You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/first-second-parity-audit.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -131,6 +131,7 @@ M6 progress now includes:
131
131
-`internal/compact`: microcompact disk cache loading now accepts non-strict cache-hit booleans for `cached`/`fromCache`/`cacheHit`/`isCached`, including `yes`/`no`, `on`/`off`, and `1`/`0` JSON number or string values.
132
132
-`internal/compact`: microcompact disk cache loading now accepts JSON:API/resource-style `resource`/`attributes`/`properties` wrappers, with summary payloads inside attributes/properties and outer resource IDs used as digest fallback when needed.
133
133
-`internal/compact`: microcompact disk cache summary payloads now accept text content-block objects, text content-block arrays, and string arrays, joining visible text blocks into the recovered summary for official/SDK-style cached microcompact files.
134
+
-`internal/compact`: microcompact disk cache summary payloads now also accept full contract message objects and unwrap `message`/`assistantMessage`/`resultMessage`/`outputMessage`/`completionMessage` response wrappers before extracting visible text summary.
134
135
-`internal/conversation`: optional auto-compact can now run before the main request, fail open with a consecutive-failure circuit breaker, emit runtime `token_warning` events from compact warning state, persist compact boundary metadata to transcript, write a session-memory summary, inject recalled session-memory snippets into API request context when enabled, and optionally extract turn-end memory facts into session memory.
135
136
-`internal/memory`: session-memory summaries can now be loaded with frontmatter field aliases, rolled up/pruned into an archive summary with prior rollup archives excluded from candidate compaction and merged across archive IDs, rune-safe rollup truncation, recalled by query with deterministic scoring and recency ordering, ranked through a model-assisted candidate/session-id selection path with fallback when selected IDs are invalid or excluded, alternate/camel response-key parsing, fenced/prose JSON extraction, scalar session-id parsing, nested/wrapped/collection-alias selection parsing, and nested selected-memory item parsing, and injected into resume context through the same optional recall agent path; deterministic and model-backed memory fact extraction can summarize user preferences, requests, decisions, and tool-use facts, including fenced/prose JSON, wrapped facts responses, alternate and structured fact field names, nested source objects, nested fact response shapes, and fact kind aliases.
136
137
- `internal/session`: project session listing and pagination, prompt-history lock/buffered flush/field aliases, lightweight transcript index/title/text-preview inference, line-offset transcript indexing/window/byte-budget-window/parent-chain/resume/tail/byte-budget-tail loading, AI-title/last-prompt/task/agent/PR/worktree transcript metadata loading and type/field aliases, transcript message/session UUID field aliases, tombstone metadata loading with target/session/reason aliases and delete/relink replay, agent-scoped content replacement metadata/record field-alias loading, session-scoped metadata reappend including AI-title/last-prompt/task-summary, streaming transcript search snippets for resume/search UI, official `subagents/agent-*.jsonl` transcript layout with legacy sidechain listing, agent metadata sidecar read/write/field aliases, sidechain runtime start/append/finish/cancel/fail summary bridging plus parent-chain append/finish, sidechain manager orchestration for spawn/append/finish/cancel/fail/list/resume, sidechain state/list/resume support with content-field aliases, sidechain resume context construction, sidechain conversation and agent-scoped content-replacement reconstruction, transcript tail/window loading and byte-budget tail loading for bounded-memory resume/UI paths, lightweight transcript metadata loading, remote-history token refresh retry, page-field/event-list/records/entries/last-id/cursor/event-id/has-next aliases plus wrapped-data/links/paging/bare-array/keyed-event-map responses, before_id resume, fallback field fill, and duplicate-aware parent linking during transcript materialization.
0 commit comments