Skip to content

Integrate evidence reliability, atomic correction and offline decision replay - #20

Merged
k2jac9 merged 51 commits into
mainfrom
feat/evidence-reliability-20261115
Nov 16, 2026
Merged

k2jac9 merged 51 commits into
mainfrom
feat/evidence-reliability-20261115

Conversation

@k2jac9

@k2jac9 k2jac9 commented Nov 16, 2026 •

Copy link
Copy Markdown
Owner

Stored agent results need inspectable eligibility decisions and atomic correction when evidence changes. This integrates the reviewed Rust/SQLite reliability work: a shared current-read explanation, expected-epoch admission batches, a Store-backed semantic fixture, authorized decision export/replay, evaluated policy activation, bounded offline diagnostics, and source-bound runtime qualification.

The original 48 implementation/verification commits are preserved. Review in the seven groups in docs/reliability-review-guide.md; later fixes belong with the implementations they correct.

Hosted verification at afd8c5d9a65167abdc2a8c8c112416b9a3e91847: all five runtime lanes passed, each with 362 Rust tests, 378 script tests, 18 reference and eight oracle checks, plus explicit integration/example stages. No warnings or test skips appeared in the retained logs. The separate previous-version checkout job passed. PR run · push run.

The hosted run exposed ambient library paths in test fixtures, a scheduling-dependent receipt test, and a prepared-worker test that assumed a claim within two seconds. The prepared-worker regression now waits for a real durable claim before advancing only its supervisor test clock. Corrections preserve production refusal and accounting rules; the new refusal regression and deterministic receipt tests passed locally, followed by the full hosted matrix. Checkout pins official v7.0.1 and separately checks v6.1.0; no current upcoming preview was available. Independent review of this integration correction found no actionable issues. See docs/hosted-integration.md for exact boundaries and retained failures.

These are offline contract results, not new model-quality measurements. PR #18's hosted adapter and PR #19's measured report remain separate. This PR performs no live database migration, provider request or model training. The unrecoverable historical superseded preflight display remains documented; newer successful verification does not reconstruct it.

@k2jac9
k2jac9 marked this pull request as ready for review November 16, 2026 05:49
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 16, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-16T06:05:38.200489Z afd8c5d New commits
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@k2jac9
k2jac9 merged commit 7807577 into main Nov 16, 2026
12 checks passed
@k2jac9
k2jac9 deleted the feat/evidence-reliability-20261115 branch November 16, 2026 07:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant