mengzhx/deepseek-harness
1
0
Fork 0
mirror of https://github.com/deepseek-ai/deepseek-harness.git synced 2026-09-11 04:00:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(session): represent the system prompt as surface node zero

Browse Source 
Consolidate the representation-change PR and its rebase reconciliations into one baseline. Preserve the exact tree and keep the in-history feature in the dependent PR. Follow-up fixes remain separate.
This commit is contained in:
Tianyi Cui
2026-09-06 20:42:43 +08:00
parent 573485e8b5
commit ee956c720d
300 changed files with 6286 additions and 2396 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/smoke-python-runtime.py
+17 -4
View File
@@ -1955,7 +1955,7 @@ def normalize_snapshot_value(
dt = member.get("dt")
if isinstance(dt, list):
member["dt"] = [0] * len(dt)
if isinstance(normalized.get("id"), str) and normalized.get("role") in ("assistant", "user"):
if isinstance(normalized.get("id"), str) and normalized.get("role") in ("assistant", "system", "user"):
if not normalized["id"].startswith("{{message:"):
normalized["id"] = "{{messageId}}"
if normalized.get("type") in ("feedback/message-put", "feedback/message-delete"):
@@ -1967,11 +1967,12 @@ def normalize_snapshot_value(
item["createdAt"] = 0
item["updatedAt"] = 0
scrub_snapshot_header(normalized)
scrub_snapshot_system_message(normalized)
return normalized
def scrub_snapshot_header(value: dict[object, object]) -> None:
"""Tokenize full request-header bulk while retaining tool names."""
"""Tokenize full request-header tool schemas while retaining tool names."""
data = value.get("data")
if not isinstance(data, dict):
return
@@ -1979,8 +1980,6 @@ def scrub_snapshot_header(value: dict[object, object]) -> None:
header = data.get("header")
if not isinstance(header, dict):
return
if "system" in header:
header["system"] = "{{system}}"
tools = header.get("tools")
if isinstance(tools, list):
header["tools"] = [
@@ -1989,6 +1988,20 @@ def scrub_snapshot_header(value: dict[object, object]) -> None:
]
def scrub_snapshot_system_message(value: dict[object, object]) -> None:
"""Tokenize the rendered prompt text of a `system/message` surface node."""
if value.get("type") != "system/message":
return
data = value.get("data")
message = data.get("message") if isinstance(data, dict) else None
content = message.get("content") if isinstance(message, dict) else None
if not isinstance(content, list):
return
for block in content:
if isinstance(block, dict) and block.get("type") == "text":
block["text"] = "{{system}}"
def render_jsonl(records: list[object]) -> str:
"""Render parsed JSON values as compact, newline-terminated JSONL."""
return "".join(