ed
8f11340b38
Per post_module_taxonomy_de_cruft_20260627 Phase 2 (FR7). Each
'from src.models import X' for a moved class is rewritten to
'from src.<destination> import X':
Ticket, Track, WorkerContext, TrackState, TrackMetadata,
ThinkingSegment, EMPTY_TRACK_STATE -> src.mma
ProjectContext, ProjectMeta, ProjectOutput, ProjectFiles,
ProjectScreenshots, ProjectDiscussion, EMPTY_PROJECT_CONTEXT -> src.project
FileItem, Preset, ContextPreset, ContextFileEntry,
NamedViewPreset -> src.project_files
Tool, ToolPreset -> src.tool_presets
BiasProfile -> src.tool_bias
TextEditorConfig, ExternalEditorConfig,
EMPTY_TEXT_EDITOR_CONFIG -> src.external_editor
Persona -> src.personas
WorkspaceProfile -> src.workspace_manager
MCPServerConfig, MCPConfiguration, VectorStoreConfig,
RAGConfig, load_mcp_config -> src.mcp_client
NOT touched (kept on src.models; Phase 3 or Phase 4 will move them):
GenerateRequest, ConfirmRequest, DEFAULT_TOOL_CATEGORIES, Metadata, PROVIDERS
Migration was performed by the one-time script
scripts/tier2/artifacts/post_module_taxonomy_de_cruft_20260627/migrate_imports.py
which uses a class-to-module map and re.sub() to rewrite each
'from src.models import X' line.
Total: 85 import lines rewritten across 71 files.
Note: this commit depends on the v2 SHIPPED work
(origin/tier2/module_taxonomy_refactor_20260627) being merged into
this branch NEXT. On master (without the v2 SHIPPED commits), the
destination modules do not exist and these imports would fail.
55 lines
2.3 KiB
Python
55 lines
2.3 KiB
Python
import re
|
|
|
|
from typing import List, Tuple
|
|
|
|
from src.mma import ThinkingSegment
|
|
|
|
|
|
def parse_thinking_trace(text: str) -> Tuple[List[ThinkingSegment], str]:
|
|
"""
|
|
Parses thinking segments from text and returns (segments, response_content).
|
|
Support extraction of thinking traces from <thinking>...</thinking>, <thought>...</thought>,
|
|
<think>...</think> (half-width form), and blocks prefixed with Thinking:.
|
|
[C: tests/test_thinking_trace.py:test_parse_empty_response, tests/test_thinking_trace.py:test_parse_multiple_markers, tests/test_thinking_trace.py:test_parse_no_thinking, tests/test_thinking_trace.py:test_parse_text_thinking_prefix, tests/test_thinking_trace.py:test_parse_thinking_with_empty_response, tests/test_thinking_trace.py:test_parse_xml_thinking_tag, tests/test_thinking_trace.py:test_parse_xml_thought_tag, tests/test_thinking_trace.py:test_parse_half_width_think_tag]
|
|
"""
|
|
segments = []
|
|
|
|
# 1. Extract <thinking> and <thought> tags
|
|
current_text = text
|
|
# Combined pattern for tags
|
|
tag_pattern = re.compile(r'<(thinking|thought|think)>(.*?)</\1>', re.DOTALL | re.IGNORECASE)
|
|
|
|
def extract_tags(txt: str) -> Tuple[List[ThinkingSegment], str]:
|
|
found_segments = []
|
|
|
|
def replace_func(match):
|
|
marker = match.group(1).lower()
|
|
content = match.group(2).strip()
|
|
found_segments.append(ThinkingSegment(content=content, marker=marker))
|
|
return ""
|
|
|
|
remaining = tag_pattern.sub(replace_func, txt)
|
|
return found_segments, remaining
|
|
|
|
tag_segments, remaining = extract_tags(current_text)
|
|
segments.extend(tag_segments)
|
|
|
|
# 2. Extract Thinking: prefix
|
|
# This usually appears at the start of a block and ends with a double newline or a response marker.
|
|
thinking_colon_pattern = re.compile(r'(?:^|\n)Thinking:\s*(.*?)(?:\n\n|\nResponse:|\nAnswer:|$)', re.DOTALL | re.IGNORECASE)
|
|
|
|
def extract_colon_blocks(txt: str) -> Tuple[List[ThinkingSegment], str]:
|
|
found_segments = []
|
|
|
|
def replace_func(match):
|
|
content = match.group(1).strip()
|
|
if content: found_segments.append(ThinkingSegment(content=content, marker="Thinking:"))
|
|
return "\n\n"
|
|
|
|
res = thinking_colon_pattern.sub(replace_func, txt)
|
|
return found_segments, res
|
|
|
|
colon_segments, final_remaining = extract_colon_blocks(remaining)
|
|
segments.extend(colon_segments)
|
|
return segments, final_remaining.strip()
|