> ## Documentation Index
> Fetch the complete documentation index at: https://mneno.lollopanta.it/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Updates and improvements to Mneno.

<Update label="June 18, 2026" description="v0.4.1">
  ### Mneno CLI Agent Setup

  * Added the local-first `mneno setup-agent` command to bootstrap coding-agent instruction templates into a repository.
  * Supported agents include Codex, Claude Code, Cursor, Gemini CLI, and Windsurf.
  * Installed reusable skills under `.agents/skills/`, with Claude Code skills under its native `.claude/skills/` path.
  * Included safe files previews with `--dry-run` and overwrite safety unless `--force` or `-f` is provided.
</Update>

<Update label="June 12, 2026" description="v0.4.0">
  ### Mneno CLI

  * Added the local-first `mneno` CLI with workspace initialization, status inspection, memory creation, ranked search,
    context building, and recent-memory commands.
  * Added JSON output for automation and stable workspace persistence through `.mneno/memories.json`.
  * Added a safe, temporary-directory demo workflow in `scripts/demo_cli.sh`.

  ### Retrieval quality

  * Search now excludes candidates with no query relevance from deterministic results, while preserving optional
    reranker behavior.
  * Context building uses the same relevance boundary so unrelated memories are not included solely because of
    recency or layer boosts.
</Update>

<Update label="June 11, 2026" description="v0.3.0a3">
  ### Bug fixes

  * Retrieval ranking now gives query relevance more influence than importance or recency, applies bounded active-session
    and related-session boosts, and uses lightweight punctuation, stopword, plural, and phrase normalization.
  * Search and context traces now preserve candidate rank, score breakdowns, inclusion decisions, exclusion reasons, and
    source dataset identity metadata when available.
</Update>

<Update label="June 7, 2026" description="v0.3.0a2">
  ### Bug fix

  * `MemoryClient.evaluate_context()` now returns a valid empty evaluation for small positive budgets when no memory fits. Labeled evaluations report context relevance `0.0` instead of calling `recall_at_k` with `k=0`.
  * Added regression coverage for 2- and 3-token budgets, including operational memories occupying the first candidate slots.
</Update>

<Update label="June 7, 2026" description="v0.3.0a1">
  Mneno Core reached its first alpha milestone. This release stabilizes local observability and SDK-side evaluation infrastructure so runtime behavior can be inspected and benchmarked before external benchmark adapters are added.

  ### Observability

  * Added typed `TraceEvent` and `OperationTrace` models with running, success, and error states.
  * Added an in-memory `TraceRecorder` and `TraceInspector` for summaries, event filtering, memory-decision explanations, and JSON-compatible exports.
  * Added opt-in tracing across search, context building, compaction, conflicts, hierarchy, extraction, sessions, continuity, and timelines.
  * Added structured secret-field redaction. Tracing remains local, optional, and disabled by default.
  * Added versioned trace envelopes using `format: "mneno.trace"` and `version: 1`.

  ### Evaluation and Mneno Bench support

  * Added typed search, context, and compaction evaluation results with deterministic metrics and `to_dict()` / `to_json()` helpers.
  * Added precision\@k, recall\@k, MRR, token efficiency, context utilization, reduction ratio, latency, and explainability coverage metrics.
  * Added the runtime-checkable `BenchmarkAdapter` protocol for future LOCOMO, LongMemEval, BEAM, and Mneno Bench integrations outside core.
  * Added versioned benchmark exports using `format: "mneno.benchmark.result"` and `version: 1`.

  ### Distribution

  * Published the first alpha to [PyPI](https://pypi.org/project/mneno/0.3.0a1/) as both a universal wheel and source distribution.
  * Added tokenless PyPI Trusted Publishing through GitHub Actions with tag/version validation and digital attestations.
  * Install the alpha with `pip install --pre mneno`.
</Update>

<Update label="May 29, 2026" description="v0.2.1">
  This release expands Mneno from a memory store into a lifecycle-aware anti-context-rot runtime with conflict detection, hierarchical memory layers, sessions and timelines, and deterministic or LLM-assisted extraction.

  ### New features

  * **Conflict detection and lifecycle.** Mneno now detects contradictions, duplicates, and superseding facts with deterministic local heuristics. Memories carry lifecycle statuses (`active`, `superseded`, `archived`, `conflicted`), and resolution updates metadata with full audit history. Mneno never deletes memories automatically.
  * **Hierarchical memory layers.** Memories are organized into `short_term`, `working`, `episodic`, `semantic`, `operational`, and `archived` layers, with explainable promotion, demotion, and archival based on importance, access, recency, and type. Retrieval and [context building](/concepts/context-building) prioritize `operational`, `working`, and `semantic` memories by default.
  * **Sessions and timelines.** Group memories by `session_id` with `sequence_index` ordering, reconstruct deterministic timelines across one or many sessions, and boost current-session memories during retrieval. Closing or archiving a session never deletes its memories.
  * **Memory extraction from text.** A new `add_from_text` flow extracts structured memories from raw text. Deterministic extraction is the default; optional LLM-assisted extraction runs through the [provider interface](/advanced/providers) with strict Pydantic validation on every output.
  * **LLM-assisted compaction wording.** [Compaction](/concepts/compaction) decisions stay deterministic, but LLMs can now polish the wording of memories the engine has already chosen to merge. Invalid LLM output falls back to deterministic merged content.

  ### Updates

  * **Provider retrieval and persistence (v0.2.0).** Earlier this week Mneno shipped JSON and SQLite [storage](/concepts/storage), [import/export and backup/restore](/advanced/import-export), provider protocols for embeddings, LLMs, and rerankers, and reranker-powered semantic search.
  * **Policy-driven context building (v0.1.2).** Explainable context packages, token-budget handling, and policy presets are available through `MemoryClient.build_context`. See [context building](/concepts/context-building).
  * **Local compaction engine (v0.1.1).** Preview/apply APIs, configurable compaction policies, decision stats, and deterministic merge and discard behavior. See [compaction](/concepts/compaction).
  * **Universal wheel artifacts.** Releases now publish universal wheels for easier installation across platforms.

  ### Bug fixes

  * Search and context building now correctly exclude `archived` and `superseded` memories by default. Use the explicit inactive-inclusion option when you need them.
  * Older memory payloads without status, conflict links, or audit events load with safe defaults, preserving backward compatibility.
  * Sessions and layer metadata round-trip cleanly through JSON storage, SQLite storage, import/export, and backup/restore.
</Update>