Encode investigation source as contiguous plain-text code blocks

tests/test_investigation_blocks.py

@@ -0,0 +1,86 @@
+import copy
+
+from viano_bug_analysis.analysis.investigation_blocks import block_view, restore_blocks
+from viano_bug_analysis.analysis.investigation_consolidation import consolidated_view
+from viano_bug_analysis.analysis.investigation_view import working_view
+from viano_bug_analysis.analysis.investigation_prompt import build_prompt
+from viano_bug_analysis.analysis.model_context import model_json
+from test_investigation_consolidation import populated, capture
+
+
+def checked(c):
+    original = copy.deepcopy(c)
+    view = block_view(c)
+    assert model_json(restore_blocks(view)) == model_json(working_view(c))
+    assert len(model_json(view)) <= len(model_json(consolidated_view(c)))
+    assert c == original
+    assert model_json(block_view(c)) == model_json(view)
+    return view
+
+
+def test_contiguous_code_has_one_start_line_and_plain_text_strings():
+    c = populated()
+    c['prompt_version'] = 'investigation_project_v7'
+    v = checked(c)
+    source = v['shared_sources']['FILE0001']
+    assert source['line_defaults'] == {'text_truncated': False}
+    assert source['blocks'] == [{'start_line': 1, 'lines': ['code line '+str(i) for i in range(1, 121)]}]
+    assert 'lines' not in source
+    for entry in v['evidence'].values():
+        assert entry['content']['items'][0]['result']['items']['encoding'] == 'shared_source_blocks_v1'
+
+
+def test_out_of_order_ranges_do_not_fill_gaps_or_change_result_order():
+    c = populated()
+    c['evidence']['E000001']['content']['items'] = [capture(range(200, 280))]
+    c['evidence']['E000002']['content']['items'] = [capture(range(1, 81))]
+    v = checked(c)
+    assert [b['start_line'] for b in v['shared_sources']['FILE0001']['blocks']] == [1, 200]
+
+
+def test_flags_missing_values_conflicts_and_unicode_are_lossless():
+    c = populated()
+    items = c['evidence']['E000002']['content']['items'][0]['result']['items']
+    items[0]['text_truncated'] = True
+    items[1]['text_truncated'] = 0  # Must not conflate 0 and false.
+    del items[2]['text_truncated']
+    items[3]['text'] = '\tUnicode ß with embedded\nnewline and \\ escapes'
+    view = checked(c)
+    assert view['shared_sources']['FILE0001']['conflicting_lines'] == [41, 42, 43, 44]
+
+
+def test_separate_versions_and_duplicate_result_records_remain_distinct():
+    c = populated()
+    c['evidence']['E000002']['content']['items'] = [capture(range(1, 81), sha='c'*64)]
+    checked(c)
+    c['evidence']['E000002']['content']['items'] = [capture([3, 3, 1])]
+    checked(c)
+
+
+def test_v6_prompt_is_unchanged_and_v7_uses_same_output_schema():
+    c = populated()
+    old = build_prompt(c)
+    assert old['messages'][1]['content'] == model_json({'task':'investigate_hypothesis', 'input':consolidated_view(c), 'output_schema':old['output_schema']})
+    c['prompt_version'] = 'investigation_project_v7'
+    new = build_prompt(c)
+    assert new['output_schema'] == old['output_schema']
+    assert new['messages'][1]['content'] == model_json({'task':'investigate_hypothesis', 'input':block_view(c), 'output_schema':new['output_schema']})
+
+
+def test_new_file_aliases_resolve_before_the_normal_tool_validation(monkeypatch):
+    from types import SimpleNamespace
+    from viano_bug_analysis.analysis.investigator import Investigator
+    c = populated()
+    c['prompt_version'] = 'investigation_project_v7'
+    state = {'case_id':'case','package_id':'package','analysis_revision':1,'prompt_protocol':2,
+             'active':{'hypothesis_id':'H1','iteration':1,'context_ref':'context.json'}}
+    class Reader:
+        def __init__(self, *args): pass
+        def __enter__(self): return self
+        def __exit__(self, *args): pass
+    monkeypatch.setattr('viano_bug_analysis.analysis.investigator.PackageReader', Reader)
+    fake = SimpleNamespace(store=SimpleNamespace(limits=None), _latest=lambda *a:'package.zip', _read=lambda *a:c)
+    action = {'operation':'project.query','arguments':{'kind':'source.read','path':'FILE0001','start_line':1,'end_line':3}}
+    original = copy.deepcopy(action)
+    assert Investigator._tool_request(fake, state, action)['requests'][0]['arguments']['path'] == 'code.cpp'
+    assert action == original

tests/test_project_research.py

@@ -203,7 +203,7 @@ def test_model_loop_uses_project_tools_and_compact_previous_result(tool_case):
             if previous:
                 assert context["evidence"][eid]["content"]["items"]
             assert "inputs" not in context["case"]
-            assert request["prompt_version"]=="investigation_project_v6"
+            assert request["prompt_version"]=="investigation_project_v7"
             reply={"assessment":{"semantic_score":50,"reason":"Scoped fact","evidence_refs":[eid]} if previous else None,
                    "update":{"confidence":"plausible","evidence_refs":[eid] if previous else [],"resolve_questions":[],"add_questions":[],"note":"Query typed identity"},
                    "next":{"kind":"finish","reason":"Check complete"} if previous else {"kind":"tool","operation":"project.query","arguments":rows()}}