Changjian Wang
f59d5c67d8
* Refactor DocumentEntry model and update result handling - Changed the type of `result` in DocumentEntry from dict to str to store LLM-ready text. - Introduced `search_payload` in DocumentEntry for optional alternate rendering. - Updated FileSearchConfig to include `include_fields` option for vector store uploads. - Modified tests to reflect changes in DocumentEntry and FileSearchConfig. - Adjusted integration tests to validate new result structure and rendering. - Removed legacy format_result tests as rendering is now handled by the SDK. * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Add test to ensure page markers are preserved in LLM input Co-authored-by: Copilot <copilot@github.com> * fix(cu-context-provider): scope LLMStats telemetry filter to rai_warnings block Address PR #5796 review comment: the previous defensive scrubber ran a global regex substitution over the full rendered string, so any markdown body bullet shaped like '- LLMStats: ...' would also be silently deleted. Add a _strip_rai_telemetry helper that confines the substitution to the front-matter rai_warnings: YAML sub-block, leaving the body verbatim. Cover the new behavior with three tests (scoped strip, body preservation, and no-op branches). * Sync uv.lock with azure-ai-contentunderstanding>=1.2.0b1 dependency bump * Python: Drop search_payload/include_fields, single to_llm_input rendering (CU context provider) Address PR #5796 review: remove the redundant search_payload field and _render_search_payload helper, drop the include_fields opt-in (already covered by output_sections), rename _resolve_pending_tokens -> _resolve_pending_analysis, and have _upload_to_vector_store read entry['result'] directly. * Python: Adopt SDK 1.2.0b2 LLMStats filtering, drop local workaround (CU context provider) azure-ai-contentunderstanding 1.2.0b2 filters LLMStats telemetry from rai_warnings and emits InputPageNumber page markers in to_llm_input, so the provider's local defense is redundant. - Bump dependency to azure-ai-contentunderstanding>=1.2.0b2 (re-lock uv.lock) - Remove _strip_rai_telemetry and its two regexes; _render_for_llm now returns to_llm_input(...) directly - Delete 4 workaround unit tests for the removed helper --------- Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Co-authored-by: Copilot <copilot@github.com> Co-authored-by: changjian-wang <v-changjwang@microsoft.com> Co-authored-by: aluneth <wangchangjian1130@163.com>
69 lines
2.6 KiB
Python
69 lines
2.6 KiB
Python
# Copyright (c) Microsoft. All rights reserved.
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock
|
|
|
|
from agent_framework_azure_contentunderstanding._models import (
|
|
DocumentEntry,
|
|
DocumentStatus,
|
|
FileSearchConfig,
|
|
)
|
|
|
|
|
|
class TestDocumentEntry:
|
|
def test_construction(self) -> None:
|
|
entry: DocumentEntry = {
|
|
"status": DocumentStatus.READY,
|
|
"filename": "invoice.pdf",
|
|
"media_type": "application/pdf",
|
|
"analyzer_id": "prebuilt-documentSearch",
|
|
"analyzed_at": "2026-01-01T00:00:00+00:00",
|
|
"analysis_duration_s": 1.23,
|
|
"upload_duration_s": None,
|
|
"result": "---\nsource: invoice.pdf\n---\n# Title",
|
|
"error": None,
|
|
}
|
|
assert entry["status"] == DocumentStatus.READY
|
|
assert entry["filename"] == "invoice.pdf"
|
|
assert entry["analyzer_id"] == "prebuilt-documentSearch"
|
|
assert entry["analysis_duration_s"] == 1.23
|
|
assert entry["upload_duration_s"] is None
|
|
assert isinstance(entry["result"], str)
|
|
|
|
def test_failed_entry(self) -> None:
|
|
entry: DocumentEntry = {
|
|
"status": DocumentStatus.FAILED,
|
|
"filename": "bad.pdf",
|
|
"media_type": "application/pdf",
|
|
"analyzer_id": "prebuilt-documentSearch",
|
|
"analyzed_at": "2026-01-01T00:00:00+00:00",
|
|
"analysis_duration_s": 0.5,
|
|
"upload_duration_s": None,
|
|
"result": None,
|
|
"error": "Service unavailable",
|
|
}
|
|
assert entry["status"] == DocumentStatus.FAILED
|
|
assert entry["error"] == "Service unavailable"
|
|
assert entry["result"] is None
|
|
|
|
|
|
class TestFileSearchConfig:
|
|
def test_required_fields(self) -> None:
|
|
backend = AsyncMock()
|
|
tool = {"type": "file_search", "vector_store_ids": ["vs_123"]}
|
|
config = FileSearchConfig(backend=backend, vector_store_id="vs_123", file_search_tool=tool)
|
|
assert config.backend is backend
|
|
assert config.vector_store_id == "vs_123"
|
|
assert config.file_search_tool is tool
|
|
|
|
def test_from_openai_factory(self) -> None:
|
|
from agent_framework_azure_contentunderstanding._file_search import OpenAIFileSearchBackend
|
|
|
|
client = AsyncMock()
|
|
tool = {"type": "file_search", "vector_store_ids": ["vs_abc"]}
|
|
config = FileSearchConfig.from_openai(client, vector_store_id="vs_abc", file_search_tool=tool)
|
|
assert isinstance(config.backend, OpenAIFileSearchBackend)
|
|
assert config.vector_store_id == "vs_abc"
|
|
assert config.file_search_tool is tool
|