diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json index 28bd40ba..c0994c22 100644 --- a/.claude-plugin/marketplace.json +++ b/.claude-plugin/marketplace.json @@ -9,7 +9,7 @@ "name": "engraphis-memory", "source": "./", "description": "Discipline for giving agents durable, scoped, explainable memory across sessions and repos with the Engraphis MCP tools.", - "version": "1.7.12" + "version": "1.7.13" } ] } diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json index 6e59e596..3dd57c33 100644 --- a/.claude-plugin/plugin.json +++ b/.claude-plugin/plugin.json @@ -1,6 +1,6 @@ { "name": "engraphis-memory", - "version": "1.7.12", + "version": "1.7.13", "description": "Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.", "author": { "name": "The Engraphis Authors", diff --git a/.claude-plugin/skill-assets.sha256 b/.claude-plugin/skill-assets.sha256 index 24d8b908..8131747b 100644 --- a/.claude-plugin/skill-assets.sha256 +++ b/.claude-plugin/skill-assets.sha256 @@ -1,5 +1,5 @@ -f6343d92f4c7249ea5789facf391c754537df888f0ca83373acad147e7a41c83 .claude-plugin/marketplace.json -bb219dc0cec6364a6c29f3f5fdd4d4aee191840404a61e015a35d63b25d42b38 .claude-plugin/plugin.json +881550b07144b8e6e5d1a98a9dab0d81e48ffb3ffafd60d0d64869100bb912cc .claude-plugin/marketplace.json +c04eda5ea2c72ce7b825923f6975a68dc3bac25faac13dfa677756dbb3b6d01d .claude-plugin/plugin.json 84b3792a88446667ca75893b2dcd30280dd89ee7fb7a88c90bc0b123dc005ccd skills/engraphis-memory/SKILL.md 055655db84af07561d002f0c69744313d8413c39f3e873f941f0fa0b1e76dc66 skills/engraphis-memory/references/CONVENTIONS.md 9d090a03f5b3f36a34d91f66b72c3844591f6915755ac3a6c6ba5f1b16977de5 skills/engraphis-memory/references/SCOPING.md diff --git a/BENCHMARKS.md b/BENCHMARKS.md index 27698bc1..bedae76b 100644 --- a/BENCHMARKS.md +++ b/BENCHMARKS.md @@ -94,14 +94,14 @@ interpretation and do not count as additional benchmark-quality gains. ### Public numeric evidence registry Every exact public aggregate retained below comes from the checked-in, public-safe -[`offline-fixtures-ux-parity-20261120.json`](docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json) artifact. Its +[`offline-fixtures-release-1.7.13-20261120.json`](docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json) artifact. Its SHA-256 is -`f671ed73fadd2f91728294490656675243547214aba57810571c36697b6bb583`, also recorded in the +`6cd7dee89ab3e295ed5474b47c166840b684f7cc00be0b615df9b2010233b5dc`, also recorded in the adjacent `.sha256` file. The artifact contains no raw questions, answers, prompts, customer data, or per-record content fingerprints. The fixture-suite digest is -`83b286c9691f79ac3f4875f3b9b6a12cbad7d006b9e823687d6829dd19bfe6ab`. The artifact defines +`43ed2e9aa52b84243f1641a86a23ac9f38a3f62ec4ebd33d681fcbfe7f32126e`. The artifact defines the digest algorithm and records the SHA-256 of every suite and dataset file. Each evidence ID also binds its exact command through `sha256(UTF-8 exact command)`: @@ -134,7 +134,7 @@ retrieval-quality improvement. It does not qualify browser behavior, hosted serv external models, or provider billing. The registered artifact was produced with: ```bash -python -m scripts.export_offline_evidence --output docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json +python -m scripts.export_offline_evidence --output docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json ``` The earlier release-review predecessors, @@ -207,13 +207,13 @@ grounded checks in separate panels; provider billing and MCP transport are not m the SVG and matching PNG with: ```bash -python scripts/render_benchmark_report.py --report docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json --output docs/images/context-efficiency.svg --png-output docs/images/context-efficiency.png +python scripts/render_benchmark_report.py --report docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json --output docs/images/context-efficiency.svg --png-output docs/images/context-efficiency.png ``` The companion examples are also generated from that artifact with: ```bash -python -m scripts.render_benchmark_examples --report docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json --output docs/images/evidence-backed-agent-examples.svg --png-output docs/images/evidence-backed-agent-examples.png +python -m scripts.render_benchmark_examples --report docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json --output docs/images/evidence-backed-agent-examples.svg --png-output docs/images/evidence-backed-agent-examples.png ``` The historical-to-executable mapping is in [`docs/BENCHMARK_CHANGE_COVERAGE.md`](docs/BENCHMARK_CHANGE_COVERAGE.md). diff --git a/CHANGELOG.md b/CHANGELOG.md index a81a5d5b..6a82a934 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,10 @@ All notable changes to Engraphis are documented here. Format loosely follows ## [Unreleased] +## [1.7.13] - 2026-11-20 + +Candidate package version: **1.7.13**. Publication and hosted-service qualification remain separate. + - Drive onboarding trial/checkout links and `/memory/license` + `/api/license` per-plan trial metadata (`trial_days`, `days_by_plan`) from `engraphis/commercial.py` with path-aware, mutation-safe manifest caching, align dashboard Team plan cards and comparison tables with live diff --git a/README.md b/README.md index 6ea5e767..43a1e708 100644 --- a/README.md +++ b/README.md @@ -91,7 +91,7 @@ Pro is $10/month or $100/year for one owner. Team is $20/seat/month or $200/seat The current registered artifact contains three deterministic offline fixture runs. It separates context size, retrieval quality, and grounded decision checks; these small fixtures do not establish general task performance.

- Three registered offline fixtures: structure-aware chunking reduced mean retrieved context from 740.3 to 214.3 tokens per question (71.1%, 18 questions); the serialized JSON-shape proxy fell from 24,590 to 11,138 tokens across 26 payload samples and 260 recalls. Candidate and packed retrieval quality (Recall@5, Hit@5, and answer-token recall) are shown separately (each 1.000). Grounded checks show 5/5 answerable queries grounded and 6/6 abstention queries rejected, including a 1/1 quarantined-evidence probe; 11/11 decisions were correct. MCP transport and provider billing were not measured. Artifact SHA-256 prefix f671ed73fadd; see the benchmark guide for the full checksum. + Three registered offline fixtures: structure-aware chunking reduced mean retrieved context from 740.3 to 214.3 tokens per question (71.1%, 18 questions); the serialized JSON-shape proxy fell from 24,590 to 11,138 tokens across 26 payload samples and 260 recalls. Candidate and packed retrieval quality (Recall@5, Hit@5, and answer-token recall) are shown separately (each 1.000). Grounded checks show 5/5 answerable queries grounded and 6/6 abstention queries rejected, including a 1/1 quarantined-evidence probe; 11/11 decisions were correct. MCP transport and provider billing were not measured. Artifact SHA-256 prefix 6cd7dee89ab3; see the benchmark guide for the full checksum.
Three offline fixtures separate context reduction, candidate and packed retrieval quality, and grounded behavior. The chart shows the artifact checksum prefix; see the benchmark guide for the full checksum and reproduction steps.

diff --git a/docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json b/docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json similarity index 99% rename from docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json rename to docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json index 31a52e34..9b36d2da 100644 --- a/docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json +++ b/docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json @@ -103,10 +103,10 @@ ], "schema": "engraphis-public-offline-fixtures/v1", "suite": { - "digest": "83b286c9691f79ac3f4875f3b9b6a12cbad7d006b9e823687d6829dd19bfe6ab", + "digest": "43ed2e9aa52b84243f1641a86a23ac9f38a3f62ec4ebd33d681fcbfe7f32126e", "digest_method": "sha256(canonical compact JSON mapping each sorted path to its file SHA-256)", "files": { - "engraphis/__init__.py": "1cde9f19e05ddc4f5f28517e00b0a7bd5ebf09d6be8ec2681cebf5b698195d70", + "engraphis/__init__.py": "22cee79b5339f004762000deb0bd6c9204ad528d0c9598fe27350c49cdf638fe", "engraphis/ai_context.py": "4dfd5d39eb95d05c591d1981e9e855eced73232f53efd9fe9966e0e08957d030", "engraphis/app.py": "44d68ad8c0ff46baed01978c9b04e40b8be5031609d5a69e205b7f05da3777fb", "engraphis/backends/__init__.py": "a9f22b9278362904166614081f1df78469d453601b298ce4e8afdba8a3722b25", diff --git a/docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json.sha256 b/docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json.sha256 new file mode 100644 index 00000000..b47d5e10 --- /dev/null +++ b/docs/benchmark-evidence/offline-fixtures-release-1.7.13-20261120.json.sha256 @@ -0,0 +1 @@ +6cd7dee89ab3e295ed5474b47c166840b684f7cc00be0b615df9b2010233b5dc offline-fixtures-release-1.7.13-20261120.json diff --git a/docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json.sha256 b/docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json.sha256 deleted file mode 100644 index 34f557ab..00000000 --- a/docs/benchmark-evidence/offline-fixtures-ux-parity-20261120.json.sha256 +++ /dev/null @@ -1 +0,0 @@ -f671ed73fadd2f91728294490656675243547214aba57810571c36697b6bb583 offline-fixtures-ux-parity-20261120.json diff --git a/docs/images/context-efficiency.png b/docs/images/context-efficiency.png index b22c48dc..4d7c1d5e 100644 Binary files a/docs/images/context-efficiency.png and b/docs/images/context-efficiency.png differ diff --git a/docs/images/context-efficiency.svg b/docs/images/context-efficiency.svg index 0c5bcf78..6e74c3da 100644 --- a/docs/images/context-efficiency.svg +++ b/docs/images/context-efficiency.svg @@ -1,6 +1,6 @@ Offline context, retrieval, and grounded benchmark results -Artifact-driven offline benchmark report with context efficiency, retrieval quality, and grounded behavior reported separately. Structure-aware chunking reports 740.3 to 214.3 retrieved tokens per question. The JSON-shape payload proxy reports 24,590 full versus 11,138 compact tokens; MCP transport was not measured; provider billing was not measured. Retrieved candidate quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Packed context quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Grounded checks score 5 of 5 answerable queries grounded and 6 of 6 abstention queries rejected, including 1 of 1 quarantined-evidence checks. Decision accuracy is 1.000 across 11 decisions. Source artifact SHA-256 f671ed73fadd2f91728294490656675243547214aba57810571c36697b6bb583. +Artifact-driven offline benchmark report with context efficiency, retrieval quality, and grounded behavior reported separately. Structure-aware chunking reports 740.3 to 214.3 retrieved tokens per question. The JSON-shape payload proxy reports 24,590 full versus 11,138 compact tokens; MCP transport was not measured; provider billing was not measured. Retrieved candidate quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Packed context quality is Recall@5 1.000, Hit@5 1.000, and answer-token recall 1.000 across 26 questions. Grounded checks score 5 of 5 answerable queries grounded and 6 of 6 abstention queries rejected, including 1 of 1 quarantined-evidence checks. Decision accuracy is 1.000 across 11 decisions. Source artifact SHA-256 6cd7dee89ab3e295ed5474b47c166840b684f7cc00be0b615df9b2010233b5dc. @@ -65,6 +65,6 @@ Quarantined-evidence probe 1 / 1 abstained Decision accuracy 1.000 (11 / 11); the quarantine probe is included in the abstention total. -SOURCE SHA-256 f671ed73fadd +SOURCE SHA-256 6cd7dee89ab3 JSON proxy only; MCP transport not measured; provider billing not measured. diff --git a/docs/images/evidence-backed-agent-examples.png b/docs/images/evidence-backed-agent-examples.png index 8d8a378b..fed1fe9e 100644 Binary files a/docs/images/evidence-backed-agent-examples.png and b/docs/images/evidence-backed-agent-examples.png differ diff --git a/docs/images/evidence-backed-agent-examples.svg b/docs/images/evidence-backed-agent-examples.svg index db8a45a9..6b3a9a67 100644 --- a/docs/images/evidence-backed-agent-examples.svg +++ b/docs/images/evidence-backed-agent-examples.svg @@ -1,6 +1,6 @@ Three evidence-backed Engraphis agent behaviors - A three-card summary of deterministic offline fixtures. Focused context returns 740.3 to 214.3 tokens while retaining Recall at 5 of 1.000. A grounded answer returns support for 5/5 answerable questions. An unsupported question safely abstains for 6/6 off-topic questions. Reproduce with eval.chunking_eval and eval.grounded. Exact commands and config digests are registered in BENCHMARKS.md. Public-safe artifact SHA-256: f671ed73fadd2f91728294490656675243547214aba57810571c36697b6bb583. + A three-card summary of deterministic offline fixtures. Focused context returns 740.3 to 214.3 tokens while retaining Recall at 5 of 1.000. A grounded answer returns support for 5/5 answerable questions. An unsupported question safely abstains for 6/6 off-topic questions. Reproduce with eval.chunking_eval and eval.grounded. Exact commands and config digests are registered in BENCHMARKS.md. Public-safe artifact SHA-256: 6cd7dee89ab3e295ed5474b47c166840b684f7cc00be0b615df9b2010233b5dc. @@ -47,5 +47,5 @@ Reproduce: eval.chunking_eval + eval.grounded - SHA256 f671ed73fadd2f91728294490656675243547214aba57810571c36697b6bb583 + SHA256 6cd7dee89ab3e295ed5474b47c166840b684f7cc00be0b615df9b2010233b5dc diff --git a/engraphis/__init__.py b/engraphis/__init__.py index 9355bad1..743b2e59 100644 --- a/engraphis/__init__.py +++ b/engraphis/__init__.py @@ -2,7 +2,7 @@ from importlib.metadata import PackageNotFoundError, version as _dist_version -_SOURCE_VERSION = "1.7.12" +_SOURCE_VERSION = "1.7.13" try: __version__ = _dist_version("engraphis") @@ -14,7 +14,7 @@ except PackageNotFoundError: # source tree without an installed distribution # Keep in step with [project] version in pyproject.toml — tests/test_packaging.py # pins the two together so a release cannot ship them out of sync. - __version__ = "1.7.12" + __version__ = "1.7.13" def _default_memory_engine_factory(**kwargs): diff --git a/engraphis/commercial_manifest.json b/engraphis/commercial_manifest.json index 00cf1c72..b0986263 100644 --- a/engraphis/commercial_manifest.json +++ b/engraphis/commercial_manifest.json @@ -1,6 +1,6 @@ { "schema": "engraphis-commercial/v2", - "version": "1.7.12", + "version": "1.7.13", "control_plane": "https://api.engraphis.com", "account_portal": "https://api.engraphis.com/account", "billing": { diff --git a/pyproject.toml b/pyproject.toml index 4068440b..4502c0bc 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -10,7 +10,7 @@ build-backend = "setuptools.build_meta" [project] name = "engraphis" -version = "1.7.12" +version = "1.7.13" description = "Local-first AI memory engine for agents — Ebbinghaus decay, interaction-aware recall, bi-temporal facts, hybrid retrieval, and an MCP server. You bring the LLM." readme = "README.md" license = "Apache-2.0" diff --git a/tests/test_benchmark_evidence.py b/tests/test_benchmark_evidence.py index 0772c0be..47bf2842 100644 --- a/tests/test_benchmark_evidence.py +++ b/tests/test_benchmark_evidence.py @@ -34,8 +34,8 @@ ROOT = Path(__file__).resolve().parents[1] -PUBLIC_OFFLINE_ARTIFACT = "offline-fixtures-ux-parity-20261120.json" -PUBLIC_OFFLINE_SHA = "f671ed73fadd2f91728294490656675243547214aba57810571c36697b6bb583" +PUBLIC_OFFLINE_ARTIFACT = "offline-fixtures-release-1.7.13-20261120.json" +PUBLIC_OFFLINE_SHA = "6cd7dee89ab3e295ed5474b47c166840b684f7cc00be0b615df9b2010233b5dc" @pytest.fixture(scope="module")