Files
Bo e1fae0dae6 Make the engineering harness lean and add optional topic memory (#1116)
RPI now owns the authorized outcome through finish, with Plan and Memory
loaded only when useful. Known defects get direct repair, and evidence
can change the approach under unchanged acceptance. Fresh exact-content
validation remains required. Memory provides optional recall, mining and
curation of reviewed topic pages; specialists and the fixed-dispatch
adapter remain optional.

The change reconciles current documentation and generated skill
projections. It preserves native budget and permission authority, BD
work ownership, protected external evidence storage and the distinction
between a supported lesson and demonstrated later benefit. It adds no
scheduler, work store, Go command or evidence schema.

Validation: required local Go/build/vet/race checks, aggregate suite,
generated-output check and 72 gates pass. The complete 44-test executor
suite passes; its shared-deadline fixture now tolerates CI scheduling
jitter while still requiring deadline exhaustion and preventing a third
launch. Fresh author-distinct review passed all 112 changed paths with
no findings; all seven exact-head CI checks passed at bfce33cce. Native
restricted-source enforcement and reduced token use are not established
by this change.
2026-09-09 10:10:29 -04:00

1.1 KiB

FAQ

Is AgentOps CI or a merge queue?

No. It produces engineering intent and independent semantic evidence. Your repository owns Git, CI, merging, release, and deployment.

What happens after FAIL or NOT_PROVEN?

Repair known findings within accepted scope and real remaining bounds, then validate the changed subject freshly. A genuine causal stall gets at most one bounded fresh helper. Stop on completed acceptance, cancellation, refusal, a spent real bound or unresolved stall; report unfinished acceptance honestly.

Must I use multiple models?

No. A fresh subagent with a distinct declared context identity is the default independent validator. Councils and mixed-model strategies are optional.

Must I use the ao CLI?

No. The semantic loop and content manifest are designed to work without Git or ao. The CLI provides repository-specific deterministic tools.

Where does learning happen?

Memory optionally recalls reviewed topic pages or separately mines authorized episodes and curates supported claims. Learn is a compatible mining entrypoint. Neither is required for a verdict or can change completed product judgment.