PROMPT, session_id="custom-smoke")
workflow_result = harness.run(WORKFLOW_PROMPT, session_id="custom-smoke")
assert text_result.final_response == EXPECTED_TEXT, text_result.final_response
assert code_result.final_response == CODE_WORKER_TEXT, code_result.final_response
assert workflow_result.final_response == WORKFLOW_WORKER_TEXT, workflow_result.final_response
assert_session_log(sessions, root, EXPECTED_TEXT, CODE_WORKER_TEXT, WORKFLOW_WORKER_TEXT)
cases: tuple[tuple[Literal["native", "ptc"], tuple[tuple[str, str], ...]], ...] = (
("native", (("reply with the smoke text", EXPECTED_TEXT), (WORKFLOW_PROMPT, WORKFLOW_WORKER_TEXT))),
("ptc", ((CODE_PROMPT, CODE_WORKER_TEXT),)),
)
for mode, turns in cases:
with tempfile.TemporaryDirectory(prefix=f"dsh-sdk-custom-{mode}-") as temporary:
root = Path(temporary).resolve()
dsh_home = root / "home"
sessions = dsh_home / "sessions"
patch = write_advanced_profile_patch(root, "custom.patch.yml", sessions, mode)
with DeepSeekHarness(
provider="deepseek-official",
model="smoke-model",
cwd=str(root),
dsh_bin=str(executable),
dsh_home=str(dsh_home),
patches=(str(patch),),
env={
"DSH_PERMISSION_MODE": "danger-full-access",
"DSH_TELEMETRY_DISABLED": "1",
},
api_key="sk-keyless-smoke",
base_url=base_url,
request_timeout_seconds=60,
) as harness:
for prompt, expected in turns:
result = harness.run(prompt, session_id=f"custom-{mode}")
assert result.final_response == expected, result.final_response
assert_session_log(sessions, root, *(expected for _, expected in turns))
def smoke_sdk_minimal(
@@ -1519,14 +1528,22 @@ def smoke_sdk_profile_plugin(base_url: str) -> None:
def smoke_sdk_snapshot(base_url: str, executable: Path, update_snapshots: bool) -> None:
"""Drive and compare the advanced SDK/executable behavioral snapshot."""
"""Exercise native and PTC calls in independent packaged-runtime compositions."""
for mode in ("native", "ptc"):
smoke_sdk_snapshot_mode(base_url, executable, update_snapshots, mode)
def smoke_sdk_snapshot_mode(
base_url: str, executable: Path, update_snapshots: bool, mode: Literal["native", "ptc"],
) -> None:
"""Drive one supported presentation through the SDK and persistent Session log."""
from deepseek_harness import DeepSeekHarness
with tempfile.TemporaryDirectory(prefix="dsh-sdk-snapshot-") as temporary:
root = Path(temporary).resolve()
dsh_home = root / "home"
sessions = dsh_home / "sessions"
patch = write_advanced_profile_patch(root, "snapshot.patch.yml", sessions)
patch = write_advanced_profile_patch(root, "snapshot.patch.yml", sessions, mode)
feedback_patch = write_profile_patch(root, "feedback.patch.yml", sessions, [{"insert": [
{"id": "snapshot-tool", "name": (
Path(__file__).resolve().parent / "fixtures/python-snapshot-tool.mjs"
@@ -1590,11 +1607,13 @@ def smoke_sdk_snapshot(base_url: str, executable: Path, update_snapshots: bool)
if feedback_types != ["feedback/record", "feedback/record", "feedback/message-put", "feedback/message-put", "feedback/message-delete"]:
raise AssertionError(f"advanced snapshot did not exercise all feedback mutations: {feedback_types}")
methods = [notification.method for notification in result.notifications]
if methods.count("subagent.started") != 2 or methods.count("subagent.finished") != 2:
raise AssertionError(f"advanced snapshot emitted unexpected subagent lifecycle: {methods}")
expected_children = 2 if mode == "native" else 0
if methods.count("subagent.started") != expected_children or methods.count("subagent.finished") != expected_children:
raise AssertionError(f"{mode} advanced snapshot emitted unexpected subagent lifecycle: {methods}")
ptc_events = [event for event in result.events
if event.get("type") in ("tool/ptc-dispatch-start", "tool/ptc-dispatch")]
if [event["type"] for event in ptc_events] != ["tool/ptc-dispatch-start", "tool/ptc-dispatch"] * 2:
expected_ptc_calls = 2 if mode == "ptc" else 0
if [event["type"] for event in ptc_events] != ["tool/ptc-dispatch-start", "tool/ptc-dispatch"] * expected_ptc_calls:
raise AssertionError(f"advanced snapshot emitted unexpected PTC dispatch events: {ptc_events}")
for index, event in enumerate(ptc_events):
data = event["data"]
@@ -1608,21 +1627,23 @@ def smoke_sdk_snapshot(base_url: str, executable: Path, update_snapshots: bool)
if event.get("type") in ("tool/result", "tool/ptc-dispatch") and "error" in event["data"]]
assert errors == [{
"name": "AutoReviewDeniedError", "code": "AUTO_REVIEW_DENIED", "reason": " transport raw\r\nreason ",
}] * 2, errors
}], errors
logs = read_session_logs(sessions)
child_ids = snapshot_child_ids(result)
child_ids = snapshot_child_ids(result, expected_children)
expected_ids = {SNAPSHOT_SESSION_ID, *child_ids}
if set(logs) != expected_ids:
raise AssertionError(f"advanced snapshot expected parent plus two child logs: {sorted(logs)}")
if "DIRECT_CHILD_OK" not in render_jsonl(logs[child_ids[0]]):
raise AssertionError("first advanced child log has no direct-subagent result")
if "WORKFLOW_CHILD_OK" not in render_jsonl(logs[child_ids[1]]):
raise AssertionError("second advanced child log has no workflow-subagent result")
raise AssertionError(f"advanced snapshot expected parent plus {expected_children} child logs: {sorted(logs)}")
if mode == "native":
if "DIRECT_CHILD_OK" not in render_jsonl(logs[child_ids[0]]):
raise AssertionError("first advanced child log has no direct-subagent result")
if "WORKFLOW_CHILD_OK" not in render_jsonl(logs[child_ids[1]]):
raise AssertionError("second advanced child log has no workflow-subagent result")
files = build_snapshot_files(result, logs, child_ids, root)
compare_snapshot_files(
files, update_snapshots, ADVANCED_SNAPSHOT_DIRECTORY, ADVANCED_SNAPSHOT_FILENAMES,
files, update_snapshots, ADVANCED_SNAPSHOT_ROOT / f"advanced-{mode}",
ADVANCED_SNAPSHOT_FILENAMES if mode == "native" else ("result.json", "session.v4.jsonl"),
native_writer_output=True,
)
@@ -2158,8 +2179,8 @@ def read_session_logs(sessions: Path) -> dict[str, list[dict[str, object]]]:
return logs
def snapshot_child_ids(result: "RunResult") -> list[str]:
"""Return the two child session ids in their SDK notification order."""
def snapshot_child_ids(result: "RunResult", expected_count: int) -> list[str]:
"""Return the expected child session ids in their SDK notification order."""
child_ids: list[str] = []
for notification in result.notifications:
if notification.method != "subagent.started":
@@ -2170,8 +2191,8 @@ def snapshot_child_ids(result: "RunResult") -> list[str]:
child_id = payload.get("childSessionId")
if isinstance(child_id, str) and child_id not in child_ids:
child_ids.append(child_id)
if len(child_ids) != 2:
raise AssertionError(f"advanced snapshot expected two child session ids: {child_ids}")
if len(child_ids) != expected_count:
raise AssertionError(f"advanced snapshot expected {expected_count} child session ids: {child_ids}")
return child_ids
@@ -2372,9 +2393,10 @@ def build_snapshot_files(
child_ids: list[str],
cwd: Path,
) -> dict[str, str]:
"""Render the SDK result and three persisted logs into stable expected outputs."""
"""Render the SDK result and its persisted parent/child logs into stable expected outputs."""
replacements = snapshot_directory_replacements(cwd, "{{cwd}}") + [(SNAPSHOT_SESSION_ID, "{{parent}}")]
replacements.append((snapshot_workflow_run_id(result), "{{workflow-run}}"))
if child_ids:
replacements.append((snapshot_workflow_run_id(result), "{{workflow-run}}"))
for index, child_id in enumerate(child_ids, start=1):
replacements.append((child_id, f"{{{{child-{index}}}}}"))
agent_id = snapshot_agent_id(result, child_id)
scripts/snapshots/python-sdk-single-exe/advanced-native/result.json
+4308
View File
File diff suppressed because it is too large. Load diff
scripts/snapshots/python-sdk-single-exe/advanced-native/session.1.v4.jsonl
+22
View File
@@ -0,0 +1,22 @@
{"type":"session","version":4,"id":"{{child-1}}","createdAt":0,"cwd":"{{cwd}}","parentSession":"{{parent}}","isSeeded":false,"origin":"subagent","delegationDepth":1}
{"type":"subagent/descriptor","data":{"version":3,"mode":"continuable","provider":"spawn","label":"Check direct child","agentProvider":"deepseek-official","agentModel":"smoke-model","agentReasoningEffort":"high"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access","source":"delegation"}}
{"type":"approval/policy","data":{"policy":"never","source":"delegation"}}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}}]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","reasoningEffort":"high","maxTokens":256000},"adapterDefaults":{"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","snapshot_double","subagent","workflow","working_directory"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[12],"source":{"kind":"fallback"}}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{child-1}}","sessionFormatVersion":4,"throughSeq":16}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["DIRECT_CHILD_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
scripts/snapshots/python-sdk-single-exe/advanced-native/session.2.v4.jsonl
+22
View File
@@ -0,0 +1,22 @@
{"type":"session","version":4,"id":"{{child-2}}","createdAt":0,"cwd":"{{cwd}}","parentSession":"{{parent}}","isSeeded":false,"origin":"subagent","delegationDepth":1}
{"type":"subagent/descriptor","data":{"version":3,"mode":"continuable","provider":"spawn","label":"advanced-exe-snapshot child 1","agentProvider":"deepseek-official","agentModel":"smoke-model","agentReasoningEffort":"high"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access","source":"delegation"}}
{"type":"approval/policy","data":{"policy":"never","source":"delegation"}}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}}]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).\n\nYou are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."},{"name":"subagent:delegation","text":"You are a delegated subagent: your permission scope was fixed when you were started and cannot be widened from inside this session — operations that require approval are rejected automatically. When the task needs access beyond that scope, do not retry the denied operation; state the limitation in your reply so the delegating agent can handle it."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","reasoningEffort":"high","maxTokens":256000},"adapterDefaults":{"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","snapshot_double","subagent","workflow","working_directory"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[12],"source":{"kind":"fallback"}}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{child-2}}","sessionFormatVersion":4,"throughSeq":16}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["WORKFLOW_CHILD_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
scripts/snapshots/python-sdk-single-exe/advanced-native/session.v4.jsonl
+65
View File
@@ -0,0 +1,65 @@
{"type":"session","version":4,"id":"{{parent}}","createdAt":0,"cwd":"{{cwd}}","isSeeded":false,"delegationDepth":0}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access"}}
{"type":"approval/policy","data":{"policy":"never"}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}}]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Run the advanced packaged-runtime snapshot scenario."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Run the advanced packaged-runtime snapshot scenario."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"id":"{{messageId}}","role":"user","content":[{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}}],"source":{"kind":"python-snapshot-image-offload"}},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","snapshot_double","subagent","workflow","working_directory"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Run the advanced packaged-runtime snapsh","messageSeqs":[11],"source":{"kind":"fallback"}}}
{"type":"assistant/attempt","data":{"turn":1,"step":1,"stream":[{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"code":"IMAGE_OFFLOAD_REQUIRED","message":"authored image budget failure","offloadImages":1}}}}]}}
{"type":"image/offload","data":{"targets":[{"seq":13,"imageIndexes":[0]}]}}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","snapshot_double","subagent","workflow","working_directory"]},"reason":"series"}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":19}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-native","name":"snapshot_double","arguments":"{\"value\": 21}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-native","name":"snapshot_double","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-native","args":["{\"value\": 21}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-native","name":"snapshot_double","arguments":"{\"value\": 21}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"advanced-native","name":"snapshot_double","arguments":"{\"value\": 21}"}}
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"advanced-native"},"toolCallId":"advanced-native","content":[{"type":"text","text":"42"}],"isError":false,"id":"{{messageId}}"}},"sourceEventSeqs":[22],"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"step/start","data":{"turn":1,"step":2}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":25}}
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-denied-native","name":"snapshot_double","arguments":"{\"value\": -1}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-denied-native","name":"snapshot_double","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-denied-native","args":["{\"value\": -1}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-denied-native","name":"snapshot_double","arguments":"{\"value\": -1}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","data":{"turn":1,"step":2,"callId":"advanced-denied-native","name":"snapshot_double","arguments":"{\"value\": -1}"}}
{"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"advanced-denied-native"},"toolCallId":"advanced-denied-native","content":[{"type":"text","text":"Error: Auto review rejected tool \"snapshot_double\"; its body was not executed"}],"isError":true,"id":"{{messageId}}"},"error":{"name":"AutoReviewDeniedError","code":"AUTO_REVIEW_DENIED","reason":" transport raw\r\nreason "}},"sourceEventSeqs":[28],"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":2}}
{"type":"step/start","data":{"turn":1,"step":3}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":31}}
{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","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.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-direct-child","name":"subagent","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-direct-child","args":["{\"description\": \"Check direct child\", \"prompt\": \"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"]},{"type":"chunk","time":0,"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":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","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":"subagent/catalog","data":{"version":0,"childId":"{{child-1}}","childCreatedAt":0,"mode":"continuable","label":"Check direct child"}}
{"type":"tool/result","data":{"turn":1,"step":3,"message":{"role":"tool","source":{"kind":"tool","callId":"advanced-direct-child"},"toolCallId":"advanced-direct-child","content":[{"type":"text","text":"started subagent {{child-1}}"}],"isError":false,"id":"{{messageId}}"}},"sourceEventSeqs":[34],"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":3}}
{"type":"step/start","data":{"turn":1,"step":4}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":38}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{child-1}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"DIRECT_CHILD_OK"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{child-1}} finished and will do no further work unless you send it more.","senderSessionId":"{{child-1}}"},"role":"user","id":"{{messageId}}"}]}}
{"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","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-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-workflow","name":"workflow","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-workflow","args":["{\"script\": \"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\", \"meta\": {\"name\": \"advanced-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"]},{"type":"chunk","time":0,"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-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","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-exe-snapshot\", \"description\": \"exercise one packaged workflow child\"}}"}}
{"type":"tool-workflow/run-start","data":{"runId":"{{workflow-run}}","name":"advanced-exe-snapshot"}}
{"type":"subagent/catalog","data":{"version":0,"childId":"{{child-2}}","childCreatedAt":0,"mode":"continuable","label":"advanced-exe-snapshot child 1"}}
{"type":"tool-workflow/agent-start","data":{"runId":"{{workflow-run}}","seq":1,"label":"workflow-child","phase":"Delegate","childId":"{{child-2}}"}}
{"type":"tool-workflow/agent-end","data":{"runId":"{{workflow-run}}","seq":1,"outcome":"completed"}}
{"type":"tool-workflow/run-end","data":{"runId":"{{workflow-run}}","stopReason":"completed"}}
{"type":"tool/result","data":{"turn":1,"step":4,"message":{"role":"tool","source":{"kind":"tool","callId":"advanced-workflow"},"toolCallId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-exe-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false,"id":"{{messageId}}"}},"sourceEventSeqs":[42],"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":4}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":5}}
{"type":"user/message","data":{"content":[{"type":"text","text":"Background subagent {{child-1}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"DIRECT_CHILD_OK"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{child-1}} finished and will do no further work unless you send it more.","senderSessionId":"{{child-1}}"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":52}}
{"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"text","text":"ADVANCED_EXECUTABLE_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{message:1}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["ADVANCED_EXECUTABLE_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_EXECUTABLE_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":5}}
{"type":"command/run","data":{"commandId":"{{command:1}}","name":"feedback","source":{"kind":"user"}}}
{"type":"feedback/record","data":{"text":"The session needs a clearer explanation."}}
{"type":"command/done","data":{"commandId":"{{command:1}}","kind":"success","text":"Feedback recorded for session {{parent}}\nAnonymous user: {{anonymous-user}}."}}
{"type":"feedback/record","data":{"category":"other"}}
{"type":"feedback/message-put","data":{"sessionId":"{{parent}}","item":{"messageId":"{{message:1}}","rating":"negative","note":"Explain the result.","category":"task-result","version":"{{feedback-version:1}}","createdAt":0,"updatedAt":0}}}
{"type":"feedback/message-put","data":{"sessionId":"{{parent}}","item":{"messageId":"{{message:1}}","rating":"positive","note":"The explanation is clear now.","version":"{{feedback-version:2}}","createdAt":0,"updatedAt":0}}}
{"type":"feedback/message-delete","data":{"sessionId":"{{parent}}","messageId":"{{message:1}}"}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
scripts/snapshots/python-sdk-single-exe/advanced-ptc/result.json
+2226
View File
File diff suppressed because it is too large. Load diff
scripts/snapshots/python-sdk-single-exe/advanced-ptc/session.v4.jsonl
+48
View File
@@ -0,0 +1,48 @@
{"type":"session","version":4,"id":"{{parent}}","createdAt":0,"cwd":"{{cwd}}","isSeeded":false,"delegationDepth":0}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access"}}
{"type":"approval/policy","data":{"policy":"never"}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}}]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Run the advanced packaged-runtime snapshot scenario."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"id":"{{messageId}}","role":"user","content":[{"type":"text","text":"Serial agent creation completed."}],"source":{"kind":"plugin:serial-created-fixture"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Run the advanced packaged-runtime snapshot scenario."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"id":"{{messageId}}","role":"user","content":[{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}}],"source":{"kind":"python-snapshot-image-offload"}},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["run_code"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Run the advanced packaged-runtime snapsh","messageSeqs":[11],"source":{"kind":"fallback"}}}
{"type":"assistant/attempt","data":{"turn":1,"step":1,"stream":[{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"code":"IMAGE_OFFLOAD_REQUIRED","message":"authored image budget failure","offloadImages":1}}}}]}}
{"type":"image/offload","data":{"targets":[{"seq":13,"imageIndexes":[0]}]}}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["run_code"]},"reason":"series"}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":19}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Call the configured Plugin tool\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-code","name":"run_code","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-code","args":["{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Call the configured Plugin tool\"}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Call the configured Plugin tool\"}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"advanced-code","name":"run_code","arguments":"{\"code\": \"return await tools.snapshot_double({ value: 21 })\", \"description\": \"Call the configured Plugin tool\"}"}}
{"type":"tool/ptc-dispatch-start","data":{"rootCallId":"advanced-code","parentCallId":"advanced-code","subCallId":"advanced-code:ptc:1","name":"snapshot_double","arguments":{"value":21}}}
{"type":"tool/ptc-dispatch","data":{"rootCallId":"advanced-code","parentCallId":"advanced-code","subCallId":"advanced-code:ptc:1","name":"snapshot_double","arguments":{"value":21},"isError":false,"content":[{"type":"text","text":"42"}]}}
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"advanced-code"},"toolCallId":"advanced-code","content":[{"type":"text","text":"42"}],"isError":false,"id":"{{messageId}}"}},"sourceEventSeqs":[22],"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"step/start","data":{"turn":1,"step":2}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":27}}
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-denied-ptc","name":"run_code","arguments":"{\"code\": \"try { await tools.snapshot_double({ value: -1 }) } catch (error) { return error.message }\", \"description\": \"Catch a structured inner tool denial\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-denied-ptc","name":"run_code","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"advanced-denied-ptc","args":["{\"code\": \"try { await tools.snapshot_double({ value: -1 }) } catch (error) { return error.message }\", \"description\": \"Catch a structured inner tool denial\"}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-denied-ptc","name":"run_code","arguments":"{\"code\": \"try { await tools.snapshot_double({ value: -1 }) } catch (error) { return error.message }\", \"description\": \"Catch a structured inner tool denial\"}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","data":{"turn":1,"step":2,"callId":"advanced-denied-ptc","name":"run_code","arguments":"{\"code\": \"try { await tools.snapshot_double({ value: -1 }) } catch (error) { return error.message }\", \"description\": \"Catch a structured inner tool denial\"}"}}
{"type":"tool/ptc-dispatch-start","data":{"rootCallId":"advanced-denied-ptc","parentCallId":"advanced-denied-ptc","subCallId":"advanced-denied-ptc:ptc:1","name":"snapshot_double","arguments":{"value":-1}}}
{"type":"tool/ptc-dispatch","data":{"rootCallId":"advanced-denied-ptc","parentCallId":"advanced-denied-ptc","subCallId":"advanced-denied-ptc:ptc:1","name":"snapshot_double","arguments":{"value":-1},"isError":true,"error":{"name":"AutoReviewDeniedError","code":"AUTO_REVIEW_DENIED","reason":" transport raw\r\nreason "},"content":[{"type":"text","text":"Error: Auto review rejected tool \"snapshot_double\"; its body was not executed"}]}}
{"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"advanced-denied-ptc"},"toolCallId":"advanced-denied-ptc","content":[{"type":"text","text":"Auto review rejected tool \"snapshot_double\"; its body was not executed"}],"isError":false,"id":"{{messageId}}"}},"sourceEventSeqs":[30],"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":2}}
{"type":"step/start","data":{"turn":1,"step":3}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{parent}}","sessionFormatVersion":4,"throughSeq":35}}
{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"ADVANCED_EXECUTABLE_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{message:1}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["ADVANCED_EXECUTABLE_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_EXECUTABLE_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":3}}
{"type":"command/run","data":{"commandId":"{{command:1}}","name":"feedback","source":{"kind":"user"}}}
{"type":"feedback/record","data":{"text":"The session needs a clearer explanation."}}
{"type":"command/done","data":{"commandId":"{{command:1}}","kind":"success","text":"Feedback recorded for session {{parent}}\nAnonymous user: {{anonymous-user}}."}}
{"type":"feedback/record","data":{"category":"other"}}
{"type":"feedback/message-put","data":{"sessionId":"{{parent}}","item":{"messageId":"{{message:1}}","rating":"negative","note":"Explain the result.","category":"task-result","version":"{{feedback-version:1}}","createdAt":0,"updatedAt":0}}}
{"type":"feedback/message-put","data":{"sessionId":"{{parent}}","item":{"messageId":"{{message:1}}","rating":"positive","note":"The explanation is clear now.","version":"{{feedback-version:2}}","createdAt":0,"updatedAt":0}}}
{"type":"feedback/message-delete","data":{"sessionId":"{{parent}}","messageId":"{{message:1}}"}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
scripts/snapshots/python-sdk-single-exe/restart-native/requests.json
+60
View File
@@ -0,0 +1,60 @@
[
{
"model": "smoke-model",
"system": "{{system}}",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Complete the first isolated Python SDK process turn."
},
{
"type": "text",
"text": "Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."
}
]
}
],
"toolNames": [
"cordis_inspect_list",
"cordis_inspect_query",
"job_kill",
"job_list",
"job_output",
"subagent",
"workflow",
"working_directory"
]
},
{
"model": "smoke-model",
"system": "{{system}}",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Complete the second isolated Python SDK process turn."
},
{
"type": "text",
"text": "Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."
}
]
}
],
"toolNames": [
"cordis_inspect_list",
"cordis_inspect_query",
"job_kill",
"job_list",
"job_output",
"subagent",
"workflow",
"working_directory"
]
}
]
scripts/snapshots/python-sdk-single-exe/restart-native/result.json
+80
View File
@@ -0,0 +1,80 @@
[
{
"session_id": "{{session-1}}",
"final_response": "PROCESS_ONE_OK",
"finish_reason": "completed",
"eventTypes": [
"agent/inbox/spliced",
"turn/start",
"agent/inbox/spliced",
"step/start",
"system/message",
"user/message",
"user/message",
"request/header",
"request/context",
"session/title",
"session-log-deepseek/delivery-accepted",
"assistant/message",
"step/end",
"turn/end"
],
"notificationMethods": [
"session.event",
"session.status",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.status"
]
},
{
"session_id": "{{session-2}}",
"final_response": "PROCESS_TWO_OK",
"finish_reason": "completed",
"eventTypes": [
"agent/inbox/spliced",
"turn/start",
"agent/inbox/spliced",
"step/start",
"system/message",
"user/message",
"user/message",
"request/header",
"request/context",
"session/title",
"session-log-deepseek/delivery-accepted",
"assistant/message",
"step/end",
"turn/end"
],
"notificationMethods": [
"session.event",
"session.status",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.status"
]
}
]
scripts/snapshots/python-sdk-single-exe/restart-native/session.1.v4.jsonl
+18
View File
@@ -0,0 +1,18 @@
{"type":"session","version":4,"id":"{{session-1}}","createdAt":0,"cwd":"{{cwd}}","isSeeded":false,"delegationDepth":0}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access"}}
{"type":"approval/policy","data":{"policy":"never"}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Complete the first isolated Python SDK process turn."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Complete the first isolated Python SDK process turn."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","subagent","workflow","working_directory"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Complete the first isolated Python","messageSeqs":[8],"source":{"kind":"fallback"}}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session-1}}","sessionFormatVersion":4,"throughSeq":12}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"PROCESS_ONE_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["PROCESS_ONE_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PROCESS_ONE_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
scripts/snapshots/python-sdk-single-exe/restart-native/session.2.v4.jsonl
+18
View File
@@ -0,0 +1,18 @@
{"type":"session","version":4,"id":"{{session-2}}","createdAt":0,"cwd":"{{cwd}}","isSeeded":false,"delegationDepth":0}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access"}}
{"type":"approval/policy","data":{"policy":"never"}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Complete the second isolated Python SDK process turn."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Complete the second isolated Python SDK process turn."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","subagent","workflow","working_directory"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Complete the second isolated Python","messageSeqs":[8],"source":{"kind":"fallback"}}}
{"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session-2}}","sessionFormatVersion":4,"throughSeq":12}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"PROCESS_TWO_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["PROCESS_TWO_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PROCESS_TWO_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
scripts/snapshots/python-sdk-single-exe/scheduler-recovery-native/requests.json
+109
View File
@@ -0,0 +1,109 @@
[
{
"model": "smoke-model",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Run three todo updates; the scheduler will reject the second call."
},
{
"type": "text",
"text": "Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically \u2014 do not request sandbox escalation (do not set `sandbox_permissions`)."
}
]
}
]
},
{
"model": "smoke-model",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Run three todo updates; the scheduler will reject the second call."
},
{
"type": "text",
"text": "Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically \u2014 do not request sandbox escalation (do not set `sandbox_permissions`)."
}
]
},
{
"role": "assistant",
"content": [
{
"type": "tool_use",
"id": "scheduler-complete",
"name": "todo_write",
"input": {
"todos": []
}
},
{
"type": "tool_use",
"id": "scheduler-fail",
"name": "todo_write",
"input": {
"todos": []
}
},
{
"type": "tool_use",
"id": "scheduler-unstarted",
"name": "todo_write",
"input": {
"todos": []
}
}
]
},
{
"role": "user",
"content": [
{
"type": "tool_result",
"tool_use_id": "scheduler-complete",
"content": [
{
"type": "text",
"text": "Updated todo list: 0 pending, 0 in progress, 0 completed."
}
],
"is_error": false
},
{
"type": "tool_result",
"tool_use_id": "scheduler-fail",
"content": [
{
"type": "text",
"text": "The tool call was interrupted after it was recorded, but no result was durably recorded. Its outcome is unknown. Decide whether to retry from the tool semantics: retry only if the operation is read-only or idempotent; if it may have side effects, first verify external state or ask the user. Do not retry blindly."
}
],
"is_error": true
},
{
"type": "tool_result",
"tool_use_id": "scheduler-unstarted",
"content": [
{
"type": "text",
"text": "The tool call was interrupted before the Harness recorded it as started. Retry it if it is still needed."
}
],
"is_error": true
},
{
"type": "text",
"text": "Continue after the scheduler failure without repeating any tools."
}
]
}
]
}
]
scripts/snapshots/python-sdk-single-exe/scheduler-recovery-native/result.json
+78
View File
@@ -0,0 +1,78 @@
[
{
"session_id": "{{parent}}",
"final_response": "",
"finish_reason": "error",
"eventTypes": [
"agent/inbox/spliced",
"turn/start",
"agent/inbox/spliced",
"step/start",
"system/message",
"user/message",
"user/message",
"request/header",
"request/context",
"session/title",
"assistant/message",
"tool/call",
"todo/write",
"tool/result",
"tool/call",
"tool/result",
"tool/result",
"step/end",
"turn/end"
],
"notificationMethods": [
"session.event",
"session.status",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.status"
]
},
{
"session_id": "{{parent}}",
"final_response": "SCHEDULER_RECOVERY_OK",
"finish_reason": "completed",
"eventTypes": [
"agent/inbox/spliced",
"turn/start",
"agent/inbox/spliced",
"step/start",
"user/message",
"assistant/message",
"step/end",
"turn/end"
],
"notificationMethods": [
"session.event",
"session.status",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.event",
"session.status"
]
}
]
scripts/snapshots/python-sdk-single-exe/scheduler-recovery-native/session.v4.jsonl
+31
View File
@@ -0,0 +1,31 @@
{"type":"session","version":4,"id":"{{parent}}","createdAt":0,"cwd":"{{cwd}}","isSeeded":false,"delegationDepth":0}
{"type":"permission/preset","data":{"preset":"danger-full-access"}}
{"type":"sandbox/mode","data":{"mode":"danger-full-access"}}
{"type":"approval/policy","data":{"policy":"never"}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Run three todo updates; the scheduler will reject the second call."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":1}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":1,"step":1}}
{"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{messageId}}"}},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Run three todo updates; the scheduler will reject the second call."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"smoke-model","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["cordis_inspect_list","cordis_inspect_query","job_kill","job_list","job_output","subagent","todo_write","workflow","working_directory"]},"reason":"initial"}}
{"type":"request/context","data":{"provider":"deepseek-official","model":"smoke-model","contextWindow":1000000}}
{"type":"session/title","data":{"title":"Run three todo updates; the","messageSeqs":[8],"source":{"kind":"fallback"}}}
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"scheduler-complete","name":"todo_write","arguments":"{\"todos\": []}"},{"type":"tool-call","id":"scheduler-fail","name":"todo_write","arguments":"{\"todos\": []}"},{"type":"tool-call","id":"scheduler-unstarted","name":"todo_write","arguments":"{\"todos\": []}"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"},{"type":"tool-call"},{"type":"tool-call"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"scheduler-complete","name":"todo_write","args":[""]},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"scheduler-complete","args":["{\"todos\": []}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"scheduler-complete","name":"todo_write","arguments":"{\"todos\": []}"}}},{"type":"chunk","time":0,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":1,"dt":[],"id":"scheduler-fail","name":"todo_write","args":[""]},{"type":"tool-call-chunks","time0":0,"index":1,"dt":[],"id":"scheduler-fail","args":["{\"todos\": []}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"scheduler-fail","name":"todo_write","arguments":"{\"todos\": []}"}}},{"type":"chunk","time":0,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":2,"dt":[],"id":"scheduler-unstarted","name":"todo_write","args":[""]},{"type":"tool-call-chunks","time0":0,"index":2,"dt":[],"id":"scheduler-unstarted","args":["{\"todos\": []}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"scheduler-unstarted","name":"todo_write","arguments":"{\"todos\": []}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"tool-call"},{"type":"tool-call"},{"type":"tool-call"}]}}}]},"surfaceOp":"append"}
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"scheduler-complete","name":"todo_write","arguments":"{\"todos\": []}"}}
{"type":"todo/write","data":{"todos":[]}}
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"scheduler-complete"},"toolCallId":"scheduler-complete","content":[{"type":"text","text":"Updated todo list: 0 pending, 0 in progress, 0 completed."}],"isError":false,"id":"{{messageId}}"}},"sourceEventSeqs":[14],"surfaceOp":"append"}
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"scheduler-fail","name":"todo_write","arguments":"{\"todos\": []}"}}
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"id":"interrupted-tool-result-scheduler-fail-18","role":"tool","toolCallId":"scheduler-fail","isError":true,"source":{"kind":"tool","callId":"scheduler-fail"},"content":[{"type":"text","text":"The tool call was interrupted after it was recorded, but no result was durably recorded. Its outcome is unknown. Decide whether to retry from the tool semantics: retry only if the operation is read-only or idempotent; if it may have side effects, first verify external state or ask the user. Do not retry blindly."}]},"error":{"name":"ToolOutcomeUnknownError","code":"TOOL_OUTCOME_UNKNOWN"}},"sourceEventSeqs":[17],"surfaceOp":"append"}
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"id":"interrupted-tool-result-scheduler-unstarted-19","role":"tool","toolCallId":"scheduler-unstarted","isError":true,"source":{"kind":"tool","callId":"scheduler-unstarted"},"content":[{"type":"text","text":"The tool call was interrupted before the Harness recorded it as started. Retry it if it is still needed."}]},"error":{"name":"ToolNotStartedError","code":"TOOL_NOT_STARTED"}},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":1,"step":1}}
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"error","error":{"message":"Snapshot scheduler preparation failed","code":"UNKNOWN"}}}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Continue after the scheduler failure without repeating any tools."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"}]}}
{"type":"turn/start","data":{"turn":2}}
{"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","data":{"turn":2,"step":1}}
{"type":"user/message","data":{"content":[{"type":"text","text":"Continue after the scheduler failure without repeating any tools."}],"source":{"kind":"user"},"role":"user","id":"{{messageId}}"},"surfaceOp":"append"}
{"type":"assistant/message","data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"SCHEDULER_RECOVERY_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"smoke-model","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}},"id":"{{messageId}}"},"usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["SCHEDULER_RECOVERY_OK"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SCHEDULER_RECOVERY_OK"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3,"totalTokens":6}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"smoke-model"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"}
{"type":"step/end","data":{"turn":2,"step":1}}
{"type":"turn/end","data":{"turn":2,"reason":{"kind":"completed"}}}