Harden historical anchor hydration edges

This commit is contained in:
Frank Song committed 2026-07-20 17:22:02 +08:00
1 parent a91f34a5f0
commit c2b5a54b38
3 files changed
+171 -13

No files matched your search

+2
View File
@@ -928,6 +928,7 @@
);
const done=_activityRowToolDone(kind,status,payload);
const isError=_activityRowToolIsError(status,payload);
const isDiff=_own(payload,'is_diff')===true||_own(payload,'isDiff')===true;
const signatureParts=[
toolName,
toolCallId||'',
@@ -943,6 +944,7 @@
output:_sanitizePayload(_own(payload,'output'))??null,
done,
is_error:isError,
...(isDiff?{is_diff:true}:{}),
duration:_activityPayloadFirst(payload,['duration','duration_seconds','elapsed'])??null,
started_at:_activityPayloadFirst(payload,['started_at','startedAt'])??null,
signature:signatureParts.join('|'),
+45 -11
View File
@@ -12309,6 +12309,7 @@ function _anchorSceneToolCallFromRow(row, opts){
)||'',
done:settled?true:(tool.done!==null&&tool.done!==undefined?tool.done:(row.status!=='running'&&row.status!=='pending')),
is_error:!!(tool.is_error||payload.is_error||row.status==='error'||row.status==='failed'),
is_diff:!!(tool.is_diff||payload.is_diff||payload.isDiff),
duration:tool.duration||payload.duration||payload.duration_seconds,
started_at:firstValidTimestampSeconds(tool.started_at, payload.started_at, rowTs),
created_at:firstValidTimestampSeconds(tool.created_at, payload.created_at, rowTs),
@@ -14735,7 +14736,7 @@ function _idLinkedHistoricalToolArguments(toolCall){
const fn=toolCall.function;
if(!fn||typeof fn!=='object'||Array.isArray(fn)) return null;
const raw=fn.arguments;
if(raw===undefined||raw===null||raw==='') return {};
if(raw===undefined||raw===null||raw==='') return null;
if(raw&&typeof raw==='object'&&!Array.isArray(raw)) return raw;
if(typeof raw!=='string') return null;
try{
@@ -14747,12 +14748,33 @@ function _idLinkedHistoricalToolArguments(toolCall){
}
function _idLinkedHistoricalToolResultRaw(message){
if(!message||typeof message!=='object') return '';
if(!message||typeof message!=='object') return null;
const content=message.content;
if(typeof content==='string') return content;
if(content===undefined||content===null) return '';
try{return JSON.stringify(content);}
catch(e){return String(content||'');}
return typeof content==='string'?content:null;
}
function _idLinkedHistoricalRedactSnippet(value){
let text=String(value||'');
if(!text) return '';
if(typeof _redactToolTargetLabel==='function'){
try{text=_redactToolTargetLabel(text);}
catch(e){}
}
return text;
}
function _idLinkedHistoricalHasVisibleSidecar(message){
if(!message||typeof message!=='object') return false;
const visibleKeys=['attachments','_attachments','_statusCard','status_card','statusCard','card','cards','artifact','artifacts','files','images','media'];
for(const key of visibleKeys){
if(!Object.prototype.hasOwnProperty.call(message,key)) continue;
const value=message[key];
if(value===undefined||value===null||value===false) continue;
if(Array.isArray(value)&&value.length===0) continue;
if(typeof value==='object'&&!Array.isArray(value)&&Object.keys(value).length===0) continue;
return true;
}
return false;
}
// Claim legacy settled ownership only when the transcript itself proves a
@@ -14775,18 +14797,25 @@ function _idLinkedHistoricalTurnScene(messages, turnStart, turnEnd, options){
for(let rawIdx=start;rawIdx<end;rawIdx++){
const message=list[rawIdx];
if(!message||typeof message!=='object') continue;
const role=message.role;
if(role==='user'&&rawIdx===start) continue;
if(message._anchor_activity_scene) return null;
if(message.role==='assistant'){
if(role==='assistant'){
assistantIndexes.push(rawIdx);
const visibleText=_idLinkedHistoricalMessageText(message);
const reasoningText=_assistantReasoningPayloadText(message);
if(visibleText) visibleAssistantIndexes.push(rawIdx);
if(reasoningText) return null;
if(_idLinkedHistoricalHasVisibleSidecar(message)) return null;
if(Array.isArray(message._partial_tool_calls)&&message._partial_tool_calls.length) return null;
if(Array.isArray(message.content)&&message.content.some(part=>part&&typeof part==='object'&&part.type==='tool_use')) return null;
const toolCalls=Array.isArray(message.tool_calls)?message.tool_calls:[];
if(toolCalls.length&&visibleText) return null;
if(!toolCalls.length) continue;
if(!toolCalls.length){
if(visibleText) continue;
return null;
}
if(message.content!==undefined&&message.content!==null&&message.content!=='') return null;
const messageRef=_idLinkedHistoricalMessageRef(message,rawIdx);
if(!declarationRefs.includes(messageRef)) declarationRefs.push(messageRef);
for(const toolCall of toolCalls){
@@ -14800,7 +14829,7 @@ function _idLinkedHistoricalTurnScene(messages, turnStart, turnEnd, options){
}
continue;
}
if(message.role!=='tool') continue;
if(role!=='tool') return null;
const callId=String(message.tool_call_id||'').trim();
if(!callId||!declarationIds.has(callId)) return null;
const matches=resultsById.get(callId)||[];
@@ -14827,8 +14856,12 @@ function _idLinkedHistoricalTurnScene(messages, turnStart, turnEnd, options){
const declaration=declarations[index];
const resultEntry=resultsById.get(declaration.callId)[0];
const args=_toolArgsSnapshot(declaration.args);
const resultSnippet=_cliToolResultSnippet(_idLinkedHistoricalToolResultRaw(resultEntry.message));
const resultRaw=_idLinkedHistoricalToolResultRaw(resultEntry.message);
if(resultRaw===null) return null;
const resultSnippet=_idLinkedHistoricalRedactSnippet(_cliToolResultSnippet(resultRaw));
const patchSnippet=_cliPatchSnippetFromArgs(declaration.name,args);
const isDiff=_cliToolCardHasDiffSnippet(resultSnippet,patchSnippet);
const snippet=_idLinkedHistoricalRedactSnippet(_cliToolCardSnippet(resultSnippet,patchSnippet));
const status=String(resultEntry.message.status||'').trim().toLowerCase();
const isError=resultEntry.message.is_error===true||status==='error'||status==='failed'||status==='failure';
activityEvents.push({
@@ -14842,9 +14875,10 @@ function _idLinkedHistoricalTurnScene(messages, turnStart, turnEnd, options){
name:declaration.name,
args,
command:String(args.command||args.cmd||''),
snippet:_cliToolCardSnippet(resultSnippet,patchSnippet),
snippet,
done:true,
is_error:isError,
is_diff:isDiff,
assistant_msg_idx:declaration.rawIdx,
},
});
@@ -66,7 +66,8 @@ vm.runInContext(
sandbox,
{{filename:'assistant_turn_anchors.js'}}
);
sandbox._redactToolTargetLabel = value => String(value);
sandbox._redactToolTargetLabel = value => String(value)
.replace(/([A-Za-z0-9_]*(?:TOKEN|API[_-]?KEY|SECRET|PASSWORD)[A-Za-z0-9_]*\\s*=\\s*)(?:"[^"]*"|'[^']*'|\\S+)/gi, '$1[redacted]');
for(const name of [
'_clipCliToolSnippet',
@@ -77,12 +78,16 @@ for(const name of [
'_firstOwnedValue',
'_cliPatchSnippetFromArgs',
'_cliToolCardSnippet',
'_cliToolCardHasDiffSnippet',
'_anchorSceneToolCallFromRow',
'_toolArgsSnapshot',
'_assistantReasoningPayloadText',
'_idLinkedHistoricalMessageText',
'_idLinkedHistoricalMessageRef',
'_idLinkedHistoricalToolArguments',
'_idLinkedHistoricalToolResultRaw',
'_idLinkedHistoricalRedactSnippet',
'_idLinkedHistoricalHasVisibleSidecar',
'_idLinkedHistoricalTurnScene',
'_hydrateIdLinkedHistoricalToolScenes',
]){{
@@ -112,7 +117,12 @@ const second = {str(repeat).lower()}
const owners = messages
.map((message, index) => message && message._anchor_activity_scene ? {{index, scene:message._anchor_activity_scene}} : null)
.filter(Boolean);
console.log(JSON.stringify({{first, second, unchanged:afterFirst===JSON.stringify(messages), owners}}));
sandbox.owners = owners;
const toolCards = vm.runInContext(
"owners.map(owner => owner.scene.activity_rows.map(row => _anchorSceneToolCallFromRow(row, {{settled:true}})))",
sandbox
);
console.log(JSON.stringify({{first, second, unchanged:afterFirst===JSON.stringify(messages), owners, toolCards}}));
"""
result = subprocess.run(
[NODE, "-e", script],
@@ -301,6 +311,118 @@ def test_ambiguous_or_richer_historical_tool_shapes_keep_legacy_ownership(messag
assert data["owners"] == []
@pytest.mark.skipif(NODE is None, reason="node is required for Anchor hydration tests")
@pytest.mark.parametrize("content", [
{"stdout": "...", "env": "API_KEY=result-secret-123"},
[{"stdout": "ok"}],
None,
])
def test_non_string_historical_tool_results_keep_legacy_ownership(content):
messages = _linked_turn()
messages[2]["content"] = content
data = _run_hydration(messages)
assert data["first"] == 0
assert data["owners"] == []
@pytest.mark.skipif(NODE is None, reason="node is required for Anchor hydration tests")
def test_string_historical_tool_result_is_redacted_before_anchor_scene():
messages = _linked_turn()
messages[2]["content"] = '{"output":"API_KEY=result-secret-123"}'
data = _run_hydration(messages)
assert data["first"] == 1
row = data["owners"][0]["scene"]["activity_rows"][0]
assert "result-secret-123" not in json.dumps(row)
assert "API_KEY=[redacted]" in row["tool"]["snippet"]
@pytest.mark.skipif(NODE is None, reason="node is required for Anchor hydration tests")
@pytest.mark.parametrize(
"messages",
[
[
{"role": "user", "content": "Run it"},
{"role": "assistant", "content": None, "tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": "{}"}}]},
{"role": "system", "content": "visible system status"},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
[
{"role": "user", "content": "Run it"},
{"role": "assistant", "content": None, "tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": "{}"}}]},
{"role": "developer", "content": "visible developer note"},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
[
{"role": "user", "content": "Run it"},
{"role": "assistant", "content": None, "tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": "{}"}}]},
{"role": "function", "name": "legacy_func", "content": "legacy function output"},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
[
{"role": "user", "content": "Run it"},
{"role": "assistant", "content": None, "tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": "{}"}}]},
{"role": "assistant", "content": None, "tool_calls": []},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
[
{"role": "user", "content": "Run it"},
{
"role": "assistant",
"content": None,
"attachments": [{"name": "evidence.txt"}],
"tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": "{}"}}],
},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
[
{"role": "user", "content": "Run it"},
{
"role": "assistant",
"content": None,
"_statusCard": {"title": "Visible status"},
"tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": "{}"}}],
},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
[
{"role": "user", "content": "Run it"},
{"role": "assistant", "content": None, "tool_calls": [{"id": "call-1", "function": {"name": "terminal", "arguments": ""}}]},
{"role": "tool", "tool_call_id": "call-1", "content": "ok"},
{"role": "assistant", "content": "Done"},
],
],
)
def test_non_whitelisted_intermediate_records_keep_legacy_ownership(messages):
data = _run_hydration(messages)
assert data["first"] == 0
assert data["owners"] == []
@pytest.mark.skipif(NODE is None, reason="node is required for Anchor hydration tests")
def test_diff_historical_tool_result_preserves_diff_card_projection():
messages = _linked_turn()
messages[2]["content"] = "diff --git a/demo.txt b/demo.txt\n@@\n-old\n+new\n"
data = _run_hydration(messages)
assert data["first"] == 1
row = data["owners"][0]["scene"]["activity_rows"][0]
assert row["payload"]["is_diff"] is True
assert row["tool"]["is_diff"] is True
assert data["toolCards"][0][0]["is_diff"] is True
@pytest.mark.skipif(NODE is None, reason="node is required for Anchor hydration tests")
def test_event_building_helper_exceptions_keep_legacy_ownership():
data = _run_hydration(_linked_turn(), throw_helper=True)