Merge branch 'main' into rayhpeng/persistence-scaffold

# Conflicts:
#	.env.example
#	backend/packages/harness/deerflow/agents/middlewares/title_middleware.py
This commit is contained in:
rayhpeng
2026-04-04 21:28:07 +08:00
180 changed files with 10945 additions and 787 deletions
+49 -16
View File
@@ -129,26 +129,38 @@ def build_run_config(
the LangGraph Platform-compatible HTTP API and the IM channel path behave
identically.
"""
configurable: dict[str, Any] = {"thread_id": thread_id}
config: dict[str, Any] = {"recursion_limit": 100}
if request_config:
configurable.update(request_config.get("configurable", {}))
# LangGraph >= 0.6.0 introduced ``context`` as the preferred way to
# pass thread-level data and rejects requests that include both
# ``configurable`` and ``context``. If the caller already sends
# ``context``, honour it and skip our own ``configurable`` dict.
if "context" in request_config:
if "configurable" in request_config:
logger.warning(
"build_run_config: client sent both 'context' and 'configurable'; preferring 'context' (LangGraph >= 0.6.0). thread_id=%s, caller_configurable keys=%s",
thread_id,
list(request_config.get("configurable", {}).keys()),
)
config["context"] = request_config["context"]
else:
configurable = {"thread_id": thread_id}
configurable.update(request_config.get("configurable", {}))
config["configurable"] = configurable
for k, v in request_config.items():
if k not in ("configurable", "context"):
config[k] = v
else:
config["configurable"] = {"thread_id": thread_id}
# Inject custom agent name when the caller specified a non-default assistant.
# Honour an explicit configurable["agent_name"] in the request if already set.
if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID and "agent_name" not in configurable:
# Normalize the same way ChannelManager does: strip, lowercase,
# replace underscores with hyphens, then validate to prevent path
# traversal and invalid agent directory lookups.
normalized = assistant_id.strip().lower().replace("_", "-")
if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
configurable["agent_name"] = normalized
config: dict[str, Any] = {"configurable": configurable, "recursion_limit": 100}
if request_config:
for k, v in request_config.items():
if k != "configurable":
config[k] = v
if assistant_id and assistant_id != _DEFAULT_ASSISTANT_ID and "configurable" in config:
if "agent_name" not in config["configurable"]:
normalized = assistant_id.strip().lower().replace("_", "-")
if not normalized or not re.fullmatch(r"[a-z0-9-]+", normalized):
raise ValueError(f"Invalid assistant_id {assistant_id!r}: must contain only letters, digits, and hyphens after normalization.")
config["configurable"]["agent_name"] = normalized
if metadata:
config.setdefault("metadata", {}).update(metadata)
return config
@@ -304,6 +316,27 @@ async def start_run(
agent_factory = resolve_agent_factory(body.assistant_id)
graph_input = normalize_input(body.input)
config = build_run_config(thread_id, body.config, body.metadata, assistant_id=body.assistant_id)
# Merge DeerFlow-specific context overrides into configurable.
# The ``context`` field is a custom extension for the langgraph-compat layer
# that carries agent configuration (model_name, thinking_enabled, etc.).
# Only agent-relevant keys are forwarded; unknown keys (e.g. thread_id) are ignored.
context = getattr(body, "context", None)
if context:
_CONTEXT_CONFIGURABLE_KEYS = {
"model_name",
"mode",
"thinking_enabled",
"reasoning_effort",
"is_plan_mode",
"subagent_enabled",
"max_concurrent_subagents",
}
configurable = config.setdefault("configurable", {})
for key in _CONTEXT_CONFIGURABLE_KEYS:
if key in context:
configurable.setdefault(key, context[key])
stream_modes = normalize_stream_modes(body.stream_mode)
task = asyncio.create_task(