# Changelog

All notable changes to this project will be documented in this file.

## [0.8.0] - Unreleased

Minor release preparation for the additive, opt-in engine APIs; includes the
unpublished 0.7.1 reliability fixes. See [publication status](docs/release-v0.8.0.md).

- Introduce the source update on the repository homepage, with [opt-in examples, migration guidance and scoped measurements](docs/recall-update.md). No new npm package or GitHub Release is published.
- Reuse the complete synthetic-data acceptance workflow for main and pull requests, including fresh-project lint/readiness checks, without reading project memory.
- Preserve original CLI subprocess failures in test helpers, retain execution/parse causes for invalid error responses, and add ten diagnostic regressions without weakening product assertions.
- Append general acceptance/evidence/repair-loop rules to AGENTS.md and preserve the historical [Cloud blocker checkpoint](docs/verification-loop.md).
- Verify complete source, compiled, installed-package, type, recall-quality and cache gates on Ubuntu and Windows in [branch-only Actions](docs/actions-acceptance-results.md). Fix workflow context/path/newline handling and freeze the recall tie fixture's clock without changing product assertions. These changes remain unreleased.

- Add opt-in exact query aliases, managed per-memory/revision embedding scopes, and serialized reads; digest cache keys avoid retained plaintext input keys.
- Compensate failed deletions, add explicit recoverable `supersedeMemory`, and return defensive summary/chunk copies from the in-memory adapter.
- Add opt-in prompt provenance and qualifier-loss warnings, plus explicit raw-content retrieval.
- Record development/held-out synthetic recall evaluation, ownership costs, repeated performance comparisons, and direct offline installed-package verification in the [round-two notes](docs/release-recall-lifecycle.md). Hosted validation now passes; the native cause of the historical Cloud EPERM remains unresolved.

- Fix optional-engine false-none recall when an ineligible hybrid winner hides an eligible candidate; keep existing thresholds.
- Add opt-in candidate search breadth, bounded prompt projection, metadata-only embedding reuse, and a content/model-keyed bounded embedding cache.
- Cache lexical token sets with update/delete invalidation and validate recall/chunking limits before expensive work.
- Add synthetic regression tests, a reproducible comparison benchmark, and [first-batch notes](docs/release-recall-efficiency.md) with migration guidance and measurement limits.

### Reliability fixes carried forward from the unpublished 0.7.1 candidate

The [historical preparation](docs/release-v0.7.1.md) was not a published release.

- Use the same validated rules block for readiness and scope checks; reject ambiguous scopes and omit raw JSONL parse messages from diagnostics.
- Prepare engine writes before mutation; compensate failed writes, expose recovery errors, preserve update metadata, reject duplicate IDs, and serialize mutations.
- Preflight initialization, back up overwritten/appended files, stage replacements, and report rollback failures as JSON.
- Share schema and route diagnostics across CLI tools; reject invalid input, inactive routes, missing successors, cycles, and scope mismatches.
- Recognize actual recall rules instead of filename mentions; validate all three setup files in project scans.
- Add fault-injection regression tests, executable settings-demo fixtures, installed-package smoke checks, and full-suite CI coverage.
- Clarify lexical recall limits, cue-first manual fallback, and non-transactional recovery boundaries.

## [0.7.0] - 2026-08-09

- Rebuilt the README around a one-command start, concrete before/after proof, agent compatibility, safety boundaries, and a shareable product visual.
- Added `deja-vu init --merge-agents` to append an idempotent rules block without replacing an existing `AGENTS.md`.
- Made `init` report incomplete setup and made `doctor` reject an `AGENTS.md` that lacks Deja Vu recall rules.
- Added cross-platform starter-kit instructions and a contributor guide.
- Added repository-wide local Markdown link validation and fixed broken memory-index template links.
- Hardened package verification to use an isolated npm cache and prepared the package metadata for the first CLI-capable npm release.

## [0.6.0] - 2026-05-17

- Reworked the README first screen around the "3-file memory system" positioning.
- Added a copy-first `starter-kit/` with minimal `AGENTS.md`, memory files, and per-agent prompts.
- Added comparison, compatibility, flow diagram, demo walkthrough, launch copy, and v0.6.0 release checklist docs.
- Added the optional unified `deja-vu init`, `deja-vu doctor`, and `deja-vu explain` CLI.
- Split read-only source tests from npm pack verification with `test:src:readonly` and `test:pack`.
- Updated scripted recall to distinguish missing setup as `not_initialized`.

## [0.5.0] - 2026-04-25

- Made remember/writeback a first-class companion to recall with a post-task writeback routing table in the README, protocol, workflow, and AGENTS template.
- Added `writeback_hint` guidance to scripted memory scans so recall naturally leads into durable memory maintenance.
- Added `deja-vu-feedback-report` to aggregate recall feedback into maintenance suggestions for aliases, weights, compaction, and route cleanup.
- Expanded memory linting beyond JSONL into Markdown lifecycle checks for summaries, decisions, open loops, frontmatter, supersession, and transcript-like records.
- Added tests for writeback hints, feedback reporting, Markdown memory linting, and package binary inclusion.

## [0.4.1] - 2026-04-25

- Reaffirmed Deja Vu as an ultra-light protocol-first memory system rather than a required package, service, daemon, vector database, or engine.
- Updated the README opening around the concrete adoption promise: stop re-explaining the repo to every new coding-agent chat.
- Added a 2-minute start path centered on `AGENTS.md`, `memory/summary.md`, and `memory/impressions.jsonl`.
- Clarified that scripts, recall feedback, detailed records, and the TypeScript engine are optional scale-up layers.
- Added release notes for the 0.4.1 protocol-first activation patch.

## [0.4.0] - 2026-04-24

- Reframed the README and package metadata around repo-local Markdown memory for AI coding agents.
- Added observable recall budget reporting to scripted scans and the TypeScript engine.
- Added recall feedback as a lightweight reward signal with `helpful`, `irrelevant`, `missed`, and `overloaded` outcomes.
- Added `memory/recall-feedback.jsonl` templates and example feedback records.
- Expanded memory linting for feedback records, status values, weights, date formats, scope naming, and unsafe record paths.
- Updated protocol, workflow, scripted recall, storage, templates, and examples for Deja Vu Protocol v0.4.
- Updated package metadata for the 0.4.0 release.

## [0.3.1] - 2026-04-23

- Added impression cue quality warnings to `deja-vu-lint-memory` for sparse, oversized, duplicate, generic, and repeated keyword sets.
- Updated the default summary generator to preserve decision, rationale, and trigger gist cues instead of only truncating source content.
- Updated the default chunker to preserve Markdown heading and paragraph boundaries before falling back to hard splitting.
- Added source tests for cue lint warnings, gist summaries, and boundary-aware chunking.
- Updated package metadata for the 0.3.1 patch release.

## [0.3.0] - 2026-04-22

- Repositioned Deja Vu as a cue-first memory protocol centered on `task cue -> familiarity score -> minimal recall -> durable writeback`.
- Reduced the minimum adoption surface to `memory/summary.md`, `memory/impressions.jsonl`, and project rules.
- Reclassified `memory/decisions/`, `memory/open-loops/`, `memory/events/`, `memory/context/`, and `memory/index.md` as recommended or optional artifacts.
- Added a default recall budget: scan always, summary at most one file, details one to three records, and no full memory-tree loads unless explicitly requested.
- Updated protocol, workflow, storage, bootstrap, scripted recall, template, example, and AI-readable docs around low-token cue-first recall.
- Updated package metadata to version 0.3.0.

## [0.2.2] - 2026-04-21

- Made engine impression scans token-only so query embeddings are deferred until chunk retrieval is needed.
- Added CLI `--memory-root` and `--file` options and aligned `matched` with weak/strong scan levels.
- Added `deja-vu-scan-memory` and `deja-vu-lint-memory` package binaries.
- Added memory linting for impression schema, duplicate ids, and linked record paths.
- Updated adoption docs, handshake, templates, and example project to make impression-first recall the default path.
- Updated protocol naming to v0.2 and clarified project-local plain text storage.

## [0.2.1] - 2026-04-21

- Added a protocol-level impression layer for compact keyword-first familiarity scans.
- Added scripted recall documentation and a default `scripts/dejavu-scan-memory.mjs` scanner.
- Added `memory/impressions.jsonl` and `memory/events/` templates for cheap long-term continuity.
- Updated workflow, protocol, storage, bootstrap, and AGENTS templates around impression-first recall.
- Extended the optional TypeScript engine with `impressionTokens` and `scanImpressions()`.
- Added tests for scanning impressions without loading deeper memory.

## [0.2.0] - 2026-04-20

- Repositioned Deja Vu as a protocol-first memory system for AI agents.
- Rewrote the root README around rules, workflow, and Markdown memory as the primary adoption path.
- Added the core protocol references:
  - `docs/protocol.md`
  - `docs/workflow.md`
  - `docs/storage-markdown.md`
- Added copyable project rules and memory templates under `docs/templates/`.
- Added `examples/protocol-project/` as a repo-first example that works without npm or the optional engine.
- Moved the semantic TypeScript engine into an explicitly optional documentation path under `docs/engine/`.
- Rewrote handshake, bootstrap, release, and AI-readable docs to match the new protocol-first framing.
- Updated package metadata to describe the npm package as an optional semantic recall layer.
- Fixed `npm run test:src` for the current Node.js v24 environment by switching to a compatible `ts-node` registration path.

## [0.1.0] - 2026-04-19

- Initial public release of Deja Vu.
- Added the familiarity-first semantic recall engine core.
- Added in-memory storage and vector adapters for zero-infrastructure local trials.
- Added runnable examples for basic recall, agent PM, chat memory, and task assistant flows.
- Added AI-readable integration docs, handshake guidance, and project rules templates.
