mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-11-09 04:20:34 +00:00
aaca3eeaeb
* refactor(agent): ground runtime decisions in structured evidence Use producer status and structured errors for tool recovery, preserve memory context without lexical confirmation, and remove predetermined receipt and skill conclusions. Require explicit MCP discovery and authenticated schedule trial actions. Preserve authorization, ownership, isolation, and bounded execution; update documentation and regression coverage. * test(sandbox): expect read_file initialization error callback * fix(agent): address evidence review follow-ups * fix(agent): preserve retry budgets for OpenAI transport errors * fix(agent): expose tool execution status in model requests Project validated execution metadata and exact tool text into request-only JSON so status survives provider serialization. Preserve stored results and receipt hashes, cover SDK and graph boundaries, and migrate replay input hashes without changing recorded responses. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
28 lines
1.3 KiB
Python
28 lines
1.3 KiB
Python
"""Evidence and proportional interaction regressions."""
|
|
|
|
from deerflow.agents.interaction_policy import RunInteractionPolicy
|
|
from deerflow.agents.middlewares.receipt_verification import render_citation_verdict, verify_receipt_citations
|
|
|
|
|
|
def test_negated_action_text_is_not_semantically_classified():
|
|
verdict = verify_receipt_citations("I did not modify report.py or run tests.", [])
|
|
assert verdict["no_citation_claims"] is False
|
|
assert verdict["citation_resolved"] is False
|
|
assert "no receipt citations" in render_citation_verdict(verdict)
|
|
|
|
|
|
def test_uncited_tool_execution_is_unresolved_regardless_of_language_or_length():
|
|
receipt = {"id": "r1", "status": "success", "tool_name": "bash"}
|
|
for text in ("42", "No changes were needed.", "??", "x" * 500):
|
|
verdict = verify_receipt_citations(text, [receipt])
|
|
assert verdict["citation_resolved"] is False
|
|
assert "action claims" not in render_citation_verdict(verdict)
|
|
|
|
|
|
def test_interactive_policy_allows_inspection_and_reversible_assumptions():
|
|
policy = RunInteractionPolicy.interactive()
|
|
assert "reversible" in policy.clarification_system
|
|
assert "independent" in policy.clarification_system
|
|
assert "Clarification ALWAYS comes BEFORE action" not in policy.clarification_system
|
|
assert "If anything is unclear" not in policy.thinking_guidance
|