fix: preserve original session coordinates through capture selection
This commit is contained in:
@@ -237,6 +237,7 @@ pub struct SessionEntryEvidence {
|
||||
pub segment_id: String,
|
||||
pub entry_ref: SessionEntryRef,
|
||||
pub origin: SessionEntryProvenance,
|
||||
/// Inclusive original-source positions in `segment_id`, not view/UI order.
|
||||
pub entry_range: [u64; 2],
|
||||
pub kind: ReferenceKind,
|
||||
pub tool_part: Option<ToolPart>,
|
||||
@@ -259,6 +260,7 @@ pub struct SessionCapture {
|
||||
session_id: String,
|
||||
segment_id: String,
|
||||
capture_id: String,
|
||||
view_entry_count: u64,
|
||||
entries: Arc<Vec<CapturedHistoryEntry>>,
|
||||
overview: Vec<OverviewItem>,
|
||||
index: Vec<ReferenceEntry>,
|
||||
@@ -271,6 +273,7 @@ impl SessionCapture {
|
||||
snapshot: SessionSnapshot,
|
||||
) -> Self {
|
||||
let segment_id = segment_id.into();
|
||||
let view_entry_count = snapshot.entries.len() as u64;
|
||||
let entries = snapshot
|
||||
.entries
|
||||
.into_iter()
|
||||
@@ -341,7 +344,7 @@ impl SessionCapture {
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
Self::from_projected(session_id.into(), segment_id, entries)
|
||||
Self::from_projected(session_id.into(), segment_id, view_entry_count, entries)
|
||||
}
|
||||
|
||||
pub fn new(
|
||||
@@ -350,6 +353,7 @@ impl SessionCapture {
|
||||
items: Vec<Item>,
|
||||
) -> Self {
|
||||
let segment_id = segment_id.into();
|
||||
let view_entry_count = items.len() as u64;
|
||||
let entries = items
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
@@ -371,15 +375,19 @@ impl SessionCapture {
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
Self::from_projected(session_id.into(), segment_id, entries)
|
||||
Self::from_projected(session_id.into(), segment_id, view_entry_count, entries)
|
||||
}
|
||||
|
||||
pub fn from_history_entries(
|
||||
/// Project a complete Host-fixed history whose source positions start at zero.
|
||||
/// Select a suffix with `select_order_range` on the resulting value instead
|
||||
/// of passing a rebased history vector: annotations do not carry source positions.
|
||||
pub fn from_complete_history(
|
||||
session_id: impl Into<String>,
|
||||
segment_id: impl Into<String>,
|
||||
entries: Vec<HistoryEntry<SessionHistoryMetadata>>,
|
||||
) -> Self {
|
||||
let segment_id = segment_id.into();
|
||||
let view_entry_count = entries.len() as u64;
|
||||
let entries = entries
|
||||
.into_iter()
|
||||
.enumerate()
|
||||
@@ -432,14 +440,20 @@ impl SessionCapture {
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
Self::from_projected(session_id.into(), segment_id, entries)
|
||||
Self::from_projected(session_id.into(), segment_id, view_entry_count, entries)
|
||||
}
|
||||
|
||||
fn from_projected(session_id: String, segment_id: String, dtos: Vec<CaptureEntryDto>) -> Self {
|
||||
fn from_projected(
|
||||
session_id: String,
|
||||
segment_id: String,
|
||||
view_entry_count: u64,
|
||||
dtos: Vec<CaptureEntryDto>,
|
||||
) -> Self {
|
||||
let dto = CaptureDto {
|
||||
version: CAPTURE_VERSION,
|
||||
session_id: session_id.clone(),
|
||||
segment_id: segment_id.clone(),
|
||||
view_entry_count,
|
||||
entries: dtos,
|
||||
};
|
||||
let capture_id = dto.fingerprint();
|
||||
@@ -589,6 +603,7 @@ impl SessionCapture {
|
||||
session_id,
|
||||
segment_id,
|
||||
capture_id,
|
||||
view_entry_count,
|
||||
entries: Arc::new(entries),
|
||||
overview,
|
||||
index,
|
||||
@@ -604,7 +619,8 @@ impl SessionCapture {
|
||||
&self.overview
|
||||
}
|
||||
|
||||
pub fn source_index_for_ref(&self, reference: &SessionEntryRef) -> Option<u64> {
|
||||
/// Capture-local UI position, not the original source position used by evidence.
|
||||
pub fn view_order_for_ref(&self, reference: &SessionEntryRef) -> Option<u64> {
|
||||
self.index
|
||||
.iter()
|
||||
.find(|entry| entry.id == *reference)
|
||||
@@ -624,12 +640,12 @@ impl SessionCapture {
|
||||
let min_entry_index = options
|
||||
.from
|
||||
.as_ref()
|
||||
.and_then(|reference| self.source_index_for_ref(reference))
|
||||
.and_then(|reference| self.view_order_for_ref(reference))
|
||||
.unwrap_or_else(|| options.min_entry_index.unwrap_or(0));
|
||||
let max_entry_index = options
|
||||
.through
|
||||
.as_ref()
|
||||
.and_then(|reference| self.source_index_for_ref(reference))
|
||||
.and_then(|reference| self.view_order_for_ref(reference))
|
||||
.unwrap_or(u64::MAX);
|
||||
let mut skipped = 0usize;
|
||||
let mut hits = Vec::new();
|
||||
@@ -787,24 +803,16 @@ impl SessionCapture {
|
||||
if entry.use_policy.is_some_and(|p| !p.memory_evidence) {
|
||||
return None;
|
||||
}
|
||||
let item = &self
|
||||
let captured = self
|
||||
.entries
|
||||
.iter()
|
||||
.find(|captured| captured.dto.order == entry.entry_range[0])?
|
||||
.item;
|
||||
let excerpt = render_item(item, entry, ReadDetail::Compact, 2 * 1024);
|
||||
.find(|captured| captured.dto.order == entry.entry_range[0])?;
|
||||
let excerpt = render_item(&captured.item, entry, ReadDetail::Compact, 2 * 1024);
|
||||
Some(SessionEntryEvidence {
|
||||
segment_id: self
|
||||
.entries
|
||||
.iter()
|
||||
.find(|captured| captured.dto.order == entry.entry_range[0])?
|
||||
.dto
|
||||
.source
|
||||
.segment_id
|
||||
.clone(),
|
||||
segment_id: captured.dto.source.segment_id.clone(),
|
||||
entry_ref: entry.id.clone(),
|
||||
origin: entry.origin.clone(),
|
||||
entry_range: entry.entry_range,
|
||||
entry_range: [captured.dto.source.entry_index; 2],
|
||||
kind: entry.kind,
|
||||
tool_part: entry.tool_part,
|
||||
label: entry.label.clone(),
|
||||
|
||||
@@ -307,6 +307,8 @@ pub struct CaptureDto {
|
||||
pub version: u32,
|
||||
pub session_id: String,
|
||||
pub segment_id: String,
|
||||
/// Extent of view order, including positions omitted by public projection.
|
||||
pub view_entry_count: u64,
|
||||
pub entries: Vec<CaptureEntryDto>,
|
||||
}
|
||||
|
||||
@@ -409,6 +411,9 @@ impl CaptureDto {
|
||||
{
|
||||
return Err(CaptureError::Invalid("entry identity"));
|
||||
}
|
||||
if entry.order >= self.view_entry_count {
|
||||
return Err(CaptureError::Invalid("entry outside view extent"));
|
||||
}
|
||||
if previous.is_some_and(|order| order >= entry.order) {
|
||||
return Err(CaptureError::Invalid("entry order"));
|
||||
}
|
||||
@@ -598,6 +603,7 @@ impl SessionCapture {
|
||||
version: CAPTURE_VERSION,
|
||||
session_id: self.session_id.clone(),
|
||||
segment_id: self.segment_id.clone(),
|
||||
view_entry_count: self.view_entry_count,
|
||||
entries: self.entries.iter().map(|e| e.dto.clone()).collect(),
|
||||
}
|
||||
}
|
||||
@@ -607,6 +613,7 @@ impl SessionCapture {
|
||||
Ok(Self::from_projected(
|
||||
dto.session_id,
|
||||
dto.segment_id,
|
||||
dto.view_entry_count,
|
||||
dto.entries,
|
||||
))
|
||||
}
|
||||
@@ -618,11 +625,48 @@ impl SessionCapture {
|
||||
Self::try_from_dto(CaptureDto::decode(bytes, limits)?, limits)
|
||||
}
|
||||
|
||||
/// Select fixed view positions. UI order is rebased, while every original
|
||||
/// source identity/position, body, provenance and policy stays unchanged.
|
||||
pub fn select_order_range(&self, range: std::ops::Range<u64>) -> Result<Self, CaptureError> {
|
||||
if range.start > range.end || range.end > self.view_entry_count {
|
||||
return Err(CaptureError::InvalidRange);
|
||||
}
|
||||
let entries = self
|
||||
.entries()
|
||||
.filter(|entry| range.contains(&entry.order))
|
||||
.map(|entry| {
|
||||
let mut entry = entry.clone();
|
||||
entry.order -= range.start;
|
||||
entry
|
||||
})
|
||||
.collect();
|
||||
Ok(Self::from_projected(
|
||||
self.session_id.clone(),
|
||||
self.segment_id.clone(),
|
||||
range.end - range.start,
|
||||
entries,
|
||||
))
|
||||
}
|
||||
|
||||
/// Host-owned target selection may exclude entries without renumbering either
|
||||
/// the fixed view or its original sources. No source I/O or business policy is applied.
|
||||
pub fn retain_entries(&self, mut include: impl FnMut(&CaptureEntryDto) -> bool) -> Self {
|
||||
Self::from_projected(
|
||||
self.session_id.clone(),
|
||||
self.segment_id.clone(),
|
||||
self.view_entry_count,
|
||||
self.entries()
|
||||
.filter(|entry| include(entry))
|
||||
.cloned()
|
||||
.collect(),
|
||||
)
|
||||
}
|
||||
|
||||
pub fn scoped_ref(
|
||||
&self,
|
||||
reference: &SessionEntryRef,
|
||||
) -> Result<ScopedSessionEntryRef, CaptureError> {
|
||||
if self.source_index_for_ref(reference).is_none() {
|
||||
if self.view_order_for_ref(reference).is_none() {
|
||||
return Err(CaptureError::UnknownReference);
|
||||
}
|
||||
Ok(ScopedSessionEntryRef {
|
||||
@@ -679,7 +723,7 @@ impl SessionCapture {
|
||||
.from
|
||||
.as_ref()
|
||||
.map(|r| {
|
||||
self.source_index_for_ref(r)
|
||||
self.view_order_for_ref(r)
|
||||
.ok_or(CaptureError::UnknownReference)
|
||||
})
|
||||
.transpose()?;
|
||||
@@ -687,7 +731,7 @@ impl SessionCapture {
|
||||
.through
|
||||
.as_ref()
|
||||
.map(|r| {
|
||||
self.source_index_for_ref(r)
|
||||
self.view_order_for_ref(r)
|
||||
.ok_or(CaptureError::UnknownReference)
|
||||
})
|
||||
.transpose()?;
|
||||
@@ -710,7 +754,7 @@ impl SessionCapture {
|
||||
match selector {
|
||||
ReadSelector::Id(id) => {
|
||||
let reference = SessionEntryRef::parse(id).ok_or(CaptureError::UnknownReference)?;
|
||||
self.source_index_for_ref(&reference)
|
||||
self.view_order_for_ref(&reference)
|
||||
.ok_or(CaptureError::UnknownReference)?;
|
||||
}
|
||||
ReadSelector::EntryRange([start, end]) => {
|
||||
|
||||
@@ -77,7 +77,7 @@ fn public_consumer_roundtrip_retains_body_original_source_order_origin_and_indep
|
||||
Some(HistoryInputMetadata::new(usage(false, false, true), None, None).unwrap()),
|
||||
),
|
||||
];
|
||||
let capture = SessionCapture::from_history_entries("synthetic-session", "selected", entries);
|
||||
let capture = SessionCapture::from_complete_history("synthetic-session", "selected", entries);
|
||||
let mut dto = capture.to_dto();
|
||||
// The checked boundary also accepts entries retained from different original segments.
|
||||
dto.entries[0].source.segment_id = "original-a".into();
|
||||
@@ -115,6 +115,7 @@ fn public_consumer_roundtrip_retains_body_original_source_order_origin_and_indep
|
||||
assert!(restored.evidence_for("Erecording").is_none());
|
||||
let evidence = restored.evidence_for("Ememory").unwrap();
|
||||
assert_eq!(evidence.segment_id, "original-b");
|
||||
assert_eq!(evidence.entry_range, [3, 3]);
|
||||
assert!(evidence.excerpt.contains("memory-only"));
|
||||
let recorded = restored
|
||||
.slice(CapturePurpose::Recording, None, 10, 16_000)
|
||||
@@ -159,7 +160,7 @@ fn common_data_drops_reasoning_raw_system_and_private_payload_even_when_unindexe
|
||||
HistoryInputMetadata::new(usage(true, true, true), Some(payload.clone()), Some(public))
|
||||
.unwrap();
|
||||
let private = HistoryInputMetadata::new(usage(true, true, true), Some(payload), None).unwrap();
|
||||
let capture = SessionCapture::from_history_entries(
|
||||
let capture = SessionCapture::from_complete_history(
|
||||
"s",
|
||||
"segment",
|
||||
vec![
|
||||
@@ -195,7 +196,7 @@ fn common_data_drops_reasoning_raw_system_and_private_payload_even_when_unindexe
|
||||
// Filtered entries do not renumber the public source positions.
|
||||
assert_eq!(capture.to_dto().entries[0].order, 3);
|
||||
assert_eq!(
|
||||
capture.source_index_for_ref(&SessionEntryRef::parse("Eordinary").unwrap()),
|
||||
capture.view_order_for_ref(&SessionEntryRef::parse("Eordinary").unwrap()),
|
||||
Some(4)
|
||||
);
|
||||
}
|
||||
@@ -318,6 +319,7 @@ fn malformed_dtos_and_oversized_representations_are_rejected() {
|
||||
.is_err()
|
||||
);
|
||||
let mut reversed = capture.to_dto();
|
||||
reversed.view_entry_count = 2;
|
||||
let mut second = reversed.entries[0].clone();
|
||||
second.entry_id = "second".into();
|
||||
second.source.entry_index = 4;
|
||||
@@ -325,6 +327,16 @@ fn malformed_dtos_and_oversized_representations_are_rejected() {
|
||||
reversed.entries[0].order = 1;
|
||||
reversed.entries.push(second);
|
||||
assert!(SessionCapture::try_from_dto(reversed, CaptureLimits::default()).is_err());
|
||||
let mut duplicate_source = capture.to_dto();
|
||||
duplicate_source.view_entry_count = 2;
|
||||
let mut second = duplicate_source.entries[0].clone();
|
||||
second.entry_id = "distinct-id".into();
|
||||
second.order = 1;
|
||||
duplicate_source.entries.push(second);
|
||||
assert!(matches!(
|
||||
SessionCapture::try_from_dto(duplicate_source, CaptureLimits::default()),
|
||||
Err(CaptureError::Invalid("duplicate source position"))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -503,7 +515,7 @@ fn snapshot_immutability_and_scoped_operations_reject_foreign_or_unknown_refs_an
|
||||
2
|
||||
);
|
||||
let unknown = SessionEntryRef::parse("E99999999").unwrap();
|
||||
assert_eq!(capture.source_index_for_ref(&unknown), None);
|
||||
assert_eq!(capture.view_order_for_ref(&unknown), None);
|
||||
assert!(matches!(
|
||||
capture.scoped_ref(&unknown),
|
||||
Err(CaptureError::UnknownReference)
|
||||
@@ -592,3 +604,108 @@ fn slices_preserve_empty_and_long_result_fields_under_item_and_metadata_budgets(
|
||||
Err(CaptureError::BudgetTooSmall)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn evidence_uses_original_segment_positions_after_roundtrip_and_view_selection() {
|
||||
let full = SessionCapture::new(
|
||||
"s",
|
||||
"selected",
|
||||
vec![
|
||||
Item::user_message("first"),
|
||||
Item::assistant_message("second"),
|
||||
],
|
||||
);
|
||||
let mut dto = full.to_dto();
|
||||
dto.entries[0].source.segment_id = "original-a".into();
|
||||
dto.entries[0].source.entry_index = 80;
|
||||
dto.entries[1].source.segment_id = "original-b".into();
|
||||
dto.entries[1].source.entry_index = 3;
|
||||
let encoded = dto.encode(CaptureLimits::default()).unwrap();
|
||||
let restored = SessionCapture::decode(&encoded, CaptureLimits::default()).unwrap();
|
||||
for (id, segment, index, order) in [
|
||||
("E00000000", "original-a", 80, 0),
|
||||
("E00000001", "original-b", 3, 1),
|
||||
] {
|
||||
let evidence = restored.evidence_for(id).unwrap();
|
||||
assert_eq!(evidence.segment_id, segment);
|
||||
assert_eq!(evidence.entry_range, [index; 2]);
|
||||
let read = restored.read(ReadSelector::Id(id), ReadOptions::default());
|
||||
assert_eq!(read.entries[0].entry_range, [order; 2]);
|
||||
}
|
||||
let selected = restored.select_order_range(1..2).unwrap();
|
||||
assert_eq!(selected.overview()[0].entry_range, [0, 0]);
|
||||
let evidence = selected.evidence_for("E00000001").unwrap();
|
||||
assert_eq!(evidence.segment_id, "original-b");
|
||||
assert_eq!(evidence.entry_range, [3, 3]);
|
||||
let roundtrip = SessionCapture::decode(
|
||||
&selected.encode(CaptureLimits::default()).unwrap(),
|
||||
CaptureLimits::default(),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(roundtrip.to_dto(), selected.to_dto());
|
||||
assert_eq!(
|
||||
roundtrip.evidence_for("E00000001").unwrap().entry_range,
|
||||
[3, 3]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fixed_history_selection_preserves_original_coordinates_and_checks_private_position_bounds() {
|
||||
let history = vec![
|
||||
history("old", Item::user_message("old"), None),
|
||||
history("hidden", Item::reasoning("PRIVATE"), None),
|
||||
history("selected", Item::user_message("selected"), None),
|
||||
history("private-tail", Item::system_message("PRIVATE"), None),
|
||||
];
|
||||
let full = SessionCapture::from_complete_history("s", "seg", history);
|
||||
let suffix = full.select_order_range(1..4).unwrap();
|
||||
let original = full
|
||||
.entries()
|
||||
.find(|entry| entry.entry_id == "selected")
|
||||
.unwrap();
|
||||
let selected = suffix.entries().next().unwrap();
|
||||
assert_eq!(selected.entry_id, original.entry_id);
|
||||
assert_eq!(selected.source, original.source);
|
||||
assert_eq!(selected.body, original.body);
|
||||
assert_eq!(selected.policy, original.policy);
|
||||
assert!(suffix.evidence_for("Eold").is_none());
|
||||
assert_eq!(suffix.search(&SearchOptions::default()).len(), 1);
|
||||
assert_eq!(
|
||||
suffix.view_order_for_ref(&SessionEntryRef::parse("Eselected").unwrap()),
|
||||
Some(1)
|
||||
);
|
||||
assert_eq!(selected.source.entry_index, 2);
|
||||
assert_eq!(selected.order, 1);
|
||||
assert_eq!(suffix.to_dto().view_entry_count, 3);
|
||||
assert_eq!(
|
||||
suffix.evidence_for("Eselected").unwrap().entry_range,
|
||||
[2, 2]
|
||||
);
|
||||
let nested = suffix.select_order_range(1..2).unwrap();
|
||||
assert_eq!(nested.entries().next().unwrap().order, 0);
|
||||
assert_eq!(nested.entries().next().unwrap().source, original.source);
|
||||
let restored = SessionCapture::decode(
|
||||
&suffix.encode(CaptureLimits::default()).unwrap(),
|
||||
CaptureLimits::default(),
|
||||
)
|
||||
.unwrap();
|
||||
assert_eq!(restored.to_dto(), suffix.to_dto());
|
||||
assert!(full.select_order_range(4..5).is_err());
|
||||
let reversed = std::ops::Range { start: 3, end: 2 };
|
||||
assert!(full.select_order_range(reversed).is_err());
|
||||
let hidden_only = full.select_order_range(3..4).unwrap();
|
||||
assert_eq!(hidden_only.entries().len(), 0);
|
||||
assert_eq!(hidden_only.to_dto().view_entry_count, 1);
|
||||
let mut invalid = full.to_dto();
|
||||
invalid.view_entry_count = 2; // the selected entry's view order is outside this extent
|
||||
assert!(SessionCapture::try_from_dto(invalid, CaptureLimits::default()).is_err());
|
||||
assert_eq!(
|
||||
full.retain_entries(|entry| entry.entry_id == "selected")
|
||||
.entries()
|
||||
.next()
|
||||
.unwrap()
|
||||
.source,
|
||||
original.source
|
||||
);
|
||||
assert_eq!(full.to_dto().view_entry_count, 4);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user