This website requires JavaScript.
Explore
Help
Register
Sign In
leefer
/
CyberGril
Watch
1
Star
0
Fork
0
Code
Issues
Pull Requests
11
Actions
Packages
Projects
Releases
Wiki
Activity
Files
81d50f28afdc4fa511854b0a540339b027e8c0d1
CyberGril
/
docs
T
History
zonggong
and
multica-agent
81d50f28af
HEL-868: fixed 13-call real A/B retest executed in one bounded round per rework860 _retest_plan under the original '同意测试' authorization after manager HEL-867 review lifted the stop gate - criteria/fixtures/orchestration untouched at
e06dcaf
(driver only captures per-call raw input/sent-context/answers and writes per-scenario outputs, never overwriting ab_scenarios.json); preflight zero-embed zero-network audit861_reuse868 + audit867_reuse868 both exit 0 with prior evidence and ledgers unchanged; 13/13 calls sent HTTP 200 (ADD1-5 anchored real extraction + QA1-8), real ledger continued on a SQLite-consistent backup of the original 26-row ledger (prefix line digest 03f92557 identical, original read-only preserved) now 39/60, embed ledger 458->498/500 (+40 dense, pre-computed debit guard held), usage 163041 tokens recorded per call; honest per-scenario results: S1/S4/S5/S8/S9 pass, S2/S3 mem0 side and S7 fail fail-closed because base-group batch-anchored infer hits carry the unshared t1 companion row in the group anchor and companion_unshared rejects them at every exit (zero leak markers in all sent contexts - the gate holds; row-level provenance for batch extractions is our adaptation gap, not visible to offline row-anchored fake payloads), S3 retrieval layer strictly better re-confirmed (11:11 target hits vs baseline 0:0) but model-use verdict fails without the gated content, S6 orchestration/status-in-block/unresolved-contrast all pass while both real answers are descriptive '资料里说...' unsupported by the pre-declared bounded grammar and honestly fail closed; no rerun, no criteria relaxation, no debug requests, no merge, no deploy; dual-target requirement checks 4/4 pass with handoff-HEL-868.json
...
Co-authored-by: multica-agent <
github@multica.ai
>
2026-10-26 03:49:33 +08:00
..
frontend
HEL-825 review: link-card accessible-name selector fix (browser_check), evidence scripts, regenerated screenshots/recordings
2026-10-24 08:27:06 +08:00
r1
HEL-780: connect persistent companion and real streaming text chat
2026-10-22 16:25:35 +08:00
r2
fix(r2): keep her self-narration and life within the approved room
2026-10-24 12:03:08 +08:00
r3
HEL-835: evidence corrections per third review - 23 calls, day2 conclusion downgraded, old probe downgraded, null-fingerprint withdrawn, probe start deviation disclosed; 15/15 paired-window correction proof; real follow-up plan
2026-10-25 09:17:34 +08:00
requirements
HEL-868: fixed 13-call real A/B retest executed in one bounded round per rework860 _retest_plan under the original '同意测试' authorization after manager HEL-867 review lifted the stop gate - criteria/fixtures/orchestration untouched at
e06dcaf
(driver only captures per-call raw input/sent-context/answers and writes per-scenario outputs, never overwriting ab_scenarios.json); preflight zero-embed zero-network audit861_reuse868 + audit867_reuse868 both exit 0 with prior evidence and ledgers unchanged; 13/13 calls sent HTTP 200 (ADD1-5 anchored real extraction + QA1-8), real ledger continued on a SQLite-consistent backup of the original 26-row ledger (prefix line digest 03f92557 identical, original read-only preserved) now 39/60, embed ledger 458->498/500 (+40 dense, pre-computed debit guard held), usage 163041 tokens recorded per call; honest per-scenario results: S1/S4/S5/S8/S9 pass, S2/S3 mem0 side and S7 fail fail-closed because base-group batch-anchored infer hits carry the unshared t1 companion row in the group anchor and companion_unshared rejects them at every exit (zero leak markers in all sent contexts - the gate holds; row-level provenance for batch extractions is our adaptation gap, not visible to offline row-anchored fake payloads), S3 retrieval layer strictly better re-confirmed (11:11 target hits vs baseline 0:0) but model-use verdict fails without the gated content, S6 orchestration/status-in-block/unresolved-contrast all pass while both real answers are descriptive '资料里说...' unsupported by the pre-declared bounded grammar and honestly fail closed; no rerun, no criteria relaxation, no debug requests, no merge, no deploy; dual-target requirement checks 4/4 pass with handoff-HEL-868.json
2026-10-26 03:49:33 +08:00
reuse-hel847
HEL-847 v4: Mem0 capability corrections per manager review - additive-only infer, backend filter/BM25 facts, pre-isolation privacy design, concrete spike spec
2026-10-25 22:23:53 +08:00
rework
HEL-825 review: link-card accessible-name selector fix (browser_check), evidence scripts, regenerated screenshots/recordings
2026-10-24 08:27:06 +08:00
01-membrane.png
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
2026-10-19 20:33:13 +08:00
02-heartbeat.png
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
2026-10-19 20:33:13 +08:00
03-memory.png
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
2026-10-19 20:33:13 +08:00
04-title.png
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
2026-10-19 20:33:13 +08:00
intro.html
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
2026-10-19 20:33:13 +08:00
preview.webp
docs: intro animation for 晚晚 (22s, pure canvas, zero assets)
2026-10-19 20:33:13 +08:00
SPEC.md
feat(think): four-tier model routing with budget guard
2026-10-19 20:14:41 +08:00