Commit graph

655 commits

Author SHA1 Message Date
twentyOne2x
4c4b3eb82f Replay PostgreSQL role and ACL parity 2026-07-16 12:32:02 +02:00
twentyOne2x
34e91db86d Merge remote-tracking branch 'origin/main' into codex/leo-gcp-data-parity-acl-preflight-20260715 2026-07-16 12:10:04 +02:00
twentyOne2x
7679416ef3
Merge pull request #175 from living-ip/codex/leo-m3taversal-name-policy-w2-20260715
Some checks are pending
CI / lint-and-test (push) Waiting to run
Enforce Telegram visible-handle name provenance
2026-07-16 12:06:47 +02:00
twentyOne2x
c8f6481fc7
Merge pull request #174 from living-ip/codex/leo-integrated-learning-loop-w2-20260715
Add isolated Leo integrated-learning lifecycle
2026-07-16 12:06:44 +02:00
twentyOne2x
42c32d5242
Merge pull request #170 from living-ip/codex/leo-observatory-private-staging-followup-w2-20260715
Harden private Observatory staging preflight
2026-07-16 12:06:41 +02:00
twentyOne2x
290737e347
Merge pull request #178 from living-ip/codex/leo-semantic-benchmark-candidate-v4-20260716
Some checks are pending
CI / lint-and-test (push) Waiting to run
Combine blinded benchmark with evidence-backed Leo reasoning
2026-07-16 11:52:31 +02:00
twentyOne2x
2712e7fbb5 Harden Leo benchmark semantic invariants 2026-07-16 11:38:51 +02:00
twentyOne2x
3b0e1bc296 Harden Leo DB contract correction path 2026-07-16 10:38:58 +02:00
twentyOne2x
31782d9b38 Accept semantic Leo benchmark paraphrases 2026-07-16 09:20:52 +02:00
twentyOne2x
bc88fcccbd Require fresh calls in Leo receipt probes 2026-07-16 08:59:57 +02:00
twentyOne2x
dcd31f5862 Use provider-compatible Leo read schema 2026-07-16 08:53:53 +02:00
twentyOne2x
9a77615e06 Reassert Leo read-only tools after runner init 2026-07-16 08:49:51 +02:00
twentyOne2x
226b4f7323 Harden Leo benchmark with structured KB reads 2026-07-16 08:41:12 +02:00
twentyOne2x
9f7913eaec Preserve live trial results across cleanup timeouts 2026-07-16 07:29:06 +02:00
twentyOne2x
b59bee8844 Fix Leo restart truth and read command reliability 2026-07-16 07:14:31 +02:00
twentyOne2x
021aaf6f09 Harden blind scoring for natural Leo replies 2026-07-16 06:13:53 +02:00
twentyOne2x
8cbda55435 Preserve subject and memory boundaries in Leo replies 2026-07-16 05:59:09 +02:00
twentyOne2x
3cbbbfaa18 Harden broad Leo database reasoning contracts 2026-07-16 05:44:21 +02:00
twentyOne2x
813d4cd91d Harden blinded Leo reasoning repair gate 2026-07-16 05:19:50 +02:00
twentyOne2x
4daa7853fe Integrate evidence-backed Leo reasoning candidate 2026-07-16 01:14:00 +02:00
twentyOne2x
00ef6b6dd1 Integrate blinded Leo benchmark candidate 2026-07-16 01:09:02 +02:00
twentyOne2x
27fbfa49a9
Accept receipt-bound natural answers in the Leo OOS scorer (#172)
* Make OOS scoring accept receipt-bound natural answers

* Test short-ID causal attribution in OOS ablation

* Close OOS provenance and schema qualifier gaps
2026-07-15 23:44:46 +02:00
twentyOne2x
e53948781d Harden private Observatory runtime identity 2026-07-15 23:05:24 +02:00
twentyOne2x
2631dcf4a5 Merge remote-tracking branch 'origin/main' into codex/leo-observatory-private-staging-followup-w2-20260715 2026-07-15 22:58:40 +02:00
twentyOne2x
aa7806587b Enforce Telegram visible-handle name provenance 2026-07-15 22:49:20 +02:00
twentyOne2x
dfd73b1cfa
feat: emit deterministic Leo identity version manifest (#169)
Some checks are pending
CI / lint-and-test (push) Waiting to run
2026-07-15 22:45:49 +02:00
twentyOne2x
8bb10e5c94 Add isolated Leo learning lifecycle 2026-07-15 22:45:45 +02:00
twentyOne2x
de7c139132 Preserve role ACLs in canonical parity preflight 2026-07-15 22:45:39 +02:00
twentyOne2x
0296176355 Fail closed on cross-provider WIF mappings 2026-07-15 22:45:24 +02:00
twentyOne2x
1a3c7fa9f4 Harden private Observatory staging preflight 2026-07-15 22:39:31 +02:00
twentyOne2x
f8a9e2831a Harden Leo against schema-contract contradictions 2026-07-15 22:36:22 +02:00
twentyOne2x
1472c8513a
Prepare Telegram exports for deterministic KB reconstruction (#168)
Some checks are pending
CI / lint-and-test (push) Waiting to run
2026-07-15 21:38:27 +02:00
twentyOne2x
ef1010c8f5 Keep challenger DB limits compatible with OOS retrieval 2026-07-15 21:25:54 +02:00
twentyOne2x
a3cce93d33 Guide Leo through evidence-backed claim challenges 2026-07-15 21:23:30 +02:00
twentyOne2x
56ad1c41dc
Merge pull request #165 from living-ip/codex/leo-observatory-private-staging-t3-w2-20260715
Some checks are pending
CI / lint-and-test (push) Waiting to run
Restore Observatory staging federation route
2026-07-15 21:22:51 +02:00
twentyOne2x
1352a825b9
Merge pull request #166 from living-ip/codex/leo-gcp-data-parity-t3-w2-20260715
Restore read-only GCP IAP status route
2026-07-15 21:22:39 +02:00
twentyOne2x
a30f48415a Bind Leo responses without masking semantic failures 2026-07-15 21:21:17 +02:00
twentyOne2x
8e198a791b Ground Leo reasoning in bounded live retrieval 2026-07-15 21:21:06 +02:00
twentyOne2x
b7197d6719 Restore Observatory staging federation route 2026-07-15 21:19:59 +02:00
twentyOne2x
9cd4a830cc Restore read-only GCP IAP status route 2026-07-15 21:19:59 +02:00
twentyOne2x
b6efa6c4a3 Keep challenger DB limits compatible with OOS retrieval 2026-07-15 13:10:15 +02:00
twentyOne2x
4d3e4afe21 Merge remote-tracking branch 'origin/pr-160' into HEAD 2026-07-15 13:04:29 +02:00
twentyOne2x
9a5305f386
Merge pull request #152 from living-ip/codex/leo-agent-challenger-loop-20260715
Some checks are pending
CI / lint-and-test (push) Waiting to run
Prove isolated Leo agent-challenger revision loop
2026-07-15 12:56:39 +02:00
twentyOne2x
68038d5f62 test: retain accepted Leo challenger proof 2026-07-15 12:33:15 +02:00
twentyOne2x
7bdca5d992
Merge pull request #164 from living-ip/codex/leo-oos-reasoning-benchmark-review-fix-20260715
Harden OOS benchmark proof boundaries
2026-07-15 12:09:20 +02:00
twentyOne2x
8a4325f42a Harden OOS benchmark provenance and leakage checks 2026-07-15 12:06:35 +02:00
twentyOne2x
977f4224d2
Merge pull request #161 from living-ip/codex/leo-gcp-data-parity-20260715
Some checks are pending
CI / lint-and-test (push) Waiting to run
Bind canonical snapshots to the private GCP parity lifecycle
2026-07-15 11:03:51 +02:00
twentyOne2x
1c6b7b182e Pin lifecycle receipts to the reviewed parity manifest 2026-07-15 10:59:43 +02:00
twentyOne2x
52fc0a88fe Normalize database authorization parity and validate hashes 2026-07-15 10:49:55 +02:00
twentyOne2x
cbcb293c10 Merge remote-tracking branch 'origin/main' into codex/leo-agent-challenger-loop-20260715 2026-07-15 10:34:04 +02:00