Select phase-specific working context and retain auditable source evidence

tests/test_compact_diagnosis.py

@@ -70,7 +70,7 @@ def test_new_diagnosis_keeps_frozen_context_and_uses_compact_request(investigate
     adapter = FinalAdapter(True)
     result = build(DiagnosisBuilder(store, gateway(adapter)))
     request = adapter.requests[0]
-    assert request['prompt_version'] == 'diagnosis_v4'
+    assert request['prompt_version'] == 'diagnosis_v5'
     visible = restore(json.loads(request['messages'][1]['content'])['input'])
     with PackageReader(result.package) as reader:
         doc = json.loads(reader.read_bytes(result.diagnosis_ref))

tests/test_compact_handoff.py

@@ -65,7 +65,7 @@ def test_retry_gets_actionable_feedback_and_portable_replay(diagnosed, tmp_path,
     class Correcting(RequestAdapter):
         async def generate(self, config, request, **kwargs):
             response = await super().generate(config, request, **kwargs)
-            assert request['prompt_version'] == (first_version if self.calls == 1 else 'change_request_v5')
+            assert request['prompt_version'] == (first_version if self.calls == 1 else 'change_request_v6')
             if self.calls == 1:
                 response.document['affected_scope'][0]['source_ref'] = 'wrong.cpp'
             else:

tests/test_diagnosis_builder.py

@@ -218,7 +218,7 @@ def test_legacy_rejection_upgrades_next_attempt_without_rewriting_context(invest
     assert build(builder).status=='REJECTED'
     assert adapter.requests[0]['prompt_version']=='diagnosis_v1'
     assert build(builder).status=='COMPLETED'
-    assert adapter.requests[1]['prompt_version']=='diagnosis_v4'
+    assert adapter.requests[1]['prompt_version']=='diagnosis_v5'
     received=restore(json.loads(adapter.requests[1]['messages'][1]['content'])['input'])
     assert received['validation_feedback'][0]['code']=='DIAGNOSIS_SELECTION'
     assert build(builder).reused and adapter.calls==2

tests/test_entity_resolution.py

@@ -82,7 +82,7 @@ class Model:
                 document["resolutions"][0]["candidate_id"] = "K9999"
         else:
             document = payload()
-            if version in {"case_interpretation_resolved_v3", "case_interpretation_resolved_v4", "case_interpretation_resolved_v5", "case_interpretation_resolved_v6", "case_interpretation_resolved_v7"}:
+            if version in {"case_interpretation_resolved_v3", "case_interpretation_resolved_v4", "case_interpretation_resolved_v5", "case_interpretation_resolved_v6", "case_interpretation_resolved_v7","case_interpretation_resolved_v8"}:
                 document.update(described_behavior=[],provisional_behavior_gap=None)
             data = restore(json.loads(request["messages"][1]["content"])["input"])
             selected = [(k,v) for k,v in data["sources"].items() if v["kind"] == "entity" and v["case_pointer"].startswith("/entity_resolution/")]
@@ -96,7 +96,7 @@ class Model:
             if self.omit_resolved:
                 self.omit_resolved -= 1
                 document["relevant_entities"] = payload()["relevant_entities"]
-            if version in {'case_interpretation_resolved_v4','case_interpretation_resolved_v5','case_interpretation_resolved_v6','case_interpretation_resolved_v7'}:
+            if version in {'case_interpretation_resolved_v4','case_interpretation_resolved_v5','case_interpretation_resolved_v6','case_interpretation_resolved_v7','case_interpretation_resolved_v8'}:
                 from viano_bug_analysis.analysis.quality import unnamed_entity_reasons
                 reasons = unnamed_entity_reasons(data)
                 for entity in document['relevant_entities']:
@@ -133,7 +133,7 @@ def test_resolves_unrecorded_subject_preserves_case_and_portable_replay(built_ca
     model = Model(); service = service_for(store)
     result = run(store, model, service)
     assert result.status == "COMPLETED" and PackageValidator().validate(result.package).valid
-    assert [r["prompt_version"] for r in model.requests] == ["entity_resolution_plan_v4","entity_resolution_assessment_v4","case_interpretation_resolved_v7"]
+    assert [r["prompt_version"] for r in model.requests] == ["entity_resolution_plan_v4","entity_resolution_assessment_v4","case_interpretation_resolved_v8"]
     assert len(service.database.calls) == 1
     assert service.database.calls[0]["filters"] == [{"column":"name","operator":"contains","value":"switch"}]
     with PackageReader(result.package) as reader:
@@ -248,7 +248,7 @@ def test_search_cannot_be_grounded_in_a_capture_filename(built_case):
 def test_empty_plan_still_supports_descriptive_quality_contract(built_case):
     store=built_case[0];model=Model(plan={'searches':[]});service=service_for(store)
     assert run(store,model,service).status=='COMPLETED'
-    assert model.requests[-1]['prompt_version']=='case_interpretation_resolved_v7' and not service.database.calls
+    assert model.requests[-1]['prompt_version']=='case_interpretation_resolved_v8' and not service.database.calls
 
 
 def test_trial_phase_stop_includes_resolution_and_is_idempotent(built_case):
@@ -409,7 +409,7 @@ def test_third_assessment_can_use_lower_reasoning_without_resetting_history(buil
     assert len(service.database.calls) == 1
     assert model.efforts == [('entity_resolution_plan_v4','medium'),
         ('entity_resolution_assessment_v4','medium'),('entity_resolution_assessment_v4','medium'),
-        ('entity_resolution_assessment_v4','low'),('case_interpretation_resolved_v7','medium')]
+        ('entity_resolution_assessment_v4','low'),('case_interpretation_resolved_v8','medium')]
     with PackageReader(result.package) as reader:
         saved = json.loads(reader.read_bytes('analysis/interpretations/0001/entity-resolution/assessment.json'))
         assert saved['payload']['attempt'] == 3

tests/test_hypothesis_builder.py

@@ -94,7 +94,7 @@ def test_generation_budget_registry_and_preservation(interpreted_case):
             if name != "manifest.json": assert before.read_bytes(name) == after.read_bytes(name)
     assert original.read_bytes() == original_bytes
     assert len(adapter.requests) == 1
-    assert adapter.requests[0]["prompt_version"] == "hypotheses_v3"
+    assert adapter.requests[0]["prompt_version"] == "hypotheses_v4"
     assert case_builder.build("case-A","stable-package").reused
     assert asyncio.run(CaseInterpreter(store,gateway(adapter)).interpret("case-A","stable-package")).reused
 

tests/test_phase_selection.py

@@ -0,0 +1,72 @@
+import copy
+import json
+from viano_bug_analysis.analysis.phase_selection import select_context
+from viano_bug_analysis.analysis.investigation_focus import focused_view
+from viano_bug_analysis.analysis.investigation_blocks import restore_blocks
+from test_investigation_consolidation import populated
+
+
+def sources():
+    return {'sources':{
+        'O0001':{'kind':'observation','case_pointer':'/human_observations/0','data':{'text':'Nothing happened','provenance':{'author':'Tester','observed_at':'old-build','source_ref':'observation.json','json_pointer':'/0'}}},
+        'F0001':{'kind':'fact','case_pointer':'/runtime_facts/0','data':{'value':{'row':{'path':'a','sha256':'b','value':None,'flag':False},'coverage':'complete_filtered_rows','truncated':False},'provenance':{'snapshot_id':'snapshot-A','source_ref':'capture.json'}}},
+        'N0001':{'kind':'entity','case_pointer':'/entity_resolution/entities/0','data':{'id':'17','type':'item','provenance':{'source_ref':'capture.json'}}},
+        'X0001':{'kind':'unread_reference','case_pointer':'/source_context/refs/0','data':{'path':'unread.cpp','sha256':'a'*64}},
+        'D0001':{'kind':'data_quality','case_pointer':'/quality/0','data':{'text':'Observation predates source revision'}}},
+        'case_ref':'case.json','case_sha256':'x'*64,'case':{'case_id':'C'}}
+
+
+def test_interpretation_omits_unread_catalog_without_removing_facts_or_identity_links():
+    c=sources();before=copy.deepcopy(c);audit=[]
+    v=select_context(c,'interpretation',audit_out=audit)
+    assert 'X0001' not in v['sources'] and '/sources/X0001' in audit
+    assert v['unread_inventory']['counts']=={'unread_reference':1}
+    assert v['sources']['F0001']['data'] == c['sources']['F0001']['data']
+    assert v['sources']['N0001']==c['sources']['N0001']
+    assert v['sources']['O0001']['data']['provenance']['observed_at']=='old-build'
+    assert v['sources']['O0001']['data']['provenance']['source_ref']=='observation.json'
+    assert c==before and select_context(c,'interpretation')==v
+
+
+def test_hypotheses_keep_all_interpretations_facts_prior_feedback_and_observations():
+    c={'case_context':sources(),'interpretation_sources':{'I0001':{'kind':'unknowns','interpretation_pointer':'/unknowns/0','data':{'text':'Deployment is unknown','source_ids':['D0001']}}},'policy':{},'prior_generations':[{'failed_patch':'Did not change behavior'}]}
+    v=select_context(c,'hypotheses')
+    assert v['interpretation_sources']['I0001']['data']==c['interpretation_sources']['I0001']['data']
+    assert v['prior_generations']==c['prior_generations']
+    assert set(v['case_context']['sources'])=={'O0001','F0001','N0001','D0001'}
+
+
+def test_diagnosis_omits_plans_and_bookkeeping_retains_every_evidence_and_uncertainty():
+    h={'proposal':{'title':'Missing hook','mechanism':'May be missing','falsifying_evidence':['Hook exists'],'rationale':'Early speculation','open_questions':['Hook present?']},'notes':[{'text':'May be missing'},{'text':'Hook found; old deployment unknown'}],'questions':[{'id':'Q1','text':'Hook present?','resolved':True},{'id':'Q2','text':'Which deployment?','resolved':False}],'evidence_refs':['E1'],'confidence':'weakened','disposition':'active'}
+    c={'case':{'case':{},'human_observations':['Nothing moved'],'runtime_facts':{'facts':[{'id':'F1','value':False}],'raw_refs':['unread']},'inputs':['huge catalog']},'investigation':{'hypotheses':{'H1':h},'active':None},'evidence':{'E1':{'content':{'items':[],'coverage':'complete_filtered_rows','truncated':False}}},'interpretation':{'contradictions':['Old observation versus new code'],'unknowns':['Deployment']},'budget':{'seen_evidence':['hash'],'accounts':{'H1':{'remaining':80,'status':'investigating','actions':{'old':'history'}}}}}
+    before=copy.deepcopy(c);audit=[];v=select_context(c,'diagnosis',audit_out=audit)
+    assert v['evidence']==c['evidence'] and v['interpretation']==c['interpretation']
+    assert v['case']['runtime_facts']['facts']==c['case']['runtime_facts']['facts']
+    assert v['investigation']['hypotheses']['H1']['notes']==h['notes'][-1:]
+    assert v['investigation']['hypotheses']['H1']['closed_questions']=={'Q1':'Hook present?'}
+    assert '/investigation/hypotheses/H1/notes/0' in audit
+    assert c==before
+
+
+def test_investigation_keeps_latest_note_and_can_recall_older_counterevidence():
+    c=populated();c['prompt_version']='investigation_project_v9';c['budget']['accounts']['H1']['actions']={}
+    h=c['hypotheses']['H1'];h['evidence_refs']=['E000002'];h['notes']=['old speculation','current counterevidence']
+    audit=[]
+    assert set(focused_view(c,audit_out=audit)['evidence'])=={'E000001'}
+    assert audit==['/hypotheses/H1/notes/0']
+    c['recalled_evidence']=['E000002']
+    v=restore_blocks(focused_view(c))
+    assert set(v['evidence'])=={'E000001','E000002'}
+    assert v['hypotheses']['H1']['notes']==['current counterevidence']
+    assert c['hypotheses']['H1']['notes']==['old speculation','current counterevidence']
+    c['prompt_version']='investigation_project_v8'
+    assert len(focused_view(c)['hypotheses']['H1']['notes'])==2
+
+
+def test_handoff_keeps_repair_constraints_and_evidence_without_search_direction():
+    c={'case':{'human_observations':['Absent'],'data_quality':{'warnings':['Snapshot only']}},'interpretation':{'investigation_direction':'search more','contradictions':['different versions'],'unknowns':['Placement coordinates'],'relevant_entities':['typed id']},'evidence':{'E1':{'content':{'items':[],'coverage':'complete_filtered_rows'},'content_sha256':'hash'}},'local_context':{'capture':{'allowed_evidence_refs':['E1']}},'policy':{'rules':['No invented coordinates']}}
+    v=select_context(c,'handoff')
+    assert 'investigation_direction' not in v['interpretation']
+    assert v['interpretation']['unknowns']==c['interpretation']['unknowns']
+    assert v['evidence']['E1']['content']==c['evidence']['E1']['content']
+    assert v['local_context']==c['local_context'] and v['policy']==c['policy']

tests/test_project_database_integration.py

@@ -94,7 +94,7 @@ def test_real_contextual_identity_resolution_with_fixture_llm(service, tmp_path)
                 assert any(e['id']=='23486' for e in entities.values())
                 resolved=next(k for k,e in entities.items() if e['id']=='23487')
                 doc=missing_payload()
-                if request["prompt_version"]in {"case_interpretation_resolved_v3","case_interpretation_resolved_v4","case_interpretation_resolved_v5","case_interpretation_resolved_v6","case_interpretation_resolved_v7"}:
+                if request["prompt_version"]in {"case_interpretation_resolved_v3","case_interpretation_resolved_v4","case_interpretation_resolved_v5","case_interpretation_resolved_v6","case_interpretation_resolved_v7","case_interpretation_resolved_v8"}:
                     doc.update(described_behavior=[{'text':'The quest describes catching wild creatures using a net while intoxicated or wearing goggles.',
                         'source_ids':[self.mention],'basis':'local_description','verification':'not_independently_verified'}],
                         provisional_behavior_gap={'text':'The tester does not see these creatures despite wearing goggles.',

tests/test_project_research.py

@@ -204,7 +204,7 @@ def test_model_loop_uses_project_tools_and_compact_previous_result(tool_case, re
             if previous:
                 assert context["evidence"][eid]["content"]["items"]
             assert "inputs" not in context["case"]
-            assert request["prompt_version"]=="investigation_project_v8"
+            assert request["prompt_version"]=="investigation_project_v9"
             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()}}

tests/test_trial.py

@@ -27,9 +27,9 @@ class PipelineAdapter:
 
     async def generate(self, config, request, **kwargs):
         self.calls += 1
-        phase = {"case_interpretation_v1": "case", "hypotheses_v1": "hypotheses", "hypotheses_v2": "hypotheses", "hypotheses_v3": "hypotheses",
-                 "investigation_v1": "loop", "investigation_v2": "loop", "investigation_v3": "loop", "diagnosis_v1": "diagnosis", "diagnosis_v2": "diagnosis", "diagnosis_v3": "diagnosis", "diagnosis_v4": "diagnosis",
-                 "change_request_v1": "request", "change_request_v2": "request", "change_request_v3": "request", "change_request_v4": "request", "change_request_v5": "request"}[request["prompt_version"]]
+        phase = {"case_interpretation_v1": "case", "hypotheses_v1": "hypotheses", "hypotheses_v2": "hypotheses", "hypotheses_v3": "hypotheses", "hypotheses_v4": "hypotheses",
+                 "investigation_v1": "loop", "investigation_v2": "loop", "investigation_v3": "loop", "diagnosis_v1": "diagnosis", "diagnosis_v2": "diagnosis", "diagnosis_v3": "diagnosis", "diagnosis_v4": "diagnosis", "diagnosis_v5": "diagnosis",
+                 "change_request_v1": "request", "change_request_v2": "request", "change_request_v3": "request", "change_request_v4": "request", "change_request_v5": "request", "change_request_v6": "request"}[request["prompt_version"]]
         adapter = self.adapters[phase]
         return await adapter.generate(config, request, **kwargs)