Coding-Dev-Tools · Coding-Dev-Tools · Sep 23, 2026 · Sep 23, 2026 · Sep 23, 2026
@@ -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": "1.7.4"
+      "version": "1.7.6"
     }
   ]
 }
@@ -1,6 +1,6 @@
 {
   "name": "engraphis-memory",
-  "version": "1.7.4",
+  "version": "1.7.6",
   "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",

@@ -1,5 +1,5 @@
-e2e08499a70d8d62ef22797cda0bb07d46cd1c6a79e5e18c1103b6c3c755b6d5  .claude-plugin/marketplace.json
-36c560916ba42634cc50dc4f81b49955cc49b72152452eef67b49b6b2a2957d5  .claude-plugin/plugin.json
+95b9cf676a90bf629137f163cce4eb62927587def995d30703c54bdf6af5bf4f  .claude-plugin/marketplace.json
+fb90a228271f77d89edf3242b98ff98e1f6aa17b3d499c4f47155de9d09bf459  .claude-plugin/plugin.json
 4bc8979b9ffeb97190960e551dbf4ddc6f7aeeb7b86894fd2298a59ff0001efa  skills/engraphis-memory/SKILL.md
 055655db84af07561d002f0c69744313d8413c39f3e873f941f0fa0b1e76dc66  skills/engraphis-memory/references/CONVENTIONS.md
 62019760766ff472a76a0f81437898f39e3c1fe2631732b7b7733e50c1ad837f  skills/engraphis-memory/references/SCOPING.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-v70.json`](docs/benchmark-evidence/offline-fixtures-v70.json) artifact. Its
+[`offline-fixtures-v71.json`](docs/benchmark-evidence/offline-fixtures-v71.json) artifact. Its
 SHA-256 is
-`a8a96cb4d096ee72131d60307cc95b95f5b09716e813d9ee07090578dc1439c3`, also recorded in the
+`cdbdf80befe00a38656c7f26fc0082ac1c9408c415e15fde9c87b303509ab123`, 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
-`6e2db2abb278af9a48ac8309564fc3fca315806861d5739d3a24a02034f19305`. The artifact defines
+`8307020857603dd991a8b82867660ac9778074b9712c866e3ca20a7accc25ad1`. 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)`:
 
@@ -123,10 +123,10 @@ Historical LoCoMo, graph, handoff, consolidation, and security figures remain pr
 source artifacts but are omitted from the current chart until each has a matching immutable,
 public-safe artifact. The chart labels coding outcomes, external datasets, and operational
 capacity as pending evaluation tracks rather than implying scores. Regenerate it with
-`python scripts/render_benchmark_report.py --report docs/benchmark-evidence/offline-fixtures-v70.json --output docs/images/context-efficiency.svg` after selecting the report to publish.
+`python scripts/render_benchmark_report.py --report docs/benchmark-evidence/offline-fixtures-v71.json --output docs/images/context-efficiency.svg` after selecting the report to publish.
 
 The companion examples are also generated from that artifact with
-`python -m scripts.render_benchmark_examples --report docs/benchmark-evidence/offline-fixtures-v70.json --output docs/images/evidence-backed-agent-examples.svg`.
+`python -m scripts.render_benchmark_examples --report docs/benchmark-evidence/offline-fixtures-v71.json --output docs/images/evidence-backed-agent-examples.svg`.
 The historical-to-executable mapping is in
 [`docs/BENCHMARK_CHANGE_COVERAGE.md`](docs/BENCHMARK_CHANGE_COVERAGE.md).
 

@@ -5,6 +5,18 @@ All notable changes to Engraphis are documented here. Format loosely follows
 
 ## [Unreleased]
 
+## [1.7.6] - 2026-09-23
+
+- Hardened Railway container startup persistence and readiness: entrypoint revalidates
+  trusted paths before ownership changes, enforces private 0700 permissions, preserves
+  ownership of external container state directories, rejects unsafe ownership markers
+  and hard-linked privileged startup inputs, and initializes private state for rootless
+  container execution.
+- Improved agent-memory evidence and benchmark integrity: expanded evaluation harness,
+  local capacity campaign runners, campaign oracles and candidate compatibility, exact
+  value correction surfaces, compact recall HTTP endpoints, and comprehensive evidence
+  verification contracts.
+- Upgraded tree-sitter-language-pack to 1.20.0, openai-codex to 0.154.0, and pyright to 1.1.414.
 - Receipt-chain structural corruption remains fail-closed at the Store boundary without
   bricking a completed service operation: affected responses now carry a content-free
   `receipt_warning`, and graph/import workers preserve their completed state.

@@ -84,9 +84,9 @@ neither is an end-to-end question-answer score. Coding outcomes, external datase
 operational capacity remain separate pending evaluation tracks until their artifacts are selected.
 
 These values are evidence IDs `offline-chunking` and `offline-performance` in
-[`offline-fixtures-v70.json`](https://github.com/Coding-Dev-Tools/engraphis/blob/main/docs/benchmark-evidence/offline-fixtures-v70.json),
+[`offline-fixtures-v71.json`](https://github.com/Coding-Dev-Tools/engraphis/blob/main/docs/benchmark-evidence/offline-fixtures-v71.json),
 SHA-256
-`a8a96cb4d096ee72131d60307cc95b95f5b09716e813d9ee07090578dc1439c3`.
+`cdbdf80befe00a38656c7f26fc0082ac1c9408c415e15fde9c87b303509ab123`.
 [`BENCHMARKS.md`](https://github.com/Coding-Dev-Tools/engraphis/blob/main/BENCHMARKS.md#public-numeric-evidence-registry)
 records the matching suite digest, exact commands, and per-command config digests. The offline
 fixture registry intentionally excludes external, model-dependent, consolidation, productivity,