hippo-memory 1.7.9 → 1.8.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md
CHANGED
|
@@ -85,6 +85,20 @@ hippo recall "data pipeline issues" --budget 2000
|
|
|
85
85
|
|
|
86
86
|
---
|
|
87
87
|
|
|
88
|
+
### What's new in v1.8.1
|
|
89
|
+
|
|
90
|
+
- **v1.8 prereg's v1.9 LongMemEval cross-validation pre-commitment RETRACTED.** Outside-voice review on two iterations of the v1.9 plan found six structural barriers (canonical harness bypasses the boost path; ingest tag namespace excludes content-derived stems; pushGoal API field mismatch; depth-cap suspension; trigger AND clause unreachable; workload-validity gate ceremonial). Per Root Cause Over Patches, public retraction over re-architecture. **This release does not re-assert the retracted −10pp magnitude.** Per `docs/RETRACTION.md`.
|
|
91
|
+
- **Pre-registration discipline rule pinned in `docs/RETRACTION.md`:** no future eval pre-commitment is binding without (a) source-read of the code paths the design depends on, AND (b) a 1-question dry-run confirming the mechanism FIRES before pre-reg locks.
|
|
92
|
+
- **Mechanism-effect status (cumulative null escalation)** appended to `docs/RETRACTION.md`. Across every workload pre-registered and tested to date (v1.7.5/6/7 SANITY_FAILs, v1.8 SAME=20/20 sign-only, v1.9 untestable), the dlPFC goal-stack mechanism has not produced a detectable behavioural effect at the metric level. The mechanism's CODE is preserved; the THEORY is preserved; what is acknowledged is that its EFFECT on the workloads we have been able to test is undetectable.
|
|
93
|
+
- **No new eval pre-commitment in v1.8.1.** Future eval directions drafted under the new discipline rule.
|
|
94
|
+
|
|
95
|
+
### What's new in v1.8.0
|
|
96
|
+
|
|
97
|
+
- **Adversarial-categories release** for the sequential-learning benchmark. 10 → 13 categories (3 new: `timezone_naive`, `idempotency_retry`, `float_accumulation`). Lesson vocabulary verified <0.30 Jaccard overlap vs existing 10 (`tools/jaccard-overlap.mjs`; max=0.033). Workload 50 → 62 tasks; late-phase metric (`--restrict-late-to 4`) preserved.
|
|
98
|
+
- **Workload-validity verdict: PASS.** C2 hippo-base lateMean = 0.25 (lattice rate), 20 of 20 seeds non-zero — first non-saturated workload across v1.7.5/6/7/8. Framed as workload-validity / non-saturation check per `docs/RETRACTION.md`, NOT a magnitude criterion.
|
|
99
|
+
- **Mechanism characterisation: C3 = C2 on all 20 seeds.** Sign-only seed-pair direction count (vs C2): 0 STRICTLY_LOWER / 0 STRICTLY_HIGHER / 20 TIED. The goal-stack mechanism does not detectably change per-seed late-4 lattice rate on this workload. Hook failures: 0/0. **This release does not re-assert the retracted −10pp magnitude.** Per `docs/RETRACTION.md`, mechanism remains shipped; no magnitude is currently claimed.
|
|
100
|
+
- **Pre-committed v1.9 direction:** LongMemEval R@5 cross-validation. Named BEFORE v1.8 ran; the v1.8 PASS verdict does not change the pre-commitment.
|
|
101
|
+
|
|
88
102
|
### What's new in v1.7.9
|
|
89
103
|
|
|
90
104
|
- **−10pp goal-stack lift magnitude RETRACTED.** Three pre-registered workload variants (v1.7.5 full-late SANITY_FAIL, v1.7.6 budget sweep B*=NULL, v1.7.7 `--restrict-late-to 4` SANITY_FAIL) all returned C2 hippo-base late mean = 0.0% across every seed. The 78% → 14% headline does not reproduce on the formal harness. Mechanism (dlPFC goal-stack) remains shipped; **no magnitude is currently claimed.**
|
package/dist/src/version.js
CHANGED
|
@@ -16,7 +16,7 @@
|
|
|
16
16
|
* an ESM `import` can resolve cleanly, and a hardcoded constant survives
|
|
17
17
|
* any packager that drops .json files.
|
|
18
18
|
*/
|
|
19
|
-
export const PACKAGE_VERSION = '1.
|
|
19
|
+
export const PACKAGE_VERSION = '1.8.1';
|
|
20
20
|
// Bump on every release alongside the 4 manifests + lockfile.
|
|
21
21
|
/**
|
|
22
22
|
* Compare two semver strings. Returns positive if a > b, 0 if equal, negative
|
package/dist/version.d.ts
CHANGED
|
@@ -16,7 +16,7 @@
|
|
|
16
16
|
* an ESM `import` can resolve cleanly, and a hardcoded constant survives
|
|
17
17
|
* any packager that drops .json files.
|
|
18
18
|
*/
|
|
19
|
-
export declare const PACKAGE_VERSION = "1.
|
|
19
|
+
export declare const PACKAGE_VERSION = "1.8.1";
|
|
20
20
|
/**
|
|
21
21
|
* Compare two semver strings. Returns positive if a > b, 0 if equal, negative
|
|
22
22
|
* if a < b.
|
package/dist/version.js
CHANGED
|
@@ -16,7 +16,7 @@
|
|
|
16
16
|
* an ESM `import` can resolve cleanly, and a hardcoded constant survives
|
|
17
17
|
* any packager that drops .json files.
|
|
18
18
|
*/
|
|
19
|
-
export const PACKAGE_VERSION = '1.
|
|
19
|
+
export const PACKAGE_VERSION = '1.8.1';
|
|
20
20
|
// Bump on every release alongside the 4 manifests + lockfile.
|
|
21
21
|
/**
|
|
22
22
|
* Compare two semver strings. Returns positive if a > b, 0 if equal, negative
|
package/openclaw.plugin.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"id": "hippo-memory",
|
|
3
3
|
"name": "Hippo Memory",
|
|
4
4
|
"description": "Biologically-inspired memory for AI agents. Decay by default, retrieval strengthening, sleep consolidation.",
|
|
5
|
-
"version": "1.
|
|
5
|
+
"version": "1.8.1",
|
|
6
6
|
"configSchema": {
|
|
7
7
|
"type": "object",
|
|
8
8
|
"additionalProperties": false,
|