# pi-lossless ## 0.1.3 ### Patch Changes - 470a7b7: Verify file bytes and sha256 against the linked message text before inserting file rows on import. A repeated entry id with different text, or a file row whose text differs from the stored message, also refuses the import without writing. Existing rows stay untouched. - 470a7b7: Signal a watermark miss on the ingest path. A full rescan now writes one `ingest-rescan` metric row and, in interactive sessions, one UI warning. Empty entries stay silent and ingest behavior is unchanged. - 470a7b7: Add a mechanical tier for noisy tools. Name tools in `mechanicalTools` in summarizer-config, `/lcm` config, or the OpenCode plugin options. Their spans compact into deterministic `mechanical` leaves with zero summarizer spend at compaction time. Every message stays stored verbatim and covered, so the integrity coverage check passes, and heal re-derives a skipped leaf from provenance on demand. There is no ingest filtering. - 470a7b7: Report orphan sidecars in doctor. `integritySnapshot` now lists sidecar files and stale `wal` and `shm` files with no live session (`.sqlite` by default, `.db` for Pi). `checkIntegrity` reports them as a read-only `orphan-sidecar` finding through `lcm doctor` and the diagnose bundle. Report only. Deletion stays manual. - 470a7b7: Upgrade recall search. `lcm_grep` takes `role`, `date_start`/`date_end`, and `tool_name` filters. Role and time are SQL predicates on the stored columns with a covering index. Tool scope is an FTS rewrite against `[tool:Name]` markers with no new table or index. `lcm_expand` takes an `anchor` entry id that centers the listing window with edge clamping. The recall manifest and the retrieval brief order by stop-word stripped query-word overlap over summary headers. A read-only files view lists each linked file once with an incomplete-coverage flag and a `large-inline` mark. No migration and no new writer. - 470a7b7: Add a read-only static sidecar dump. `/lcm dump` and `/lossless-dump` open the session sidecar `queryOnly` and reuse the recall views and metric rows. The dump redacts displayed seams, labels removed rows, and reports old generations as named skips. Output is capped at 16 KB. - 0c70748: Ask providers for a whole number of tokens. A leaf target was half of the calibrated chunk budget, so it was fractional whenever that budget was odd, and a provider that validates `max_tokens` as an unsigned integer rejected the call with a 422. The ladder then stored the deterministic truncate: in one week of Pi sessions that was 1,315 of 5,358 summaries, with 540 rejected calls naming values such as `max_tokens: 5543.5`. The request builder now rounds to nearest, never below one, and treats a non-finite budget as that floor, before the reasoning headroom is added. Integer budgets produce the same request as before. No config key, migration or metric row changes. ## 0.1.2 ### Patch Changes - de419eb: Ship a versioned Intent skill with each package (`skills//SKILL.md` in the published tarball): install, command and recall vocabulary, config essentials, and common mistakes, stamped with the package version on release. Adds `skills` to each package's published files and validates skills on publish and in CI. ## 0.1.1 ### Patch Changes - 6748df1: Refresh every external dependency to its newest published version: Vite+ 1.4.0 and Vitest 5.0.5, TypeScript 7.0.2, `@types/node` 26.6.5, `@changesets/cli` 3.0.3, Pi 1.4.0, OpenCode 2.1.4, Typebox 1.4.3, Blume 2.2.5, and Bun 1.4.4. Pi host packages now use the `*` peer range its package guide documents for packages the host supplies. - 6748df1: Derive the heal source window from the summary target instead of clipping every source message at a fixed 3,000 tokens. The window is clamped to the summarizer request budget and has an explicit `healSourceTokens` override in Pi and OpenCode. A leaf that exceeds one window is mapped through up to eight exact windows and reduced once, so a large tool result can become clean without one enormous prompt. A source beyond the bounded plan is blocked without another model call, while a mechanical node gets one improvement. Heal reports now separate clean repairs from improvements and record source-blocked nodes. - 6748df1: Add per-node summary timing, session-correlated engine rows, and adapter-routed metrics. OpenCode now writes engine and summarizer rows to its sidecar log, exposes the summarizer call and pass budgets, marks character-derived usage as estimated, and reports summary latency, cap outcomes, and abandoned rows. Add persistent summary quality: clean, clipped, mechanical, and derived. Existing stores migrate to generation 2, and a failed parent stays visible as derived. Add a bounded heal command in both adapters. It finds tainted summaries and their ancestors, re-derives them from stored source bottom-up, rejects another mechanical result, and supports a dry run. A heal owns its store connection so a plugin reload cannot finalize it, and one session allows one heal at a time. Mechanical work runs before a clipped retry, so a bounded run keeps making progress. ## 0.1.0 First release.